$ak:coding-level
/ak:coding-level [0-5]
Set coding experience level for tailored output. Use for adjusting explanation depth, code complexity, and response format to user expertise.
Open visual guide →[0-5] Skills cheatsheet
AgentKit Skills — Engineer & Marketing
Skill catalog by workflow group, with subcommands, args, and flags. Claude Code & Cursor: /ak:<skill> · Codex: $ak:<skill>.
Engineer = core + engineer skills. Marketing owns domain skills. Do not assume 1:1 with /ck:*. Syntax from kit argument-hint and SKILL.md.
103
Engineer
83
Marketing
/ak: · $ak:
Syntax
Chip legend
archive Subcommand
Skill branch: /ak:plan archive
[task] Argument
Positional / placeholder args
--fast Flag
Dash options like --flag
hint argument-hint
Full syntax from SKILL.md
Beta Preview — what is new in beta
New skills and notable upgrades in beta, not yet in the stable kit. Brand-new skills also get a BETA badge in the groups below.
/ak:docs enhanced $ak:docs
New philosophy mode (runs only when you ask for it): reads the repo and this project's past sessions, interviews you about product principles, then writes only the exact change you approve. Ordinary docs runs never read session history.
philosophy /ak:test enhanced $ak:test
Verification-first rework: before adding tests it states what must hold, the risk, and which existing check already covers it; reuses earlier results only when code, config and environment still match; decides when to add, merge or retire tests; never weakens tests or gates to get a green run. optimize and audit no longer fan out parallel scouts by default.
/ak:skill-creator enhanced $ak:skill-creator
Leaner skill guidance: first checks whether a new skill is really needed or an existing skill, reference or script is enough; keeps SKILL.md focused on outcome, limits and known failure modes; moves catalogs and examples into references. One production standard is now the authoring contract, and a report script summarizes standard warnings across many skills at once.
/ak:ak enhanced $ak:ak
Knows the newer beta CLI: the ak insights work commands for tracking improvement work (verify only compares recorded evidence; finishing a plan is not proof of improvement), safer login (no piping an email code into a headless login; use the API-key route instead), and setup that keeps your saved telemetry choice instead of asking again. It reads ak describe <command> --json for a command's flags, exit codes and risk before scripting it, and when a fresh install plan stops on risks it shows you each risk and reruns with --accept-risks only after you accept that exact list.
/ak:brainstorm enhanced $ak:brainstorm
New opt-in --ak-render: builds the HTML brief with the AK Render compiler instead of hand-writing it. It implies --html, and a project .ak-render/ folder turns it on too.
--ak-render /ak:explain enhanced $ak:explain
New opt-in --ak-render: builds the visual explanation page from a page spec with the pinned AK Render CLI. It implies --html, and a project .ak-render/ folder turns it on too.
--ak-render /ak:plan enhanced $ak:plan
New opt-in --ak-render: compiles plan.html from plan.page.yaml with the pinned AK Render CLI instead of hand-writing it. It implies --html, and a project .ak-render/ folder turns it on too.
--ak-render /ak:preview enhanced $ak:preview
New opt-in --ak-render: compiles --explain, --diff, --plan-review or --recap HTML from a page spec with AK Render. It implies --html, and a project .ak-render/ folder turns it on too.
--ak-render /ak:diagram enhanced $ak:diagram
Diagrams can now be embedded in pages that other skills build with AK Render: a wrapper script compiles the whole page with the diagram inside. The diagram compiler itself stays offline; only the first run downloads the pinned AK Render package from npm.
/ak:orchestrate enhanced $ak:orchestrate
States which parts work off macOS: planning, probing and in-session subagent jobs run on Linux and Windows too, while jobs that need a supervised CLI or Pi process are reported blocked with the platform reason instead of being refused outright or run unsupervised.
Start Here (Essentials)
Core path: Level → Ask → Brainstorm → Plan → Preview → Execute
2 /ak:ask
$ak:ask
/ak:ask [technical-question] [--yagni]
Answer technical and architectural questions with expert analysis. Use for design decisions, best practices evaluation, solution comparison.
Open visual guide →[question] --yagni $ak:brainstorm
/ak:brainstorm [topic or problem] [--advice] [--html] [--report] [--ultra] [--yagni] [--no-antv|--no-diagram-design|--no-editorial-visuals]
Turn unclear intent into an accepted outcome and compare viable approaches before delivery.
Open visual guide →[topic or problem] --advice--html--no-antv--no-diagram-design--no-editorial-visuals--report--ultra--yagni $ak:plan
/ak:plan [task] [--fast|--hard|--deep|--parallel|--two|--debate|--ultra] [--tdd|--no-tasks] [--html] [--github] [--wiki] [--advice] [--yagni] [--skip-journal] [--no-antv|--no-diagram-design|--no-editorial-visuals] OR [archive|red-team|validate]
Create, validate or review implementation plans with acceptance criteria and executable phases. Use for planning and roadmaps; implementation belongs to cook.
Open visual guide →archivered-teamvalidate [task] --advice--debate--deep--fast--github--hard--html--no-antv--no-diagram-design--no-editorial-visuals--no-tasks--parallel--skip-journal--tdd--two--ultra--wiki--yagni $ak:preview
/ak:preview [path] OR [--html] --explain|--slides|--diagram|--ascii [topic] OR --html --diff|--plan-review|--recap [--no-antv|--no-diagram-design|--no-editorial-visuals]
View files or generate visual explanations, slides, and diagrams. Use for code walkthroughs, architecture visualization, HTML/Markdown presentations.
Open visual guide →[path][topic] --ascii--diagram--diff--explain--html--no-antv--no-diagram-design--no-editorial-visuals--plan-review--recap--slides $ak:cook
/ak:cook [task|plan-path] [--interactive|--fast|--parallel|--auto|--no-test] [--tdd] [--advice] [--yagni] [--skip-journal]
Implement features, plans, and fixes with structured workflow. Use for feature development, plan execution, code implementation pipelines.
Open visual guide →[task|plan-path] --advice--auto--fast--interactive--no-test--parallel--skip-journal--tdd--yagni $ak:advise
/ak:advise [prompt-or-url] [--html] [--md] [--wiki] [--github] [--agent] [--ultra] [--yagni] [--no-antv|--no-diagram-design|--no-editorial-visuals]
Interview until user and agent share the same picture of the outcome, preview it visually, then deliver evidence-backed technical advice. Use for advisory interviews and second opinions; implementation belongs to a delivery workflow.
Open visual guide →[prompt-or-url] --agent--github--html--md--no-antv--no-diagram-design--no-editorial-visuals--ultra--wiki--yagni $ak:vibe
/ak:vibe [--ship] [--beta] [--both] [--advice] [--ultra] <github-issue-url | feature request>
Run the full vibe pipeline from request intake to PR readiness, with optional merge and post-merge CI convergence. Orchestrates worktree, plan, cook/fix, code-review, ship, and review-pr, integrating debug, research, test, and docs. Supports dual-stage beta-then-stable ships via --both, ultra verifier mode via --ultra, and kongming advisory supervision via --advice.
Open visual guide →<github-issue-url | feature request> --advice--beta--both--ship--ultra /ak:bro NEW
$ak:bro
/ak:bro [last message | topic to simplify]
Restate the assistant's last message in simpler, shorter, jargon-free language. Use when the user says ak:bro, simplify that, say it plainly, or explain it like a human.
Open visual guide →[last message | topic to simplify] Plan & Research
Brainstorming, planning, advisory, and codebase exploration
$ak:autoresearch
/ak:autoresearch <goal or hypothesis> [--iterations N] [--metric <metric>]
Route bounded, goal-directed iteration to the AgentKit skill that owns the desired outcome.
Open visual guide →<goal or hypothesis> --iterations--metric $ak:codex-goal
/ak:codex-goal <objective | goal draft>
Guide long-running Codex goal work with a verifiable stop condition. Use when users mention /goal, goal mode, durable objectives, or autonomous multi-turn Codex runs.
Open visual guide →objective $ak:fable-thinking
/ak:fable-thinking [task or question to reason through]
Reasoning protocol distilled from Claude Fable 5.1 — evidence-grounded claims, multi-hypothesis diagnosis, adversarial self-review, calibrated outcome-first delivery. Its Floor check catches simple-looking trick questions models answer confidently wrong; its Constraint Loop mechanically verifies banned letters, exact counts, and strict formats.
Open visual guide →[task or question to reason through] $ak:goal-warmup
/ak:goal-warmup "<goal>" [--fast]
Outcome-locked preflight before long-running /goal or autonomous runs. Interview to a user-approved Outcome Contract, plan without silent scope drift, contract-preserving review, whole-plan preflight matrix, then Ready/Blocked/Decision handoff. Never auto-starts /goal. Use for goal warmup, goal prepare, long-running goal prep, outcome lock, execution readiness.
Open visual guide →<goal> --fast $ak:issue-to-plan
/ak:issue-to-plan <github-issue-url | issue-number> [--repo owner/name] [--plan-ready-label <name>] [--decision-label <name>]
Turn a GitHub issue into an audited, validated implementation plan. Reads the issue, scouts the codebase, runs a hard brainstorm gate, and only then plans with mandatory --html --wiki, validate, and red-team, before pushing a plan branch and handing off on the issue. Use to convert a GitHub issue into a validated plan that is ready for plan audit.
Open visual guide →<github-issue-url | issue-number> --decision-label--plan-ready-label--repo $ak:predict
/ak:predict <feature description or change proposal> [--files <glob>] [--chain reason|probe]
5 expert personas debate proposed changes before implementation. Catches architectural, security, performance, and UX issues early. Use before major features or risky changes.
Open visual guide →<feature description or change proposal> --chain--files $ak:problem-solving
/ak:problem-solving [problem description] [--ultra]
Apply systematic problem-solving techniques when stuck. Use for complexity spirals, innovation blocks, recurring patterns, assumption constraints, simplification cascades, scale uncertainty.
Open visual guide →[problem description] --ultra $ak:research
/ak:research [topic] [--ultra] [--yagni]
Research technical solutions, analyze architectures, gather requirements thoroughly. Use for technology evaluation, best practices research, solution design, scalability/security/maintainability analysis.
Open visual guide →[topic] --ultra--yagni $ak:research-prompt
/ak:research-prompt <research topic | decision>
Draft a self-contained research brief for a human or AI researcher. Use when users ask for a research prompt, research brief, or a deep-research task to hand off.
Open visual guide →decision /ak:scout COMMON
$ak:scout
/ak:scout [search-target] [ext] [--ultra]
Fast codebase scouting using native search, optional Explore agents, and user-permitted OpenCode probes. Use for file discovery, task context gathering, and scoped searches across directories.
Open visual guide →[search-target][ext] --ultra /ak:sowat NEW
$ak:sowat
/ak:sowat [recent-changes|issue|PR]
Analyze recently implemented work and related issues like a product owner. Use to identify high-impact next steps, challenge weak priorities, and explain what matters now.
Open visual guide →[recent-changes|issue|PR] Design & Frontend
UI/UX, frontend, diagrams, and visual tools
$ak:design
/ak:design [design-type] [context]
Design brand identity, logos, banners, posters, and visual assets. Use for brand systems, design tokens, corporate identity programs, event/editorial/marketing posters, and visual campaign assets. Not for UI code patterns.
Open visual guide →[design-type][context] $ak:diagram
/ak:diagram [input-file] [--format <svg|fragment|html>] [--preset <classic|signal-flow|blueprint|editorial>] [--theme <light|dark>] [--out <path>]
Compile typed JSON IR into validated interactive system maps and self-contained HTML readers. Use for architecture, workflow, sequence, dataflow and lifecycle maps; use editable-canvas or publication-diagram skills for those artifacts.
Open visual guide →[input-file] --format--out--preset--theme $ak:enhance-ux-ax
/ak:enhance-ux-ax [url|path|focus] [--auto] [--loop [N]]
Combined UX + AI-experience (AX) review of an existing site or app: scores brand recall, punchy content, motion and responsive layouts, scans SEO/GEO discovery surfaces (sitemap, robots, llms.txt, per-URL markdown, schema, social cards, copy/share/send-to-AI actions), and writes ranked proposals with an explicit DONE contract. --auto implements them; --loop [N] repeats review-to-verify rounds with screenshot vision checks. For a UI-polish-only audit or new UI use ak:frontend-design; for an SEO/GEO-only audit or keyword research use ak:seo.
Open visual guide →[url|path|focus] --auto--loop $ak:excalidraw
/ak:excalidraw [diagram description|path] [--export <png|svg>] [--live]
Create Excalidraw diagrams — architecture, data flow, workflows, system design. Use when user wants to visualize, diagram, draw architecture, show data flow, create flowcharts, map components, or export .excalidraw files to PNG/SVG. Supports two modes: live MCP canvas (real-time) or file-based JSON + Playwright rendering. Also supports zero-config codebase auto-diagramming — just say "diagram this repo" or "visualize the architecture".
Open visual guide →[diagram description|path] --export--live $ak:frontend-design
/ak:frontend-design [prompt|image-path|component|url]
Create polished frontend interfaces with deliberate art direction, from a brief, design, screenshot or video, and audit live products for UI/UX polish. Use for landing pages, product/dashboard UI, web components, 3D experiences, replicating UI designs, quick prototypes, immersive interfaces, avoiding AI slop, and hands-on UX audits of dev/staging/production apps across desktop, tablet and mobile.
Open visual guide →[prompt|image-path|component|url] $ak:frontend-development
/ak:frontend-development [component or feature]
Build React/TypeScript frontends with modern patterns. Use for components, Suspense, lazy loading, useSuspenseQuery, MUI v7 styling, TanStack Router, performance optimization.
Open visual guide →[component or feature] $ak:mermaidjs-v11
/ak:mermaidjs-v11 [diagram-type or description]
Create diagrams with Mermaid.js v11 syntax. Use for flowcharts, sequence diagrams, class diagrams, ER diagrams, Gantt charts, state diagrams, architecture diagrams, timelines, user journeys.
Open visual guide →[diagram-type or description] $ak:page-builder
/ak:page-builder [setup|update|operate] [project-path] [request]
Build, extend, or operate a dynamic page builder using a project's components and stack. Use for configurable resizable widgets, responsive touch editors, previews, publishing, and agent interfaces with a project operator skill. Not for one-off page design or a generic API wrapper.
Open visual guide →setupupdateoperate [project-path][request] $ak:react-best-practices
/ak:react-best-practices [component or pattern]
Apply React and Next.js performance optimization patterns from Vercel Engineering. Use for component optimization, rendering performance, bundle analysis.
Open visual guide →[component or pattern] $ak:shader
/ak:shader [effect or pattern]
Write GLSL fragment shaders for procedural graphics. Topics: shapes (SDF), patterns, noise (Perlin/simplex/cellular), fBm, colors (HSB/RGB), matrices, gradients, animations. Use for generative art, textures, visual effects, WebGL, Three.js shaders.
Open visual guide →[effect or pattern] $ak:show-off
/ak:show-off [markdown-or-prompt] [--no-antv|--no-diagram-design|--no-editorial-visuals]
Create preference-aware self-contained HTML pages to showcase work. Use for demos, visual presentations, interactive showcases.
Open visual guide →[markdown-or-prompt] --no-antv--no-diagram-design--no-editorial-visuals $ak:stitch
/ak:stitch [design prompt or action]
AI design generation with Google Stitch. Generate UI designs from text prompts, export Tailwind/HTML/DESIGN.md, orchestrate design-to-code pipeline. Use for rapid prototyping, UI generation, design exploration.
Open visual guide →[design prompt or action] $ak:tech-graph
/ak:tech-graph [diagram-type or system description]
Generate production-quality SVG+PNG technical diagrams — architecture, data flow, flowchart, sequence, agent/memory, or concept maps — across 7 visual styles. Use when user wants "generate diagram", "draw diagram", "visualize", "architecture diagram", "flowchart", or any system/flow they want illustrated. Pairs with /ak:preview --diagram for visual self-review and /ak:mermaidjs-v11 for inline-doc diagrams; this skill is the publish-grade output mode.
Open visual guide →[diagram-type or system description] $ak:threejs
/ak:threejs [3D scene or feature]
Build 3D web experiences with Three.js. Use for WebGL/WebGPU scenes, GLTF models, animations, physics, VR/XR.
Open visual guide →[3D scene or feature] $ak:ui-styling
/ak:ui-styling [component or layout]
Style UIs with shadcn/ui components (Radix UI + Tailwind CSS). Use for accessible components, themes, dark mode, responsive layouts, design systems, color customization.
Open visual guide →[component or layout] $ak:ui-ux-pro-max
/ak:ui-ux-pro-max [component|page|design-system] [--style <style>] [--framework <fw>]
UI/UX design intelligence for web and mobile: style selection, color systems, typography, layout, accessibility, interaction states, responsive behavior, forms, charts, design systems, and code review across React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS.
Open visual guide →[component|page|design-system] --framework--style $ak:webmcp
/ak:webmcp [page, form, or feature to expose as a tool]
Build agent-ready websites with browser WebMCP tools, schemas, safety annotations, and evals. Use for page actions and agent-callable forms; server MCP belongs to ak:mcp-builder.
Open visual guide →[page, form, or feature to expose as a tool] AI Generation & Multimodal
Image/video generation, vision, and media processing
$ak:ai-artist
/ak:ai-artist [concept] [--mode search|creative|wild|all] [--provider auto|google|openrouter] [--skip]
Generate product mockups, marketing assets, brand visuals, and concept art via Nano Banana with 129 curated prompts. Reuse supplied style, mood, and color constraints; ask only for missing consequential choices. 3 modes: search, creative, wild. Styles: Ukiyo-e, Bento grid, cyberpunk, cinematic, vintage patent.
Open visual guide →[concept] --mode--provider--skip $ak:ai-multimodal
/ak:ai-multimodal [file-path] [prompt]
Analyze and generate image, audio, video, and document content. Prefers the active model's native vision for image/document understanding; falls back to the npm-latest Multix CLI and live provider catalogs only when native vision is ineligible or a generation/audio/video task needs a configured provider.
Open visual guide →[file-path][prompt] $ak:hyperframes
/ak:hyperframes [composition or command]
Wrap HeyGen HyperFrames CLI for HTML-first programmatic video generation. Use for short vertical/social videos, product-launch clips, motion graphics rendered from HTML composition. See also the installed remotion skill for a React-based alternative.
Open visual guide →[composition or command] $ak:media-processing
/ak:media-processing [input-file] [operation]
Process media with FFmpeg (video/audio), ImageMagick (images), RMBG (AI background removal). Use for encoding, format conversion, filters, thumbnails, batch processing, HLS/DASH streaming.
Open visual guide →[input-file][operation] $ak:remotion
/ak:remotion [video or component]
Build video content with Remotion in React. Use for programmatic video creation, animated sequences, data-driven video rendering.
Open visual guide →[video or component] Build & Ship
Backend, frameworks, deploy, and ship pipelines
$ak:agentize
/ak:agentize [feature-or-module] [--both|--mcp|--cli] [--auto|--ask] [--ultra] [--advice] [--yagni]
Expose existing code or APIs through an agent-friendly CLI, MCP server, or both. Choose the surface and deployment scope from the user’s task and existing project.
Open visual guide →[feature-or-module] --advice--ask--auto--both--cli--mcp--ultra--yagni $ak:backend-development
/ak:backend-development [framework] [task]
Build backends with Node.js, Python, Go (NestJS, FastAPI, Django). Use for REST/GraphQL/gRPC APIs, auth (OAuth, JWT), databases, microservices, security (OWASP), Docker/K8s.
Open visual guide →[framework][task] $ak:better-auth
/ak:better-auth [auth-method or feature]
Add authentication with Better Auth (TypeScript). Use for email/password, OAuth providers (Google, GitHub), 2FA/MFA, passkeys/WebAuthn, sessions, RBAC, rate limiting.
Open visual guide →[auth-method or feature] $ak:bootstrap
/ak:bootstrap [requirements] [--auto|--full|--fast|--parallel] [--ask] [--ultra] [--yagni] [--skip-journal]
Bootstrap new projects (web, mobile, CLI, API, MCP, WebMCP, libraries) from a locked scope straight to implementation via ak:cook, then ak:code-review, ak:enhance-ux-ax --auto for web surfaces, and optional release with live verification; no separate planning phase. Modes: auto (default, agent decides), full (interactive thorough), fast (skip research), parallel (multi-agent); --ask interviews the user via ak:advise until scope is locked.
Open visual guide →[requirements] --ask--auto--fast--full--parallel--skip-journal--ultra--yagni $ak:databases
/ak:databases [query or schema task]
Design schemas, write queries for MongoDB and PostgreSQL. Use for database design, SQL/NoSQL queries, aggregation pipelines, indexes, migrations, replication, performance optimization, psql CLI.
Open visual guide →[query or schema task] $ak:deploy
/ak:deploy [platform] [environment]
Deploy projects to any platform with auto-detection. Use when user says "deploy", "publish", "ship", "go live", "push to production", "host this app", or mentions any hosting platform (Vercel, Netlify, Cloudflare, Railway, Fly.io, Render, Heroku, TOSE, Github Pages, AWS, GCP, Digital Ocean, Vultr, Coolify, Dokploy). Auto-detects the deployment target from config files and documents or updates the project's existing deployment guide.
Open visual guide →[platform][environment] $ak:devops
/ak:devops [platform] [task]
Deploy to Cloudflare (Workers, R2, D1), Docker, GCP (Cloud Run, GKE), Kubernetes (kubectl, Helm). Use for serverless, containers, CI/CD, GitOps, security audit.
Open visual guide →[platform][task] /ak:fix COMMON
$ak:fix
/ak:fix [issue] --auto|--review|--quick|--parallel [--ultra] [--advice] [--skip-journal]
Fix bugs, errors, test failures, and CI/CD issues with intelligent routing. Use for type errors, lint issues, log errors, UI bugs, code problems.
Open visual guide →[issue] --advice--auto--parallel--quick--review--skip-journal--ultra $ak:loop
/ak:loop [Goal/Metric description] or inline config block
Autonomous iterative optimization loop — run N iterations against a mechanical metric, learn from git history, auto-keep/discard changes. Use for improving measurable metrics (coverage, performance, bundle size, etc.) through repeated experimentation.
Open visual guide →[Goal/Metric description] $ak:mobile-development
/ak:mobile-development [platform] [feature]
Build mobile apps with React Native, Flutter, Swift/SwiftUI, Kotlin/Jetpack Compose. Use for iOS/Android, mobile UX, performance optimization, offline-first, app store deployment.
Open visual guide →[platform][feature] /ak:ship COMMON
$ak:ship
/ak:ship [official|stable|main|beta|dev|next] [--both] [--advice] [--merge] [--skip-tests] [--skip-review] [--skip-journal] [--skip-docs] [--social] [--yes-post] [--yes-post-private] [--dry-run]
Ship a completed branch through tests, review, commit, push, and PR creation. Supports official/beta aliases, Kongming advice, and optional reviewed merge with CI convergence.
Open visual guide →officialstablemainbetadevnext --advice--both--dry-run--merge--skip-docs--skip-journal--skip-review--skip-tests--social--yes-post--yes-post-private $ak:tanstack
/ak:tanstack [framework] [feature]
Build with TanStack Start (full-stack React framework), TanStack Form (headless form management), and TanStack AI (AI streaming/chat). Use when creating TanStack projects, routes, server functions, forms, validation, or AI chat features.
Open visual guide →[framework][feature] $ak:web-frameworks
/ak:web-frameworks [framework] [feature]
Build with Next.js (App Router, RSC, SSR, ISR), Turborepo monorepos. Use for React apps, server rendering, build optimization, caching, shared dependencies, and SEO/GEO surfaces (sitemap, robots, llms.txt, .md page variants, social cards, JSON-LD, copy/share/open-in-AI actions).
Open visual guide →[framework][feature] Git & Version Control
Git ops, GitHub via gh, worktrees, and PR review
/ak:git COMMON
$ak:git
/ak:git cm|cp|pr|merge|merge-pr|stack [args]
Git operations with conventional commits. Use for staging, committing, pushing, PRs, merges, stacked PRs. Auto-splits commits by type/scope. Security scans for secrets.
Open visual guide →cmcpprmergemerge-prstack [args] $ak:github
/ak:github <task description or issue/PR ref> [--interactive] [--advice]
Operate and manage GitHub projects fluently with the gh CLI — create/update/close issues with evidence-backed dedup checks, manage labels, PRs (create, review, rebase, auto-merge), GitHub Projects, Actions CI/CD, and org/repo/environment/secret administration. Use whenever the user asks to file an issue, triage issues, manage a PR lifecycle, inspect CI runs, or administer repositories via gh.
Open visual guide →<task description or issue/PR ref> --advice--interactive $ak:review-pr
/ak:review-pr <PR number or URL> [<PR number or URL> ...] [--fix] [--reply] [--merge] [--advice] [--ultra]
Review GitHub pull requests for correctness, regressions and security. Optional fix, reply and merge modes authorize their respective delivery steps.
Open visual guide →<PR number or URL> --advice--fix--merge--reply--ultra $ak:worktree
/ak:worktree [feature-description] OR [project] [feature]
Create, inspect, and clean isolated git worktrees. Use for feature isolation, worktree health audits, stale cleanup, and monorepo or submodule workflows.
Open visual guide →createremoveinfoliststatusprune [feature-description][project][feature] Test & Debug
Testing, debugging, review, and scenarios
/ak:code-review COMMON
$ak:code-review
/ak:code-review [#PR | COMMIT | --pending | codebase [parallel]] [--ultra] [--advice] [--yagni]
Review code quality with evidence-based rigor. Supports input modes: pending changes, PR number, commit hash, and codebase scan. Focuses on bugs, regressions, maintainability, reliability, and verification gaps.
Open visual guide →[#PR][COMMIT][codebase] --advice--pending--ultra--yagni /ak:debug COMMON
$ak:debug
/ak:debug [error or issue description] [--ultra]
Debug systematically with root cause analysis before fixes. Use for bugs, test failures, unexpected behavior, performance issues, call stack tracing, multi-layer validation, log analysis, CI/CD failures, database diagnostics, system investigation.
Open visual guide →[error or issue description] --ultra $ak:deep-swe
/ak:deep-swe <OpenRouter model slug>
Benchmark a coding model on DeepSWE through Pier and OpenRouter. Use when users ask to run DeepSWE, score a model, or verify coding-agent benchmark results.
Open visual guide →<OpenRouter model slug> $ak:scenario
/ak:scenario <file path or feature description> [--iterations N] [--saturation]
Generate comprehensive edge cases and test scenarios by decomposing features across 12 dimensions. Use for pre-implementation risk discovery, QA planning, regression design, and bounded iterative exploration of coverage gaps.
Open visual guide →<file path or feature description> --iterations--saturation /ak:test COMMON
$ak:test
/ak:test [context] OR ui [url] OR create|optimize|audit [scope] [--advice] [--ultra] [--interview]
Run unit, integration, e2e, and UI tests. Use for test execution, coverage analysis, build verification, visual regression, and QA reports.
Open visual guide →uicreateoptimizeaudit [context][url] --advice--interview--ultra $ak:web-testing
/ak:web-testing [test-type] [target]
Web testing with Playwright, Vitest, k6. E2E/unit/integration/load/security/visual/a11y testing. Use for test automation, flakiness, Core Web Vitals, mobile gestures, cross-browser.
Open visual guide →[test-type][target] Security & Intelligence
Security audits, scans, and threat intel
$ak:cti-expert
/ak:cti-expert [target] [--yolo] [--case|--sweep|--query|--flow] [--format html|md] [--no-antv|--no-diagram-design|--no-editorial-visuals]
Analyze cyber threat intelligence and OSINT cases. Use for exposure reviews, domain recon, breach checks, username/email/phone research, image forensics, blockchain tracing, darknet checks, cloud tenant recon, vulnerability lookup, threat modeling, and structured reports.
Open visual guide →[target] --case--flow--format--no-antv--no-diagram-design--no-editorial-visuals--query--sweep--yolo $ak:security
/ak:security [scope] [--secrets-only] [--deps-only] [--fix] [--red-team] [--iterations N]
Scan codebase for security vulnerabilities, hardcoded secrets, dependency issues, and OWASP patterns, with optional STRIDE threat modeling, red-team persona discovery, and auto-fix. Use when asked to 'security scan', 'check for secrets', 'audit security', or before major releases.
Open visual guide →[scope] --deps-only--fix--iterations--red-team--secrets-only Docs & Content
Documentation, writing, and content tools
$ak:copywriting
/ak:copywriting [copy-type] [context]
Conversion copywriting formulas, headline templates, email copy patterns, landing page structures, CTA optimization, and writing style extraction. Activate for writing high-converting copy, crafting headlines, email campaigns, landing pages, or applying custom writing styles from assets/writing-styles/ directory.
Open visual guide →[copy-type][context] $ak:docs
/ak:docs init|update|summarize|agent-context|agents|llms
Analyze a codebase and create, refresh, summarize, or audit project documentation without imposing a fixed docs layout, with an opt-in classic layout via --preset classic, including authoring and optimizing the root CLAUDE.md/AGENTS.md agent context file, or distilling DO/DON'T rules for that file from git history, CI runs, and (with --source) current source-tree markers.
Open visual guide →initupdatesummarizeagent-contextagentsllms $ak:docs-seeker
/ak:docs-seeker [library-name] [topic]
Search library/framework documentation via llms.txt (context7.com). Use for API docs, GitHub repository analysis, technical documentation lookup, latest library features.
Open visual guide →[library-name][topic] $ak:document-skills
/ak:document-skills <docx|pdf|pptx|xlsx> [path] [action]
Read, create, and edit Office documents (docx, pdf, pptx, xlsx). Use for tables, forms, slides, spreadsheets.
Open visual guide →<docx|pdf|pptx|xlsx>[path][action] $ak:folder-context
/ak:folder-context <target-folder>
Create a compact subfolder CLAUDE.md and linked AGENTS.md for durable local conventions. Use when a folder needs agent context beyond the project root.
Open visual guide →<target-folder> $ak:interview-docs
/ak:interview-docs <vision | document-path | topic>
Extract a user's vision and decisions into durable project documents through a guided interview. Use for README, ADR, strategy, principles, and structured-doc authoring.
Open visual guide →<vision | document-path | topic> $ak:llms
/ak:llms [path|url] [--full] [--md-links] [--output path]
Generate llms.txt, llms-full.txt, and per-page .md variants from docs or codebase scanning, following the llmstxt.org spec. Use for LLM-friendly site indexes, Markdown page mirrors, documentation summaries, AI context optimization.
Open visual guide →[path|url] --full--md-links--output $ak:markdown-novel-viewer
/ak:markdown-novel-viewer [file-or-directory]
View markdown files in a calm, book-like reader served via HTTP. Use for long-form content review — RFCs, runbooks, design docs, reports, specs, novels — anywhere you want a distraction-free reading mode in the browser.
Open visual guide →[file-or-directory] $ak:mintlify
/ak:mintlify [task] [path]
Build and maintain Mintlify documentation sites. Covers docs.json, MDX components, navigation, page frontmatter, theming, OpenAPI/AsyncAPI, AI docs assets such as llms.txt and skill.md, deployment targets, and local validation CLI commands.
Open visual guide →[task][path] MCP & Integration
MCP servers, agents, payments, and integrations
$ak:agent-browser
/ak:agent-browser [url or task]
Automate tool-managed browsers with agent-browser for snapshots, clicks, forms and browser testing. Use chrome-profile when real Chrome account state is required.
Open visual guide →[url or task] $ak:chrome-profile
/ak:chrome-profile [url] [--profile <name>] [--tab <title|url>]
Target a real Google Chrome profile for browser automation through Chrome DevTools MCP. Provides the chrome-profile CLI, profile discovery, live DevTools probing guidance, setup playbooks, and URL-anchor tab selection.
Open visual guide →[url] --profile--tab $ak:google-adk-python
/ak:google-adk-python [agent or feature]
Build AI agents with Google ADK Python. Multi-agent systems, A2A protocol, MCP tools, workflow agents, state/memory, callbacks/plugins, Vertex AI deployment, evaluation.
Open visual guide →[agent or feature] $ak:mcp-builder
/ak:mcp-builder [service or API to integrate]
Build, upgrade, test and publish MCP servers that expose external services as tools. Covers MCP spec 2026-07-28, TypeScript SDK v2 and Python mcp v2 (MCPServer), tool design, OAuth, evaluations and the MCP Registry.
Open visual guide →[service or API to integrate] $ak:payment-integration
/ak:payment-integration [provider] [task]
Integrate payments with SePay and PayFS (Vietnamese bank transfers, VietQR), Polar, Stripe, Creem, Dodo Payments, Lemon Squeezy, Paddle, and PayPal. Checkout, webhooks, subscriptions, usage billing, license keys, QR codes, and multi-provider orders.
Open visual guide →[provider][task] $ak:shopify
/ak:shopify [extension-type] [feature]
Build Shopify apps, extensions, themes with Shopify CLI. Use for GraphQL/REST APIs, Polaris UI, Liquid templates, checkout customization, webhooks, billing integration.
Open visual guide →[extension-type][feature] $ak:team
/ak:team <template> <context> [--devs|--researchers|--reviewers N] [--delegate]
Orchestrate Agent Teams for parallel multi-session collaboration. Use for research, implementation, review, and debug workflows requiring independent teammates.
Open visual guide →<template><context> --delegate--devs--researchers--reviewers Session Management
Handoffs, dispatch, orchestration, journals, and context
$ak:context-engineering
/ak:context-engineering [topic or question]
Manage context, task budgets, compaction and model selection using outcome evidence. Use for token waste, context left, usage limits, slow or forgetful sessions, long tasks, compression evaluation, benchmark cost/duration/agent steps, memory and agent systems.
Open visual guide →[topic or question] $ak:handoff
/ak:handoff [task focus] [--output PATH] [--include-diff] [--include-status] [--force] [--dispatch --agent <id> [--handoff PATH] [--cwd PATH] [--model NAME] [--yes]]
Create a portable, redacted Markdown continuation contract that a fresh coding agent can consume to resume in-progress work safely, and optionally dispatch it to a selected coding runtime with --dispatch. Use when switching sessions, models, or runtimes, or when preserving decisions, verification state, and blockers.
Open visual guide →[next-session focus] --agent--cwd--dispatch--force--handoff--include-diff--include-status--model--output--yes $ak:journal
/ak:journal [topic or reflection]
Write chronological technical journals for session reflection and change analysis. Journals preserve work history; they do not replace current docs or ADRs.
Open visual guide →[topic or reflection] /ak:orchestrate NEW
$ak:orchestrate
/ak:orchestrate <job-spec.yaml | task description | --resume <run-dir>> [--yes] [--internal]
Coordinate staged or parallel jobs across live-verified coding-agent runtimes, Pi coding-agent sessions, and in-session subagents, using capability- and risk-based routing, worktree-isolated writes, resumable state, capture, safety gates, and independent arbiter review. Onboards a missing Pi runtime (install, profile, authentication, AgentKit projection) as a visible setup step when a job or the user asks for Pi.
Open visual guide →<job-spec.yaml | task description | --resume <run-dir> --internal--resume--yes /ak:sumup NEW
$ak:sumup
/ak:sumup [task|PR|branch|recent]
Summarize completed implementation, failures, workarounds, decisions, behavior, architecture, usage, follow-ups, and next steps. Use after implementation or for a technical recap.
Open visual guide →[task|PR|branch|recent] $ak:watzup
/ak:watzup [branch|worktree|status]
Generate short handoff reports from Git branches, remote refs, worktrees, unfinished plans, and roadmap docs. Surfaces priority-ranked next steps with checkbox progress and rationale. Use when the user asks what's in flight, wants progress/next steps, is in a fresh worktree or detached checkout, or needs end-of-session status.
Open visual guide →[branch|worktree|status] Project Tracking
Progress, kanban, and project organization
$ak:plans-kanban
/ak:plans-kanban [deprecated flags are accepted with warnings]
Open the AgentKit plans dashboard in the CLI config UI. Use for plan kanban views, progress tracking, timeline checks, and quick navigation into plan files.
Open visual guide →[deprecated flags are accepted with warnings] $ak:project-management
/ak:project-management [task: status, hydrate, sync, report]
Track progress, update plan statuses, coordinate runtime work, generate reports, and preserve cross-session continuity.
Open visual guide →[task: status, hydrate, sync, report] $ak:project-organization
/ak:project-organization [directories or files to organize]
Organize files, directories, and content structure in any project. Use when explicitly designing or reorganizing project structure, resolving a layout conflict, or organizing existing assets.
Open visual guide →[directories or files to organize] $ak:retro
/ak:retro [timeframe] [--compare] [--team] [--format html|md] [--no-antv|--no-diagram-design|--no-editorial-visuals]
Generate data-driven sprint retrospectives from any git history. Use for sprint reviews, commit analysis, code-health indicators, team-velocity reporting, and quarterly engineering reviews. Works on solo or team repos.
Open visual guide →[timeframe] --compare--format--no-antv--no-diagram-design--no-editorial-visuals--team Utilities
ak CLI, skill tools, packaging, and general utilities
$ak:agentkit
/ak:agentkit [task to route]
Task router for AgentKit installs. Classifies the task, activates the right installed skills, chains them into the shortest workflow that fits, and spawns installed subagents at defined trigger points to raise output quality. Use at the start of multi-step, multi-domain, or ambiguous work, or when unsure which skill or agent applies.
Open visual guide →[task to route] $ak:ak
/ak:ak [goal or subcommand]
Operate the ak control-plane CLI itself — the AgentKit binary that installs, inspects, updates, recovers, and removes kits and their skills. Use when the next action is invoking an ak subcommand (init, kit, skills, plan, journal, doctor, recover, self-update, login), deciding between read-only inspection and lifecycle mutation, disambiguating project vs global scope, or interpreting ak --json output. Not for authoring skills (use ak:skill-creator) or routing generic work (use ak:agentkit).
Open visual guide →[goal or subcommand] $ak:explain
/ak:explain [subject|path|URL] [--html] [--eli5]
Explain concepts, code, systems, errors, and documents with grounded evidence. Use --eli5 for plain-language analogies or --html for a visual explanation.
Open visual guide →[subject|path|URL] --eli5--html $ak:find-skills
/ak:find-skills [capability or task description]
Discover or install agent skills when users explicitly seek new capabilities or a verified capability gap blocks their task. Prefer the live installed catalog before external search.
Open visual guide →[capability or task description] $ak:gkg
/ak:gkg [symbol or query]
Semantic code analysis with GitLab Knowledge Graph. Use for go-to-definition, find-usages, impact analysis, architecture visualization. Supports Ruby, Java, Kotlin, Python, TypeScript/JavaScript.
Open visual guide →[symbol or query] $ak:graphify
/ak:graphify [path] [--mcp|--report|--watch]
Build queryable knowledge graphs from code, docs, papers, and images. Use for repeated relationship queries and architecture analysis when a reusable graph adds value beyond native search.
Open visual guide →[path] --mcp--report--watch $ak:help
/ak:help [topic|skill|command]
Open the AgentKit help index. Use when users ask how to use ak, what skills are available, or which workflow to run.
Open visual guide →[topic|skill|command] $ak:repomix
/ak:repomix [path] [--style xml|markdown|plain|json]
Pack repositories into AI-friendly files with Repomix (XML, Markdown, plain text). Use for new-project onboarding, codebase snapshots, LLM context preparation, security audits, third-party library analysis.
Open visual guide →[path] --style $ak:skill-creator
/ak:skill-creator <create|update|audit|optimize> [skill-name|path|kit|--all] [--kit <kit>|--project|--user] [--long-horizon] [--apply] [--from-audit <report>] [--advice]
Create, update, audit, validate, and package agent skills. Use when authoring SKILL.md resources or diagnosing skill routing and behavior. Not for implementing CLI or MCP servers.
Open visual guide →[skill-name|path|kit|--all] --advice--all--apply--from-audit--kit--long-horizon--project--user $ak:xia
/ak:xia <github-url-or-owner/repo|local-path> [feature] [--compare|--copy|--improve|--port] [--auto|--fast]
Extract, compare, port, or adapt a feature from a GitHub repository or local repo path into the current project. Use when the user wants to copy behavior from another repo, study how another codebase implements something, compare implementations, or rewrite a feature in the local stack. Triggers on: 'port from', 'copy from repo', 'like how X does it', 'clone feature from', 'adapt from', 'bring feature from', 'borrow from', 'take from repo', 'xia', 'xi a', 'xia feature'.
Open visual guide →local-path [feature] --auto--compare--copy--fast--improve--port No NEW skills in this kit
No COMMON skills in this kit
Beta Preview — what is new in beta
New skills and notable upgrades in beta, not yet in the stable kit. Brand-new skills also get a BETA badge in the groups below.
/ak:docs enhanced New philosophy mode (runs only when you ask for it): reads the repo and this project's past sessions, interviews you about product principles, then writes only the exact change you approve. Ordinary docs runs never read session history.
/ak:test enhanced Verification-first rework: before adding tests it states what must hold, the risk, and which existing check already covers it; reuses earlier results only when code, config and environment still match; decides when to add, merge or retire tests; never weakens tests or gates to get a green run. optimize and audit no longer fan out parallel scouts by default.
/ak:skill-creator enhanced Leaner skill guidance: first checks whether a new skill is really needed or an existing skill, reference or script is enough; keeps SKILL.md focused on outcome, limits and known failure modes; moves catalogs and examples into references. One production standard is now the authoring contract, and a report script summarizes standard warnings across many skills at once.
/ak:ak enhanced Knows the newer beta CLI: the ak insights work commands for tracking improvement work (verify only compares recorded evidence; finishing a plan is not proof of improvement), safer login (no piping an email code into a headless login; use the API-key route instead), and setup that keeps your saved telemetry choice instead of asking again. It reads ak describe <command> --json for a command's flags, exit codes and risk before scripting it, and when a fresh install plan stops on risks it shows you each risk and reruns with --accept-risks only after you accept that exact list.
/ak:brainstorm enhanced New opt-in --ak-render: builds the HTML brief with the AK Render compiler instead of hand-writing it. It implies --html, and a project .ak-render/ folder turns it on too.
/ak:explain enhanced New opt-in --ak-render: builds the visual explanation page from a page spec with the pinned AK Render CLI. It implies --html, and a project .ak-render/ folder turns it on too.
/ak:plan enhanced New opt-in --ak-render: compiles plan.html from plan.page.yaml with the pinned AK Render CLI instead of hand-writing it. It implies --html, and a project .ak-render/ folder turns it on too.
/ak:preview enhanced New opt-in --ak-render: compiles --explain, --diff, --plan-review or --recap HTML from a page spec with AK Render. It implies --html, and a project .ak-render/ folder turns it on too.
/ak:filmmaking new Long-form AI films (about 5-30 minutes) run as a production graph: character bibles, shot continuity, storyboard and animatic gates, audio-first dialogue, separate sound stems, and fixing one failed shot without re-rendering the film.
/ak:elevenlabs enhanced Now writes and directs the voice script, not just the audio: new script, enhance and dialogue actions turn an idea into a performance-ready script, add delivery tags to final copy without changing its words, or direct a multi-speaker dialogue, then speak, clone and sfx generate the audio as before.
/ak:motion-video enhanced About 70 style profiles now, including a Vox-like collage explainer. Before any paid audio it shows a beat map (story arc, hook, one line per scene) and plans a shot and camera move per scene; printed or collage looks and supplied photos are generated as image layers through multix and animated in GSAP.
/ak:onboarding-cro enhanced Rewritten as a lean core: activation must be one user action that predicts retention (or is labeled a hypothesis with the events to track); the plan fixes the biggest measured drop first, keeps required steps instead of deleting them, and ties every change to a success metric and a guardrail. No invented benchmarks, and it never sends messages itself.
Start Here (Essentials)
Core path: Level → Ask → Brainstorm → Plan → Preview → Execute
1 /ak:init
$ak:init
/ak:init [prompt]
Initialize marketing project — discover or establish project context, brand constraints, marketing direction, and setup. Use when starting a new marketing project or onboarding an existing one.
Open visual guide →[prompt] 2 /ak:ask
$ak:ask
/ak:ask [technical-question] [--yagni]
Answer technical and architectural questions with expert analysis. Use for design decisions, best practices evaluation, solution comparison.
Open visual guide →[question] --yagni $ak:brainstorm
/ak:brainstorm [topic or problem] [--advice] [--html] [--report] [--ultra] [--yagni] [--no-antv|--no-diagram-design|--no-editorial-visuals]
Turn unclear intent into an accepted outcome and compare viable approaches before delivery.
Open visual guide →[topic or problem] --advice--html--no-antv--no-diagram-design--no-editorial-visuals--report--ultra--yagni 4 /ak:plan
$ak:plan
/ak:plan [archive|ci|cro|fast|hard|parallel|two|validate] [--html] [task]
Create, validate or review implementation plans with acceptance criteria and executable phases. Use for planning and roadmaps; implementation belongs to cook.
Open visual guide →archivecicrofasthardparalleltwovalidate [task] --html $ak:write
/ak:write [audit|blog|blog-youtube|cro|enhance|fast|good|publish] [args]
Marketing authoring front door for blog posts, copy drafting, CTA/CRO revisions, enhancement, and publication-ready content. Maps natural requests to one authoring workflow; strategy and analytics belong to their respective capabilities.
Open visual guide →auditblogblog-youtubecroenhancefastgoodpublishformula [args] $ak:bro
/ak:bro [last message | topic to simplify]
Restate the assistant's last message in simpler, shorter, jargon-free language. Use when the user says ak:bro, simplify that, say it plainly, or explain it like a human.
Open visual guide →[last message | topic to simplify] $ak:cook
/ak:cook [task|plan-path] [--interactive|--fast|--parallel|--auto|--no-test] [--tdd] [--advice] [--yagni] [--skip-journal]
Implement features, plans, and fixes with structured workflow. Use for feature development, plan execution, code implementation pipelines.
Open visual guide →[task|plan-path] --advice--auto--fast--interactive--no-test--parallel--skip-journal--tdd--yagni Strategy & Research
Market research, personas, and planning
$ak:codex-goal
/ak:codex-goal <objective | goal draft>
Guide long-running Codex goal work with a verifiable stop condition. Use when users mention /goal, goal mode, durable objectives, or autonomous multi-turn Codex runs.
Open visual guide →objective $ak:competitor
/ak:competitor [analyze|content|seo|alternatives|list] [url or competitor]
Competitive analysis, alternative pages, vs comparisons, SEO competitor content, market positioning, and battlecard generation.
Open visual guide →alternatives [analyze|content|seo|alternatives|list][url or competitor] $ak:creativity
/ak:creativity [style or medium]
Creative direction intelligence. 55 styles, 18 platforms, 12 voiceover types, 17 music genres, 30 campaign categories. Actions: create, design, plan, direct, brief creative campaigns. Projects: ads, videos, social content, commercials, brand films. Styles: minimalist, maximalist, nostalgic, cinematic, UGC, luxury, futuristic, emotional. Topics: visual style, platform specs, voiceover, music, color palette, audience targeting.
Open visual guide →[style or medium] $ak:marketing-ideas
/ak:marketing-ideas [product or niche]
When the user needs marketing ideas, inspiration, or strategies for their SaaS or software product. Also use when the user asks for 'marketing ideas,' 'growth ideas,' 'how to market,' 'marketing strategies,' 'marketing tactics,' 'ways to promote,' or 'ideas to grow.' This skill provides a reference catalog of marketing approaches organized by category.
Open visual guide →[product or niche] $ak:marketing-planning
/ak:marketing-planning [goal or timeframe]
Plan marketing strategies, campaigns, funnels, content calendars, and initiatives using frameworks such as RACE, SOSTAC, and STP. Reuses current evidence and researches material gaps.
Open visual guide →[goal or timeframe] $ak:marketing-psychology
/ak:marketing-psychology [principle or tactic]
When the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,' 'behavioral science,' 'why people buy,' 'decision-making,' or 'consumer behavior.' This skill provides 70+ mental models organized for marketing application.
Open visual guide →[principle or tactic] $ak:marketing-research
/ak:marketing-research [topic or market]
Research market trends, competitors, audience insights, customer personas, and marketing best practices. Use before marketing-planning for data-driven strategy.
Open visual guide →[topic or market] $ak:research-prompt
/ak:research-prompt <research topic | decision>
Draft a self-contained research brief for a human or AI researcher. Use when users ask for a research prompt, research brief, or a deep-research task to hand off.
Open visual guide →decision $ak:scout
/ak:scout [search-target] [ext] [--ultra]
Fast codebase scouting using native search, optional Explore agents, and user-permitted OpenCode probes. Use for file discovery, task context gathering, and scoped searches across directories.
Open visual guide →[search-target][ext] --ultra $ak:sowat
/ak:sowat [recent-changes|issue|PR]
Analyze recently implemented work and related issues like a product owner. Use to identify high-impact next steps, challenge weak priorities, and explain what matters now.
Open visual guide →[recent-changes|issue|PR] Content & Copy
Content hubs, marketing copy, and playbooks
$ak:content-hub
/ak:content-hub [action: open|browse|search]
Browser-based asset gallery for managing marketing assets. Visual grid with filter/search, brand context sidebar, and actions (preview, edit, generate). Use when browsing assets, managing content library, or generating new assets with brand context.
Open visual guide →browsesearch $ak:content-marketing
/ak:content-marketing [content-type] [topic]
Activate for content strategy, editorial calendars, content pillar mapping, blog planning, and content audit. Use when planning content programs, creating editorial workflows, or building topic clusters.
Open visual guide →[content-type][topic] $ak:copywriting
/ak:copywriting [copy-type] [context]
Conversion copywriting formulas, headline templates, email copy patterns, landing page structures, CTA optimization, and writing style extraction. Activate for writing high-converting copy, crafting headlines, email campaigns, landing pages, or applying custom writing styles from assets/writing-styles/ directory.
Open visual guide →[copy-type][context] $ak:play
/ak:play [create|next|status|list|blocked|learn|reset|gate|templates|goals] [args]
Marketing playbook orchestrator with dependency-graph routing, quality gates, goal tracking, and suggestions based on recorded state. Triggers: /ak:play, playbook, campaign playbook, product discovery playbook, founder or product owner workflow, validate an idea, what's next, play status.
Open visual guide →createnextstatuslistblockedlearnresetgatetemplatesgoals [args] Campaign Management
Campaigns, ads, and affiliate channels
$ak:ads-management
/ak:ads-management [platform] [campaign-type]
Operate paid-ad campaigns through available authorized platform APIs: reporting, setup, targeting, budget updates, pause/enable, and creative delivery. Strategy and copy-only advice belong to paid-ads.
Open visual guide →[platform][campaign-type] $ak:affiliate-marketing
/ak:affiliate-marketing [program or strategy]
Design and evaluate affiliate partner programs, commissions, KOL/KOC recruitment, attribution, and fraud controls. Use for partner-led acquisition; customer refer-a-friend programs belong to referral-program-building.
Open visual guide →[program or strategy] $ak:campaign
/ak:campaign [create|status|analyze|email] [name]
Marketing campaign planning, execution, optimization. Create campaigns, track status, analyze performance, manage budgets, coordinate multi-channel efforts.
Open visual guide →createstatusanalyzeemail [name] $ak:paid-ads
/ak:paid-ads [platform] [campaign-type]
When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ad copy,' 'ad creative,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' or 'audience targeting.' This skill owns strategy, copy, audience recommendations, and optimization analysis; ads-management owns authorized account operations.
Open visual guide →[platform][campaign-type] SEO & Analytics
Search optimization and performance dashboards
$ak:analytics
/ak:analytics [metric or report-type]
Activate for marketing analytics, KPI tracking, reporting dashboards, attribution analysis, and performance optimization. Use when analyzing campaign data, creating reports, or measuring marketing ROI.
Open visual guide →[metric or report-type] $ak:marketing-dashboard
/ak:marketing-dashboard [start|stop|status|open]
Run and inspect the local Assets, Brand, and Settings dashboard.
Open visual guide →[start|stop|status|open] $ak:seo
/ak:seo [audit|geo|keywords|pseo|optimize|schema] [target]
SEO and GEO audits, keyword research (ReviewWeb.site API), on-page and technical SEO, AI discoverability (robots.txt, sitemap.xml, llms.txt, llms-full.txt, .md page variants, social cards, copy/share/open-in-AI page actions), programmatic SEO, JSON-LD schema, Google Search Console, Core Web Vitals.
Open visual guide →auditgeokeywordspseooptimizeschema [target] Design & Visual
Brand, logos, banners, motion design, and marketing visuals
$ak:assets-organizing
/ak:assets-organizing [directory or asset-type]
Resolve marketing asset paths and organize asset collections while preserving user paths, repository conventions, existing links, and files.
Open visual guide →[directory or asset-type] $ak:banner-design
/ak:banner-design [platform] [style] [dimensions]
Design banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with AI-generated visuals. Actions: design, create, generate banner. Platforms: Facebook, Twitter/X, LinkedIn, YouTube, Instagram, Google Display, website hero, print. Styles: minimalist, gradient, bold typography, photo-based, illustrated, geometric, retro, glassmorphism, 3D, neon, duotone, editorial, collage. Uses ui-ux-pro-max, frontend-design, ai-artist, ai-multimodal skills.
Open visual guide →[platform][style][dimensions] $ak:brand
/ak:brand [update|review|create] [args]
Brand voice, visual identity, messaging frameworks, asset management, brand consistency. Activate for branded content, tone of voice, marketing assets, brand compliance, style guides.
Open visual guide →updatereviewcreate [args] $ak:cip-design
/ak:cip-design [deliverable or brand-element]
Design Corporate Identity Program mockups and brand applications such as stationery, signage, apparel, and packaging. Preserve existing identity or develop new concepts within the requested brief.
Open visual guide →[deliverable or brand-element] $ak:design
/ak:design [design-type] [context]
Design brand identity, logos, banners, posters, and visual assets. Use for brand systems, design tokens, corporate identity programs, event/editorial/marketing posters, and visual campaign assets. Not for UI code patterns.
Open visual guide →[design-type][context] $ak:design-system
/ak:design-system [component or token]
Token architecture, component specifications, and slide generation. Three-layer tokens (primitive→semantic→component), CSS variables, spacing/typography scales, component specs, strategic slide creation. Use for design tokens, systematic design, brand-compliant presentations.
Open visual guide →[component or token] $ak:enhance-ux-ax
/ak:enhance-ux-ax [url|path|focus] [--auto] [--loop [N]]
Combined UX + AI-experience (AX) review of an existing site or app: scores brand recall, punchy content, motion and responsive layouts, scans SEO/GEO discovery surfaces (sitemap, robots, llms.txt, per-URL markdown, schema, social cards, copy/share/send-to-AI actions), and writes ranked proposals with an explicit DONE contract. --auto implements them; --loop [N] repeats review-to-verify rounds with screenshot vision checks. For a UI-polish-only audit or new UI use ak:frontend-design; for an SEO/GEO-only audit or keyword research use ak:seo.
Open visual guide →[url|path|focus] --auto--loop $ak:frontend-design
/ak:frontend-design [prompt|image-path|component|url]
Create polished frontend interfaces with deliberate art direction, from a brief, design, screenshot or video, and audit live products for UI/UX polish. Use for landing pages, product/dashboard UI, web components, 3D experiences, replicating UI designs, quick prototypes, immersive interfaces, avoiding AI slop, and hands-on UX audits of dev/staging/production apps across desktop, tablet and mobile.
Open visual guide →[prompt|image-path|component|url] $ak:logo-design
/ak:logo-design [brand-name] [style]
Design logos and explore logo styles, palettes, and brand concepts. Use for a new mark or requested revision, preserving supplied brand constraints and verifying final image formats.
Open visual guide →[brand-name][style] $ak:mermaidjs-v11
/ak:mermaidjs-v11 [diagram-type or description]
Create diagrams with Mermaid.js v11 syntax. Use for flowcharts, sequence diagrams, class diagrams, ER diagrams, Gantt charts, state diagrams, architecture diagrams, timelines, user journeys.
Open visual guide →[diagram-type or description] $ak:motion-design
/ak:motion-design [element, interaction, or animation brief]
Motion design principles for emotionally-driven, technically sound animation. Emotion-to-motion mapping, Disney's 12 principles adapted for UI, timing and easing tables (Material 3, Apple HIG), stagger recipes, and multi-element choreography. Use when creating animations, transitions, micro-interactions, loading states, hero/CTA/promo motion, page transitions, or scroll-triggered effects. Implementation-agnostic: works with CSS, Framer Motion, GSAP, Lottie, Spring, or Remotion. Pairs with frontend-design, banner-design, video, design-system for implementation.
Open visual guide →[element, interaction, or animation brief] $ak:preview
/ak:preview [path] OR [--html] --explain|--slides|--diagram|--ascii [topic] OR --html --diff|--plan-review|--recap [--no-antv|--no-diagram-design|--no-editorial-visuals]
View files or generate visual explanations, slides, and diagrams. Use for code walkthroughs, architecture visualization, HTML/Markdown presentations.
Open visual guide →[path][topic] --ascii--diagram--diff--explain--html--no-antv--no-diagram-design--no-editorial-visuals--plan-review--recap--slides $ak:tech-graph
/ak:tech-graph [diagram-type or system description]
Generate production-quality SVG+PNG technical diagrams — architecture, data flow, flowchart, sequence, agent/memory, or concept maps — across 7 visual styles. Use when user wants "generate diagram", "draw diagram", "visualize", "architecture diagram", "flowchart", or any system/flow they want illustrated. Pairs with /ak:preview --diagram for visual self-review and /ak:mermaidjs-v11 for inline-doc diagrams; this skill is the publish-grade output mode.
Open visual guide →[diagram-type or system description] $ak:ui-ux-pro-max
/ak:ui-ux-pro-max [component|page|design-system] [--style <style>] [--framework <fw>]
UI/UX design intelligence for web and mobile: style selection, color systems, typography, layout, accessibility, interaction states, responsive behavior, forms, charts, design systems, and code review across React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS.
Open visual guide →[component|page|design-system] --framework--style Email & Social
Email sequences and social outreach
$ak:email
/ak:email [flow|sequence|newsletter|cold|launch|nurture] [args]
Email campaigns, newsletters, drip sequences, automation flows, email copywriting, deliverability, subject line formulas, A/B testing. Generate email content for any marketing purpose.
Open visual guide →flowsequencenewslettercoldlaunchnurture [args] $ak:social
/ak:social [platform] [type] | publish | schedule | list-providers
Social media content creation, scheduling, and multi-provider publishing (Postiz, Buffer, Post Bridge, Typefully, Zernio, Publer) for X, LinkedIn, Instagram, TikTok, YouTube, Facebook, Threads, Bluesky, Mastodon, and more. Platform-specific workflows, engagement templates, hook writing.
Open visual guide →publishschedulelist-providers [platform][type] Growth & CRO
Launch, pricing, funnels, and conversion
$ak:ab-test-setup
/ak:ab-test-setup [page or feature]
Design marketing and product A/B tests, split tests, variant copy experiments, and multivariate tests. Define hypotheses, metrics, allocation, and stopping rules; not for general debugging hypotheses.
Open visual guide →[page or feature] $ak:form-cro
/ak:form-cro [form-url or description]
When the user wants to optimize any form that is NOT signup/registration — including lead capture forms, contact forms, demo request forms, application forms, survey forms, or checkout forms. Also use when the user mentions "form optimization," "lead form conversions," "form friction," "form fields," "form completion rate," or "contact form." Signup and popup implementation belong to a matching capability discovered in the live catalog.
Open visual guide →[form-url or description] $ak:free-tool-strategy
/ak:free-tool-strategy [tool-idea or niche]
Plan and evaluate free tools for acquisition, lead generation, SEO, or brand awareness. Use for engineering-as-marketing calculators and generators; not for internal utilities without a marketing objective.
Open visual guide →[tool-idea or niche] $ak:gamification-marketing
/ak:gamification-marketing [mechanic or campaign]
Design gamified marketing campaigns using points, badges, leaderboards, streaks, challenges. Use for loyalty programs, referral campaigns, onboarding flows, engagement boosts, email gamification. Provides mechanics selection, psychology alignment, strategy docs, templates, KPIs.
Open visual guide →[mechanic or campaign] $ak:launch-strategy
/ak:launch-strategy [product or feature]
When the user wants to plan a product launch, feature announcement, or release strategy. Also use when the user mentions 'launch,' 'Product Hunt,' 'feature release,' 'announcement,' 'go-to-market,' 'beta launch,' 'early access,' 'waitlist,' or 'product update.' This skill covers phased launches, channel strategy, and ongoing launch momentum.
Open visual guide →[product or feature] $ak:onboarding-cro
/ak:onboarding-cro [flow-url or description]
When the user wants to optimize post-signup onboarding, user activation, first-run experience, or time-to-value. Also use when the user mentions "onboarding flow," "activation rate," "user activation," "first-run experience," "empty states," "onboarding checklist," "aha moment," or "new user experience." For signup and email work, resolve a matching installed capability.
Open visual guide →[flow-url or description] $ak:pricing-strategy
/ak:pricing-strategy [product or tier]
When the user wants help with pricing decisions, packaging, or monetization strategy. Also use when the user mentions 'pricing,' 'pricing tiers,' 'freemium,' 'free trial,' 'packaging,' 'price increase,' 'value metric,' 'Van Westendorp,' 'willingness to pay,' or 'monetization.' This skill covers pricing research, tier structure, and packaging strategy.
Open visual guide →[product or tier] $ak:referral-program-building
/ak:referral-program-building [product or program-type]
Build referral programs for SaaS/digital products. Covers reward structures (two-sided, tiered, multi-step), platform selection (Rewardful, ReferralCandy, Viral Loops, FirstPromoter), technical implementation (tracking, attribution, API patterns), fraud prevention, email templates, and KPI metrics. Use for designing viral growth loops, implementing refer-a-friend features, or optimizing existing referral systems.
Open visual guide →[product or program-type] Video & Media
Video, motion graphics routing, YouTube, slides, and multimodal media
$ak:ai-multimodal
/ak:ai-multimodal [file-path] [prompt]
Analyze and generate image, audio, video, and document content. Prefers the active model's native vision for image/document understanding; falls back to the npm-latest Multix CLI and live provider catalogs only when native vision is ineligible or a generation/audio/video task needs a configured provider.
Open visual guide →[file-path][prompt] $ak:elevenlabs
/ak:elevenlabs [action: speak|clone|sfx] [text-or-file]
Generate speech, clone voices, create sound effects & music with ElevenLabs API. TTS, voice design, audio generation, conversational AI agents.
Open visual guide →clonesfx [text-or-file] /ak:filmmaking beta
$ak:filmmaking
/ak:filmmaking [create|script|breakdown|bible|storyboard|animatic|render|audio|qc|assemble] [brief-or-project]
Plan and produce long-form AI films (roughly 5-30 minutes) as a production graph with consistent characters, scene/shot continuity, storyboards, animatics, audio-first dialogue and lipsync, separate sound stems, cost-aware model routing, shot-level regeneration and final assembly. Not for marketing or social videos, motion graphics, or a single generated clip.
Open visual guide →createscriptbreakdownbiblestoryboardanimaticrenderaudioqcassemble [brief-or-project] $ak:hyperframes
/ak:hyperframes [composition or command]
Wrap HeyGen HyperFrames CLI for HTML-first programmatic video generation. Use for short vertical/social videos, product-launch clips, motion graphics rendered from HTML composition. See also the installed remotion skill for a React-based alternative.
Open visual guide →[composition or command] $ak:motion-graphics
/ak:motion-graphics [intent-or-pack] [--list|--propose <pack>|--verify <file>]
Route motion, animation, or video work to an available installed workflow and verify rendered artifacts. Propose external template packs only when existing capabilities do not cover the request.
Open visual guide →[intent-or-pack] --list--propose--verify $ak:motion-video
/ak:motion-video [brief or project] [--poor]
Produce beat-synced 1080p motion-graphic videos in HyperFrames (HTML + GSAP) with an AI voice-over, Vietnamese karaoke captions, SFX and generated music, in any of ~60 named style profiles (glass keynote, comic, Apple-like cinematic, Swiss, cyberpunk, Nike-like and more) or a per-scene mix of them, with production-grade juicy motion and fast 1:1 / 9:16 editions. Use when the user asks for a launch/release/feature video, motion graphic, animated explainer or promo clip, a restyle, or a square/vertical version of one.
Open visual guide →[brief or project] --poor $ak:remotion
/ak:remotion [video or component]
Build video content with Remotion in React. Use for programmatic video creation, animated sequences, data-driven video rendering.
Open visual guide →[video or component] $ak:slides
/ak:slides [topic] [slide-count]
Create strategic HTML presentations with Chart.js, design tokens, responsive layouts, copywriting formulas, and contextual slide strategies.
Open visual guide →create [topic][slide-count] $ak:video
/ak:video [create|script-create|storyboard-create] [topic]
Create marketing video scripts, storyboards, rendered videos, and platform repurposing. Choose the production stage requested; generation uses an available provider and thumbnails are a separate requested deliverable.
Open visual guide →createscript-createstoryboard-create [topic] $ak:youtube
/ak:youtube [blog|infographic|social] [youtube-url]
Convert YouTube videos to blog posts, infographics, social content. Download video/audio, get captions/transcripts, generate AI summaries, analyze comments via VidCap.xyz API.
Open visual guide →bloginfographicsocial [youtube-url] $ak:youtube-thumbnail-design
/ak:youtube-thumbnail-design [niche] [style]
Design YouTube thumbnails and test variants using the video brief, approved brand/face references, and readable text. Verify exported dimensions, format, and file size; CTR improvement is a test objective.
Open visual guide →[niche][style] Test & Debug
Testing, debugging, review, and scenarios
$ak:debug
/ak:debug [error or issue description] [--ultra]
Debug systematically with root cause analysis before fixes. Use for bugs, test failures, unexpected behavior, performance issues, call stack tracing, multi-layer validation, log analysis, CI/CD failures, database diagnostics, system investigation.
Open visual guide →[error or issue description] --ultra $ak:fix
/ak:fix [issue] --auto|--review|--quick|--parallel [--ultra] [--advice] [--skip-journal]
Fix bugs, errors, test failures, and CI/CD issues with intelligent routing. Use for type errors, lint issues, log errors, UI bugs, code problems.
Open visual guide →[issue] --advice--auto--parallel--quick--review--skip-journal--ultra $ak:test
/ak:test [context] OR ui [url] OR create|optimize|audit [scope] [--advice] [--ultra] [--interview]
Run unit, integration, e2e, and UI tests. Use for test execution, coverage analysis, build verification, visual regression, and QA reports.
Open visual guide →uicreateoptimizeaudit [context][url] --advice--interview--ultra Git & Version Control
Git ops, GitHub via gh, worktrees, and PR review
$ak:git
/ak:git cm|cp|pr|merge|merge-pr|stack [args]
Git operations with conventional commits. Use for staging, committing, pushing, PRs, merges, stacked PRs. Auto-splits commits by type/scope. Security scans for secrets.
Open visual guide →cmcpprmergemerge-prstack [args] $ak:worktree
/ak:worktree [feature-description] OR [project] [feature]
Create, inspect, and clean isolated git worktrees. Use for feature isolation, worktree health audits, stale cleanup, and monorepo or submodule workflows.
Open visual guide →createremoveinfoliststatusprune [feature-description][project][feature] Session Management
Handoffs, dispatch, orchestration, journals, and context
$ak:handoff
/ak:handoff [task focus] [--output PATH] [--include-diff] [--include-status] [--force] [--dispatch --agent <id> [--handoff PATH] [--cwd PATH] [--model NAME] [--yes]]
Create a portable, redacted Markdown continuation contract that a fresh coding agent can consume to resume in-progress work safely, and optionally dispatch it to a selected coding runtime with --dispatch. Use when switching sessions, models, or runtimes, or when preserving decisions, verification state, and blockers.
Open visual guide →[next-session focus] --agent--cwd--dispatch--force--handoff--include-diff--include-status--model--output--yes $ak:journal
/ak:journal [topic or reflection]
Write chronological technical journals for session reflection and change analysis. Journals preserve work history; they do not replace current docs or ADRs.
Open visual guide →[topic or reflection] $ak:sumup
/ak:sumup [task|PR|branch|recent]
Summarize completed implementation, failures, workarounds, decisions, behavior, architecture, usage, follow-ups, and next steps. Use after implementation or for a technical recap.
Open visual guide →[task|PR|branch|recent] $ak:watzup
/ak:watzup [branch|worktree|status]
Generate short handoff reports from Git branches, remote refs, worktrees, unfinished plans, and roadmap docs. Surfaces priority-ranked next steps with checkbox progress and rationale. Use when the user asks what's in flight, wants progress/next steps, is in a fresh worktree or detached checkout, or needs end-of-session status.
Open visual guide →[branch|worktree|status] Project Tracking
Progress, kanban, and project organization
$ak:docs
/ak:docs init|update|summarize|agent-context|agents|llms
Analyze a codebase and create, refresh, summarize, or audit project documentation without imposing a fixed docs layout, with an opt-in classic layout via --preset classic, including authoring and optimizing the root CLAUDE.md/AGENTS.md agent context file, or distilling DO/DON'T rules for that file from git history, CI runs, and (with --source) current source-tree markers.
Open visual guide →initupdatesummarizeagent-contextagentsllms $ak:folder-context
/ak:folder-context <target-folder>
Create a compact subfolder CLAUDE.md and linked AGENTS.md for durable local conventions. Use when a folder needs agent context beyond the project root.
Open visual guide →<target-folder> $ak:interview-docs
/ak:interview-docs <vision | document-path | topic>
Extract a user's vision and decisions into durable project documents through a guided interview. Use for README, ADR, strategy, principles, and structured-doc authoring.
Open visual guide →<vision | document-path | topic> Utilities
ak CLI, skill tools, packaging, and general utilities
$ak:agent-browser
/ak:agent-browser [url or task]
Automate tool-managed browsers with agent-browser for snapshots, clicks, forms and browser testing. Use chrome-profile when real Chrome account state is required.
Open visual guide →[url or task] $ak:agentkit
/ak:agentkit [task to route]
Task router for AgentKit installs. Classifies the task, activates the right installed skills, chains them into the shortest workflow that fits, and spawns installed subagents at defined trigger points to raise output quality. Use at the start of multi-step, multi-domain, or ambiguous work, or when unsure which skill or agent applies.
Open visual guide →[task to route] $ak:ak
/ak:ak [goal or subcommand]
Operate the ak control-plane CLI itself — the AgentKit binary that installs, inspects, updates, recovers, and removes kits and their skills. Use when the next action is invoking an ak subcommand (init, kit, skills, plan, journal, doctor, recover, self-update, login), deciding between read-only inspection and lifecycle mutation, disambiguating project vs global scope, or interpreting ak --json output. Not for authoring skills (use ak:skill-creator) or routing generic work (use ak:agentkit).
Open visual guide →[goal or subcommand] $ak:docs-seeker
/ak:docs-seeker [library-name] [topic]
Search library/framework documentation via llms.txt (context7.com). Use for API docs, GitHub repository analysis, technical documentation lookup, latest library features.
Open visual guide →[library-name][topic] $ak:explain
/ak:explain [subject|path|URL] [--html] [--eli5]
Explain concepts, code, systems, errors, and documents with grounded evidence. Use --eli5 for plain-language analogies or --html for a visual explanation.
Open visual guide →[subject|path|URL] --eli5--html $ak:google-adk-python
/ak:google-adk-python [agent or feature]
Build AI agents with Google ADK Python. Multi-agent systems, A2A protocol, MCP tools, workflow agents, state/memory, callbacks/plugins, Vertex AI deployment, evaluation.
Open visual guide →[agent or feature] $ak:skill-creator
/ak:skill-creator <create|update|audit|optimize> [skill-name|path|kit|--all] [--kit <kit>|--project|--user] [--long-horizon] [--apply] [--from-audit <report>] [--advice]
Create, update, audit, validate, and package agent skills. Use when authoring SKILL.md resources or diagnosing skill routing and behavior. Not for implementing CLI or MCP servers.
Open visual guide →[skill-name|path|kit|--all] --advice--all--apply--from-audit--kit--long-horizon--project--user $ak:storage
/ak:storage [upload|download|list|sync] [file|path] [--bucket <name>]
S3-compatible object storage integration for marketing assets. Works with Cloudflare R2, AWS S3, MinIO, Backblaze B2, DigitalOcean Spaces.
Open visual guide →[file|path] --bucket No NEW skills in this kit
No COMMON skills in this kit