VividKit Crystal clear AI coding
VI
Choose Your Setup Get Started with AgentKit Continue with ClaudeKit Migrate from ClaudeKit to AgentKit Clean cutover from ClaudeKit What Is AgentKit? How AgentKit Works AgentKit Kits, Skills, Agents & Hooks AgentKit Runtime Support AgentKit Desktop App AgentKit Configuration AgentKit CLI Quick Reference AgentKit Skills Cheatsheet AgentKit Workflows AgentKit Statusline Update AgentKit CLI & Kits AgentKit Helper Clean reinstall of AgentKit AgentKit Troubleshooting What is ClaudeKit? ClaudeKit CLI Guide Command Finder Commands Cheat Sheet Workflow Recipes CLI Quick Reference Claude Mechanics Permission Modes ClaudeKit Hooks Coexistence ClaudeKit x Codex CK → Other coding tools How ClaudeKit Works Inside ClaudeKit Finding Your Unknowns Session Recovery Fix from Logs UI/UX Guide Accounts Switcher IDE Config Remote Control Codex App System Diagramming UI Review Gate Promotions Support VividKit

Quick Ref / Command

Marketing Kit

/ak:play

Marketing playbook orchestrator

Marketing playbook orchestrator with dependency graph routing, template management, goal tracking, quality gates, smart suggestions, and stateful manifest updates.

01

Parse Entry

02

Route Reference

03

Load Manifest

04

Evaluate Graph

Rule 01

A playbook is a stateful dependency graph, not a loose checklist.

Rule 02

Every step has strategy, AI execution, and human-decision layers.

Rule 03

Goal gaps and graph readiness determine what is next.

Rule 04

Templates are validated before use; execution only routes through known commands and rostered agents.

Execution Map

Core lanes from input to output, aligned with the command's real execution path.

01

Start

Input, scope, route

  1. 1 Parse Entry Read create, next, status, list, blocked, learn, reset, gate, templates, goals, or treat a name as status.
  2. 2 Route Reference Load references/{subcommand}.md for the requested operation.
02

Work

Agent / skill execution

  1. 3 Load Manifest Read data/playbooks/{slug}/manifest.json for state, template, outputs, timestamps, and learnings.
  2. 4 Evaluate Graph Use graph logic to determine ready, blocked, stale, gate-pending, in-progress, and completed steps.
03

Verify

Gate, review, validation

  1. 5 Check Goals Pull or accept metrics, compare against goal targets, and calculate trend or gap.
  2. 6 Suggest Next Rank the top actions by goal gap, readiness, expected impact, and dependency status.
04

Close

Report, handoff, artifact

  1. 7 Execute Routed Step Route step definitions to existing agents, skills, or /ak:* commands; keep human gates explicit.
  2. 8 Update State Write manifest status, outputs, timestamps, goal values, and learnings after the operation.

Modes / Routes

create <name> [--template <id>]

Create a playbook from a named template or custom flow.

Research:
Template
Review:
Invalid schema
Validate:
Manifest created
next [name]

Show the best ready action from dependency graph and goal gap.

Research:
Manifest
Review:
Blocked deps
Validate:
Top actions
status [name]

Display playbook progress, blocked work, stale steps, goals, and outputs.

Research:
State
Review:
Stale data
Validate:
Dashboard
list

Summarize local playbooks under data/playbooks/.

Research:
Playbook directory
Review:
Missing state
Validate:
Inventory
blocked [name]

Explain blocked and gate-pending steps and recommend an unblock path.

Research:
Manifest state
Review:
Wrong unblock
Validate:
Blocked reasons
learn [name]

Capture user-reviewed reusable patterns into manifest.json and learnings.md.

Research:
Reviewed output
Review:
Unvetted pattern
Validate:
Learning saved
reset <name> [step]

Reset one step or the whole playbook while preserving output files.

Research:
Reset scope
Review:
Wrong step
Validate:
State reset
gate <name> <step> approve|reject

Approve or reject a human decision gate.

Research:
Gate state
Review:
Wrong step
Validate:
Manifest update
goals [set|pull]

Set or pull goal metrics and compare them to targets.

Research:
Metrics
Review:
No API keys
Validate:
Goal trends
templates [--browse]

Browse bundled templates such as product-hunt-launch, content-engine, campaign-sprint, and saas-launch.

Research:
Template catalog
Review:
Unsupported gate
Validate:
Schema

Sample Prompt

Concrete invocations for each flag, subcommand, mode, or route available in the live workflow.

Create playbook Recommended 
/ak:play create saas-launch --template saas-launch
Use when:
You need a reproducible marketing playbook from a bundled template.
Expected:
A manifest-backed playbook with steps, goals, dependencies, and template version.
Next action 
/ak:play next saas-launch
Use when:
You want the highest-impact ready step instead of scanning the whole plan.
Expected:
Top suggested actions from graph readiness and goal gaps.
Status dashboard 
/ak:play status saas-launch
Use when:
You need current progress, blocked steps, stale work, goals, and outputs.
Expected:
Playbook status dashboard.
Gate decision 
/ak:play gate saas-launch pricing-page approve
Use when:
A human decision gate is pending and needs an explicit decision.
Expected:
Manifest gate status updated and next ready step recalculated.
Goal pull 
/ak:play goals pull
Use when:
You need current metric progress using available analytics bridges or manual fallback.
Expected:
Goal values, trends, and smart suggestions.
Browse templates 
/ak:play templates --browse
Use when:
You need to inspect bundled playbook templates before creating one.
Expected:
Lists bundled templates with ids and descriptions and does not create or mutate a playbook manifest.

Handled Scope

  • Parse Entry
  • Route Reference
  • Load Manifest
  • Evaluate Graph
  • Check Goals
  • Suggest Next

Next