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:plan

Marketing-kit plan router

Marketing-kit plan creator and router for fast, hard, parallel, two-approach, validation, CI, CRO, and archive workflows — creates plans, not implementation.

01

Detect Context

02

Confirm Active Plan

03

Parse Subcommand

04

Analyze Task

Rule 01

Owns planning and prompt enhancement, not execution.

Rule 02

Existing plan context changes routing: active plans require confirmation before continuing.

Rule 03

Subcommand choice controls depth: fast is no-research, hard researches, parallel decomposes, two compares approaches, validate interviews the plan.

Rule 04

Reports sacrifice grammar for concision while preserving quality and unresolved questions.

Execution Map

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

01

Start

Input, scope, route

  1. 1 Detect Context Check Plan Context for an active plan path, suggested branch-matched plan, or no plan.
  2. 2 Confirm Active Plan If an active or suggested plan exists, ask whether to continue it, activate it, or create a new one.
02

Work

Agent / skill execution

  1. 3 Parse Subcommand Read archive, ci, cro, fast, hard, parallel, two, or validate from the first argument.
  2. 4 Analyze Task Ask for missing details if needed and determine task complexity and planning depth.
03

Verify

Gate, review, validation

  1. 5 Enhance Prompt Convert the user task into a detailed instructions prompt for the selected planning workflow.
  2. 6 Route Reference Load the corresponding references/{subcommand}.md or decide fast versus hard by complexity.
04

Close

Report, handoff, artifact

  1. 7 Activate Skills Analyze the skill catalog and activate planning plus any task-relevant skills.
  2. 8 Report Plan Write a concise, high-quality plan and put unresolved questions at the end.

Modes / Routes

fast

No research; analyze and create an implementation plan quickly.

Research:
No
Review:
Light
Validate:
Plan clarity
hard

Research, analyze, and create a deeper implementation plan.

Research:
Yes
Review:
Assumptions
Validate:
Evidence
parallel

Create a detailed plan with phases that can execute in parallel.

Research:
As needed
Review:
Dependencies
Validate:
DAG fit
two

Research and create an implementation plan with two approaches.

Research:
Yes
Review:
Tradeoffs
Validate:
Choice criteria
validate

Validate a plan through a critical-questions interview.

Research:
Plan
Review:
Critical questions
Validate:
Interview
archive

Write journal entries and archive specific plans or all plans.

Research:
Plan state
Review:
Wrong target
Validate:
Archive path
ci

Analyze GitHub Actions logs and provide a plan to fix CI issues.

Research:
CI logs
Review:
Root cause
Validate:
Fix plan
cro

Create a conversion-rate-optimization plan for provided content.

Research:
Content
Review:
Conversion leaks
Validate:
CRO actions

Sample Prompt

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

Fast plan Recommended 
/ak:plan fast Launch a webinar funnel for founders
Use when:
The work is clear and does not need research.
Expected:
Concise implementation plan from an enhanced task prompt.
Hard plan 
/ak:plan hard Build a cross-channel launch system for a new SaaS product
Use when:
The task needs research, assumptions, and deeper analysis.
Expected:
Research-backed plan with open questions listed at the end.
Parallel plan 
/ak:plan parallel Create content, ads, landing page, and email launch assets
Use when:
Independent workstreams should be planned for concurrent execution.
Expected:
Plan broken into parallel-executable phases with dependencies.
Two approaches 
/ak:plan two Improve activation for a self-serve SaaS trial
Use when:
You want two viable approaches before choosing direction.
Expected:
Two researched approaches with tradeoffs and decision criteria.
Validate plan 
/ak:plan validate plans/launch-plan.md
Use when:
A plan exists and needs critical-question review.
Expected:
Validation interview exposing gaps and unresolved questions.

Handled Scope

  • Detect Context
  • Confirm Active Plan
  • Parse Subcommand
  • Analyze Task
  • Enhance Prompt
  • Route Reference

Next