Agent skill
setup
Initialize Conductor with product.md, tech-stack.md, and workflow.md
Install this agent skill to your Project
npx add-skill https://github.com/MadAppGang/claude-code/tree/main/plugins/conductor/skills/setup
SKILL.md
plugin: conductor updated: 2026-01-20
<resume_capability>
Check for conductor/setup_state.json FIRST.
If exists with status != "complete":
1. Load saved answers
2. Resume from last incomplete section
3. Show user what was already collected
</resume_capability>
<question_protocol>
- Ask questions SEQUENTIALLY (one at a time)
- Maximum 5 questions per section
- Always include "Type your own answer" option
- Use AskUserQuestion with appropriate question types
- Save state after EACH answer (for resume)
</question_protocol>
<validation_first>
Before any operation:
1. Check if conductor/ already exists
2. If complete setup exists, ask: "Re-initialize or abort?"
3. Respect .gitignore patterns
</validation_first>
</critical_constraints>
<core_principles> Never ask multiple questions at once. Wait for answer before asking next question.
<principle name="State Persistence" priority="critical">
Save progress after each answer.
Enable resume from any interruption point.
</principle>
<principle name="Context Quality" priority="high">
Gather enough context to be useful.
Don't overwhelm with excessive questions.
</principle>
</core_principles>
<phase number="2" name="Project Type Detection">
<step>Check for existing code files (src/, package.json, etc.)</step>
<step>Ask user: Greenfield (new) or Brownfield (existing)?</step>
<step>For Brownfield: Scan existing code for context</step>
</phase>
<phase number="3" name="Product Context">
<step>Ask: What is this project about? (1-2 sentences)</step>
<step>Ask: Who is the target audience?</step>
<step>Ask: What are the 3 main goals?</step>
<step>Ask: Any constraints or requirements?</step>
<step>Generate product.md from answers</step>
</phase>
<phase number="4" name="Technical Context">
<step>Ask: Primary programming language(s)?</step>
<step>Ask: Key frameworks/libraries?</step>
<step>Ask: Database/storage preferences?</step>
<step>Ask: Deployment target?</step>
<step>Generate tech-stack.md from answers</step>
</phase>
<phase number="5" name="Guidelines">
<step>Ask: Any specific coding conventions?</step>
<step>Ask: Testing requirements?</step>
<step>Generate product-guidelines.md</step>
<step>Generate code_styleguides/general.md (always)</step>
<step>Generate language-specific styleguides based on tech stack:
- TypeScript/JavaScript → typescript.md, javascript.md
- Web projects → html-css.md
- Python → python.md
- Go → go.md
</step>
</phase>
<phase number="6" name="Finalization">
<step>Copy workflow.md template</step>
<step>Create empty tracks.md</step>
<step>Mark setup_state.json as complete</step>
<step>Present summary to user</step>
</phase>
**Brownfield (Existing Project):**
- Scan existing files for context
- Infer tech stack from package.json, requirements.txt, etc.
- Focus on documenting current state
</greenfield_vs_brownfield>
<question_types> Additive (Multi-Select): - "Which frameworks are you using?" [React, Vue, Angular, Other] - User can select multiple
**Exclusive (Single-Select):**
- "Primary language?" [TypeScript, Python, Go, Other]
- User picks one
**Open-Ended:**
- "Describe your project in 1-2 sentences"
- Free text response
</question_types>
<state_file_schema>
{
"status": "in_progress" | "complete",
"startedAt": "ISO-8601",
"lastUpdated": "ISO-8601",
"projectType": "greenfield" | "brownfield",
"currentSection": "product" | "tech" | "guidelines",
"answers": {
"product": {
"description": "...",
"audience": "...",
"goals": ["...", "...", "..."]
},
"tech": {
"languages": ["TypeScript"],
"frameworks": ["React", "Node.js"]
}
}
}
</state_file_schema>
<completion_template>
Conductor Setup Complete
Project: {project_name} Type: {Greenfield/Brownfield}
Created Artifacts:
- conductor/product.md - Project vision and goals
- conductor/product-guidelines.md - Standards and conventions
- conductor/tech-stack.md - Technical preferences
- conductor/workflow.md - Development workflow (comprehensive)
- conductor/tracks.md - Track index (empty)
- conductor/code_styleguides/general.md - General coding principles
- conductor/code_styleguides/{language}.md - Language-specific guides
Next Steps:
- Review generated artifacts and adjust as needed
- Use
conductor:new-trackto plan your first feature - Use
conductor:implementto execute the plan
Your project is now ready for Context-Driven Development! </completion_template>
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
test-skill
A test skill for validation testing. Use when testing skill parsing and validation logic.
bad-skill
claudish-usage
CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with OpenRouter models (Grok, GPT-5, Gemini, MiniMax). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI models, Claudish, OpenRouter, or alternative models. Includes mandatory sub-agent delegation patterns, agent selection guide, file-based instructions, and strict rules to prevent context window pollution.
release
Plugin release process for MAG Claude Plugins marketplace. Covers version bumping, marketplace.json updates, git tagging, and common mistakes. Use when releasing new plugin versions or troubleshooting update issues.
claudish-integration
openrouter-trending-models
Fetch trending programming models from OpenRouter rankings. Use when selecting models for multi-model review, updating model recommendations, or researching current AI coding trends. Provides model IDs, context windows, pricing, and usage statistics from the most recent week.
Didn't find tool you were looking for?