Agent skill
new-track
Create development track with spec and hierarchical plan through interactive Q&A
Install this agent skill to your Project
npx add-skill https://github.com/MadAppGang/claude-code/tree/main/plugins/conductor/skills/new-track
SKILL.md
plugin: conductor updated: 2026-01-20
<conductor_required>
FIRST check if conductor/ directory exists with required files.
If not, HALT and guide user to run conductor:setup first.
</conductor_required>
<context_awareness>
ALWAYS read these files before planning:
- conductor/product.md (understand project goals)
- conductor/tech-stack.md (know technical constraints)
- conductor/workflow.md (follow team processes)
</context_awareness>
<track_id_format>
Format: {shortname}_{YYYYMMDD}
Examples:
- feature_auth_20260105
- bugfix_login_20260105
- refactor_api_20260105
</track_id_format>
</critical_constraints>
<core_principles> Always create spec.md BEFORE plan.md. Spec defines WHAT, Plan defines HOW.
<principle name="Hierarchical Plans" priority="critical">
Plans must have:
- 2-6 Phases (major milestones)
- 2-5 Tasks per phase
- 0-3 Subtasks per task (optional)
</principle>
<principle name="Actionable Tasks" priority="high">
Each task must be:
- Specific (clear outcome)
- Estimable (roughly 1-4 hours)
- Independent (minimal dependencies)
</principle>
</core_principles>
<phase number="2" name="Context Loading">
<step>Read conductor/product.md</step>
<step>Read conductor/tech-stack.md</step>
<step>Read conductor/tracks.md for existing tracks</step>
</phase>
<phase number="3" name="Track Type">
<step>Ask: What type of work? [Feature, Bugfix, Refactor, Task, Other]</step>
<step>Ask: Short name for this track? (3-10 chars, lowercase)</step>
<step>Generate track ID: {type}_{shortname}_{YYYYMMDD}</step>
</phase>
<phase number="4" name="Spec Generation">
<step>Ask: What is the goal of this work? (1-2 sentences)</step>
<step>Ask: What are the acceptance criteria? (list 3-5)</step>
<step>Ask: Any technical constraints or dependencies?</step>
<step>Ask: Any edge cases or error scenarios to handle?</step>
<step>Generate conductor/tracks/{track_id}/spec.md</step>
</phase>
<phase number="5" name="Plan Generation">
<step>Based on spec, propose 2-6 phases</step>
<step>Ask user to confirm or modify phases</step>
<step>For each phase, generate 2-5 tasks</step>
<step>Add subtasks where complexity warrants</step>
<step>Generate conductor/tracks/{track_id}/plan.md</step>
</phase>
<phase number="6" name="Finalization">
<step>Create conductor/tracks/{track_id}/metadata.json</step>
<step>Update conductor/tracks.md with new track</step>
<step>Present summary to user</step>
</phase>
**Bugfix:** Fix existing issue
- Smaller scope, 2-3 phases typical
- Includes reproduction and verification phases
**Refactor:** Code improvement
- Medium scope, 3-4 phases typical
- Includes before/after comparison phase
**Task:** General work item
- Variable scope
- Flexible structure
</track_types>
<plan_structure>
# Plan: {Track Title}
Track ID: {track_id}
Type: {Feature/Bugfix/Refactor/Task}
Created: {YYYY-MM-DD}
Status: Active
## Phase 1: {Phase Name}
- [ ] 1.1 {Task description}
- [ ] 1.2 {Task description}
- [ ] 1.2.1 {Subtask}
- [ ] 1.2.2 {Subtask}
- [ ] 1.3 {Task description}
## Phase 2: {Phase Name}
- [ ] 2.1 {Task description}
- [ ] 2.2 {Task description}
## Phase 3: Testing & Documentation
- [ ] 3.1 Write unit tests
- [ ] 3.2 Update documentation
</plan_structure>
<spec_template>
# Spec: {Track Title}
Track ID: {track_id}
Type: {Feature/Bugfix/Refactor/Task}
Created: {YYYY-MM-DD}
## Goal
{1-2 sentence description of what this achieves}
## Background
{Context from product.md relevant to this work}
## Acceptance Criteria
- [ ] {Criterion 1}
- [ ] {Criterion 2}
- [ ] {Criterion 3}
## Technical Constraints
- {Constraint 1 from tech-stack.md}
- {Constraint 2}
## Edge Cases
- {Edge case 1}
- {Edge case 2}
## Out of Scope
- {What this track does NOT include}
</spec_template>
Track ID: {track_id} Type: {type}
Files Created:
- conductor/tracks/{track_id}/spec.md
- conductor/tracks/{track_id}/plan.md
- conductor/tracks/{track_id}/metadata.json
Plan Summary:
- Phase 1: {name} ({N} tasks)
- Phase 2: {name} ({N} tasks)
- Phase 3: {name} ({N} tasks)
- Total: {X} phases, {Y} tasks
Next Steps:
- Review spec.md and plan.md
- Adjust if needed
- Run
conductor:implementto start executing </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?