Use this skill when the user asks about Conductor concepts, workflow patterns, track lifecycle, plan structures, or context-driven development principles. Also activate when working with conductor/ directory files or when implementing tasks following TDD and verification protocols.
Guides developers through Conductor's context-driven workflows for structured planning, implementation, and track lifecycle management.
/plugin marketplace add https://www.claudepluginhub.com/api/plugins/rbarcante-conductor/marketplace.json/plugin install rbarcante-conductor@cpd-rbarcante-conductorThis skill inherits all available tools. When active, it can use any tool Claude has access to.
SKILL-SUMMARY.mdmanifest.jsonConductor is a context-driven development framework that structures software development through a rigorous lifecycle: Context → Spec & Plan → Implement. This skill provides guidance on Conductor's principles, file structures, and workflows.
Measure twice, code once. Conductor treats context as a managed artifact alongside code, transforming repositories into a single source of truth that drives every agent interaction with deep, persistent project awareness.
Located in the conductor/ directory at project root:
product.md: Product vision, users, goals, and featuresproduct-guidelines.md: Prose style, brand messaging, visual identitytech-stack.md: Technology choices, languages, frameworks, databasesworkflow.md: Development workflow (TDD, commit strategy, coverage requirements)code_styleguides/: Language-specific coding standardstracks.md: Master list of all tracks with status and linksEach track lives in conductor/tracks/<track_id>/:
spec.md: Detailed requirements for the trackplan.md: Hierarchical plan with phases, tasks, and sub-tasksdecisions.md: Architecture Decision Records for track decisionsreview.md: Auto-generated code review report on track completionmetadata.json: Track metadata (ID, type, status, timestamps)Tracks represent high-level units of work (features, bugs, chores):
/conductor:newTrack): Generate spec and plan[~] when work begins[x] when all tasks finishPlans use hierarchical markdown with status markers:
# Phase 1: Foundation
- [ ] Task: Set up database schema
- [ ] Create users table
- [ ] Create posts table
- [ ] Add indexes
- [~] Task: Implement user model
- [x] Write failing tests
- [~] Implement User class
# Phase 2: Features
- [ ] Task: Build authentication
[ ] - Pending[~] - In progress[x] - Completed# Phase Name)- [ ] Task: Description- [ ] Description- [x] Task: Description [abc1234])# Phase 1 [checkpoint: def5678])Standard workflow from workflow.md:
[ ] to [~] in planWhen a phase completes:
CI=trueconductor(checkpoint): Checkpoint end of Phase Xfeat(module): Add feature descriptionfix(module): Fix issue descriptiontest(module): Add tests for featureconductor(plan): Mark task 'description' as completeconductor(checkpoint): Checkpoint end of Phase Xconductor(track): Create track 'description'conductor(setup): Add conductor setup filesdocs(conductor): Synchronize docs for track 'description'Conductor uses git notes for auditable tracking:
Attached to implementation commits with format:
Task: <Task Name>
Summary: <Brief description of changes>
Files Changed:
- path/to/file1.ts
- path/to/file2.ts
Why: <Rationale for changes>
Attached to checkpoint commits with format:
Phase: <Phase Name>
Automated Tests: <Command run and result>
Manual Verification:
- Step 1: <Action and expected result>
- Step 2: <Action and expected result>
User Confirmation: <User's confirmation statement>
When gathering requirements or context:
For brainstorming and scope (users, goals, features):
For singular commitments (technology selection, workflow rules):
Always include:
Track IDs follow the pattern: shortname_YYYYMMDD
Examples:
darkmode_20260113 - Add dark mode featurebugfix_20260113 - Fix login issuerefactor_20260113 - Refactor database layerTracks setup progress for resumability:
{
"last_successful_step": "2.3_tech_stack"
}
Possible values:
"" - Initial state"2.1_product_guide" - Product guide complete"2.2_product_guidelines" - Guidelines complete"2.3_tech_stack" - Tech stack complete"2.4_code_styleguides" - Style guides copied"2.5_workflow" - Workflow configured"3.3_initial_track_generated" - Setup fully complete{
"track_id": "feature_20260113",
"type": "feature",
"status": "in_progress",
"created_at": "2026-01-13T10:30:00Z",
"updated_at": "2026-01-13T15:45:00Z",
"description": "Add user authentication"
}
[x])Conductor provides git-aware revert for logical units:
All commands are invoked with /conductor:<command>:
/conductor:setup - Initialize project/conductor:newTrack [description] - Create new track/conductor:implement [track] - Execute track plan/conductor:status - Show progress overview/conductor:revert [target] - Revert workCommands use Claude Code tools (Read, Write, Edit, Bash, Glob, Grep) and follow plugin best practices.
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
Search, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, install a skill for Claude, or extend Claude's capabilities with reusable AI agent components.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.