This skill should be used when the user asks about "conductor methodology", "context-driven development", "conductor directory structure", "conductor files", "tracks.md", "plan.md", "spec.md", or when commands reference conductor concepts. Provides comprehensive understanding of the Conductor framework for Context-Driven Development.
/plugin marketplace add ShalomObongo/claude-conductor/plugin install shalomobongo-claude-conductor@ShalomObongo/claude-conductorThis skill inherits all available tools. When active, it can use any tool Claude has access to.
examples/sample-track/metadata.jsonexamples/sample-track/plan.mdexamples/sample-track/spec.mdreferences/brownfield-analysis.mdscripts/validate-conductor.shConductor implements Context-Driven Development, a methodology that treats project context as a first-class artifact alongside code. This skill provides essential knowledge about the Conductor framework, directory structure, file formats, and core concepts.
Measure twice, code once. Conductor enforces a strict workflow:
This approach ensures AI agents follow consistent, high-quality development practices with proper planning and context awareness.
When Conductor is active in a project, it creates and manages this structure:
conductor/
├── product.md # Product vision, users, goals
├── product-guidelines.md # Brand voice, design principles, UX guidelines
├── tech-stack.md # Languages, frameworks, architecture, tools
├── workflow.md # Development methodology (TDD, commits, testing)
├── code_styleguides/ # Language-specific style guides
│ ├── general.md
│ ├── javascript.md
│ ├── typescript.md
│ ├── python.md
│ ├── go.md
│ └── html-css.md
├── tracks.md # Master list of all tracks
└── tracks/
└── <track_id>/
├── metadata.json # Track metadata (ID, title, type, status, dates)
├── spec.md # Detailed requirements and acceptance criteria
└── plan.md # Hierarchical implementation plan
A track is a logical unit of work - a feature, bug fix, or chore. Each track has:
track_20231215_143022)Detailed requirements document for a track, including:
Hierarchical implementation plan with three levels:
Each item has a status marker:
[ ] - Pending (not started)[~] - In Progress (currently working)[x] - Completed (done)[!] - Blocked (cannot proceed)The workflow.md file defines the development process, including:
Master list of all tracks:
# Conductor Tracks
## Active Tracks
### [ ] Track: Add user authentication
- **ID**: track_20231215_143022
- **Type**: Feature
- **Status**: In Progress
- **Created**: 2023-12-15
### [ ] Track: Fix login redirect bug
- **ID**: track_20231215_150033
- **Type**: Bug
- **Status**: Pending
- **Created**: 2023-12-15
## Completed Tracks
### [x] Track: Setup project infrastructure
- **ID**: track_20231214_120000
- **Type**: Chore
- **Status**: Completed
- **Created**: 2023-12-14
- **Completed**: 2023-12-15
Track metadata in JSON:
{
"track_id": "track_20231215_143022",
"title": "Add user authentication",
"type": "feature",
"status": "in-progress",
"created_at": "2023-12-15T14:30:22Z",
"updated_at": "2023-12-15T16:45:00Z"
}
Hierarchical plan with status markers:
# Implementation Plan: Add User Authentication
## Phase 1: Backend API
### [ ] Task: Create user model
- [ ] Sub-task: Define user schema
- [ ] Sub-task: Add email and password fields
- [ ] Sub-task: Add timestamps
### [~] Task: Implement authentication endpoints
- [x] Sub-task: Create /register endpoint
- [~] Sub-task: Create /login endpoint
- [ ] Sub-task: Create /logout endpoint
### [ ] Task: Conductor - User Manual Verification 'Backend API' (Protocol in workflow.md)
## Phase 2: Frontend UI
### [ ] Task: Create login form
- [ ] Sub-task: Design form layout
- [ ] Sub-task: Add form validation
- [ ] Sub-task: Connect to API
### [ ] Task: Conductor - User Manual Verification 'Frontend UI' (Protocol in workflow.md)
Existing projects with code, dependencies, or version control. Conductor analyzes:
Pre-populates context files based on analysis.
New projects starting from scratch. Conductor guides through:
Defines product vision and goals:
Establishes brand and design standards:
Documents technical decisions:
Defines development process:
Use consistent markers throughout plans:
| Marker | Status | Meaning |
|---|---|---|
[ ] | Pending | Not started |
[~] | In Progress | Currently working |
[x] | Completed | Done |
[!] | Blocked | Cannot proceed |
If workflow.md defines a "Phase Completion Verification and Checkpointing Protocol", each phase must include a final verification task:
### [ ] Task: Conductor - User Manual Verification '<Phase Name>' (Protocol in workflow.md)
This ensures quality gates at phase boundaries.
Conductor provides five commands:
Conductor is Git-aware:
For detailed patterns and advanced techniques, consult:
references/brownfield-analysis.md - Brownfield project analysis patternsreferences/plan-generation.md - Plan generation strategiesexamples/sample-track/ - Complete example track/claude-conductor:setup/claude-conductor:newTrack/claude-conductor:newTrack "Feature description"/claude-conductor:implement/claude-conductor:status/claude-conductor:revertWhen commands reference conductor concepts, use this skill to understand:
This knowledge enables accurate implementation of conductor workflows and proper maintenance of conductor artifacts.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.