Context-driven development methodology. Understands projects set up with Conductor (via Gemini CLI or Claude Code). Use when working with conductor/ directories, tracks, specs, plans, or when user mentions context-driven development.
/plugin marketplace add ReinaMacCredy/my-workflow/plugin install reinamaccredy-my-workflow@ReinaMacCredy/my-workflowThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/workflows.mdMeasure twice, code once.
Conductor enables context-driven development by:
Conductor implements the Knowledge & Vibes 4-phase framework:
| Phase | Purpose | Conductor Equivalent |
|---|---|---|
| Requirements | Understand problem completely before code | /conductor-newtrack questions → spec.md |
| Plan | Create detailed plan BEFORE writing code | spec.md → plan.md generation |
| Implement | Build incrementally with TDD | bd ready → execution via plan-executor |
| Reflect | Verify before shipping | verification-before-completion + bd close |
Key Questions per Phase:
Interoperability: This skill understands conductor projects created by either:
/conductor:setup, /conductor:newTrack, etc.)/conductor-setup, /conductor-newtrack, etc.)Both tools use the same conductor/ directory structure.
Automatically engage when:
conductor/ directoryconductor/tracks.md, conductor/product.md existUsers can invoke these commands directly:
| Command | Description |
|---|---|
/conductor-setup | Initialize project with product.md, tech-stack.md, workflow.md |
/conductor-newtrack [desc] | Create new feature/bug track with spec and plan |
/conductor-implement [id] | Execute tasks from track's plan |
/conductor-status | Display progress overview |
/conductor-revert | Git-aware revert of work |
When users express these intents, invoke the corresponding workflow:
| User Intent | Action | Command |
|---|---|---|
| "Set up this project" / "Initialize conductor" | Run setup workflow | /conductor-setup |
| "Create a new feature" / "Add a track for X" | Create new track | /conductor-newtrack [desc] |
| "Start working" / "Implement the feature" | Begin implementation | /conductor-implement |
| "What's the status?" / "Show progress" | Display status | /conductor-status |
| "Undo that" / "Revert the last task" | Revert work | /conductor-revert |
| "Check for issues" / "Validate the project" | Run validation | /conductor-validate |
| "This is blocked" / "Can't proceed" | Mark as blocked | /conductor-block |
| "Skip this task" | Skip current task | /conductor-skip |
| "Archive completed tracks" | Archive tracks | /conductor-archive |
| "Export project summary" | Generate export | /conductor-export |
When this skill activates, automatically load:
conductor/product.md - Understand the productconductor/tech-stack.md - Know the tech constraintsconductor/workflow.md - Follow the methodologyconductor/tracks.md - Current work statusFor active tracks, also load:
conductor/tracks/<track_id>/spec.mdconductor/tracks/<track_id>/plan.mdconductor/tracks/<track_id>/implement_state.json (if exists)When skill is active:
When you see this structure, the project uses Conductor:
conductor/
├── product.md # Product vision, users, goals
├── product-guidelines.md # Brand/style guidelines (optional)
├── tech-stack.md # Technology choices
├── workflow.md # Development standards (TDD, commits, coverage)
├── tracks.md # Master track list with status markers
├── setup_state.json # Setup progress tracking
├── code_styleguides/ # Language-specific style guides
└── tracks/
└── <track_id>/ # Format: shortname_YYYYMMDD
├── metadata.json # Track type, status, dates
├── spec.md # Requirements and acceptance criteria
└── plan.md # Phased task list with status
Throughout conductor files:
[ ] - Pending/New[~] - In Progress[x] - Completed (often followed by 7-char commit SHA)When working in a Conductor project:
conductor/product.md - Understand what we're building and for whomconductor/tech-stack.md - Know the technologies and constraintsconductor/workflow.md - Follow the development methodology (usually TDD)conductor/tracks.md - See all work items and their statusspec.md and plan.mdWhen implementing tasks, follow conductor/workflow.md which typically specifies:
feat:, fix:, test:, etc.)[~] when starting, [x] when done + commit SHAProjects set up with Gemini CLI's Conductor extension use identical structure. The only differences are command syntax:
| Gemini CLI | Claude Code |
|---|---|
/conductor:setup | /conductor-setup |
/conductor:newTrack | /conductor-newtrack |
/conductor:implement | /conductor-implement |
/conductor:status | /conductor-status |
/conductor:revert | /conductor-revert |
Files, workflows, and state management are fully compatible.
When you see conductor/tracks.md with content like:
## [~] Track: Add user authentication
*Link: [conductor/tracks/auth_20241215/](conductor/tracks/auth_20241215/)*
You know:
conductor/tracks/auth_20241215/conductor/workflow.mdFor detailed workflow documentation, see references/workflows.md.
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 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 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.