Use this skill when the user mentions "plan", "track", "spec", "conductor", asks about project progress, or references conductor files like plan.md, spec.md, tracks.md, product.md, tech-stack.md, or workflow.md. Also use when the user wants to understand the Conductor methodology or Context-Driven Development workflow.
/plugin marketplace add pedrovhb/conductor-claude/plugin install pedrovhb-conductor@pedrovhb/conductor-claudeThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Conductor is a workflow methodology that transforms Claude Code into a project manager following a strict protocol: Context -> Spec & Plan -> Implement.
Measure twice, code once. By treating context as a managed artifact alongside code, you transform your repository into a single source of truth that drives every agent interaction with deep, persistent project awareness.
A track is a high-level unit of work (feature or bug fix). Each track has:
spec.md - Detailed requirements and acceptance criteriaplan.md - Actionable to-do list with phases, tasks, and sub-tasksmetadata.json - Track metadata (ID, type, status, timestamps)Tracks are stored in conductor/tracks/<track_id>/.
Located in the conductor/ directory:
product.md - Product vision, goals, users, featuresproduct-guidelines.md - Prose style, brand messaging, visual identitytech-stack.md - Languages, frameworks, databases, toolsworkflow.md - Development methodology (TDD, commit strategy)tracks.md - Master list of all tracks and their statuscode_styleguides/ - Language-specific coding standards[ ] - Pending (not started)[~] - In progress (currently being worked on)[x] - Completed (finished and committed)When a user mentions "the plan" or "the spec", they likely refer to:
conductor/tracks/<track_id>/plan.mdconductor/tracks/<track_id>/spec.mdconductor/tracks.mdConductor follows Test-Driven Development by default:
At the end of each phase:
| Command | Purpose |
|---|---|
/conductor:setup | Initialize project context |
/conductor:new-track | Create new feature/bug track |
/conductor:implement | Execute tasks from plan |
/conductor:status | Display progress overview |
/conductor:revert | Rollback tracks/phases/tasks |
Templates are bundled with the plugin at ${CLAUDE_PLUGIN_ROOT}/templates/:
workflow.md - Default workflow configurationcode_styleguides/ - Language-specific style guidesThis 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.