MUST BE LOADED BEFORE modifying docs/PROJECT.md. Also load when user mentions PROJECT.md in ANY form (docs/PROJECT.md, @docs/PROJECT.md, "the project file", etc.) or discusses tasks/tracking. Triggers include: "add a task", "add this task", "update PROJECT.md", "mark as done", "mark complete", "track this", "next task", "what's next", "work on next", create tickets/issues, write feature docs, create PRD, manage TODO.md/STATUS.md, "add a feature", "improve X to allow Y", plan features, break down tasks, or ANY project/task management discussion. This skill handles all project planning, documentation, and work tracking through docs/PROJECT.md or external tools (GitHub Projects, Jira).
Manages project tasks and documentation through docs/PROJECT.md. Triggers when you mention PROJECT.md, discuss tasks/tracking, request features, or say "add task", "mark done", "work on next", "create PRD", or similar project management phrases.
/plugin marketplace add fx/cc/plugin install fx-dev@fx-ccThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/project-md-template.mdThis skill manages project tasks and documentation for AI-driven development. All work is tracked in docs/PROJECT.md (or linked external tools) and results in pull requests.
docs/PROJECT.md is the central tracking documentCRITICAL: Load this skill BEFORE reading, modifying, or editing docs/PROJECT.md. Do not use Read/Edit tools on PROJECT.md without loading this skill first.
Load this skill IMMEDIATELY when:
docs/PROJECT.md, @docs/PROJECT.md, "project file", "project tasks"agent-fx-research:tech-scout - Research libraries, technologies, solutionsagent-Explore - Explore codebase structure, patterns, implementationsagent-Plan - Design implementation plansagent-fx-dev:coder - Implement features, fix bugsagent-fx-dev:planner - Create detailed implementation plansagent-fx-dev:pr-preparer - Prepare and create pull requestsagent-fx-dev:sdlc - Orchestrate complete development lifecycleWhen working with GitHub issues or projects:
Skill tool with skill="fx-dev:github"gh CLI for all GitHub operationsTo create or understand the PROJECT.md format, read the template at:
references/project-md-template.md
- [x] Task name (PR #N)- [ ] Task (#123) when linked to GitHub issueWhen user says "add a feature that does X" or "improve X to allow Y":
Analyze deeply
agent-Explore to understand current codebaseagent-fx-research:tech-scout if technology decisions neededDetermine scope
Clarify ambiguity via AskUserQuestion:
Update PROJECT.md with tasks (if breakdown needed)
Get approval then begin work on first task
When user says "work on next issue", "next feature", or "what's next":
Read docs/PROJECT.md
Select next uncompleted task (top of list = highest priority)
Announce the task to user
Execute using development agents
Update PROJECT.md marking task complete with PR number
Ensure PR includes PROJECT.md update
When user requests PRD or feature documentation:
Gather requirements via AskUserQuestion
Research context using agent-Explore and agent-fx-research:tech-scout
Create PRD in docs/ folder
Update PROJECT.md with reference and tasks
Create PR with documentation
When GitHub Projects, Jira, or other tools are available:
Load GitHub skill if using GitHub
Create issues/tickets in external tool
Update PROJECT.md to reference external tracking
Link tasks between PROJECT.md and external tool
When docs/PROJECT.md doesn't exist:
Explore the project using agent-Explore
Ask about tracking preferences via AskUserQuestion:
Read the template at references/project-md-template.md
Create PROJECT.md with initial backlog
Migrate existing tracking (TODO.md, STATUS.md) if present
- [x] Task (PR #N)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.