SYSTEM STANDARD: MANDATES ALL project planning document formats, templates, and protocols. YOU MUST ACTIVATE THIS SKILL WHEN creating or editing ANY BRIEF.md, ROADMAP.md, PLAN.md, ADR, or ISSUES entries.
/plugin marketplace add Git-Fg/cat-toolkit-marketplace/plugin install project-orchestrator@cat-toolkit-marketplaceThis skill is limited to using the following tools:
assets/templates/adr-entry.mdassets/templates/brief.mdassets/templates/issue-entry.mdassets/templates/issues.mdassets/templates/phase-plan.mdassets/templates/roadmap.mdreferences/adr-format.mdreferences/context-management.mdreferences/git-integration.mdreferences/issues-format.mdreferences/phase-patterns.mdreferences/plan-format.mdreferences/scope-estimation.mdYOU MUST ACTIVATE THIS SKILL WHEN:
PROACTIVELY REFERENCE:
assets/templates/ BEFORE creating any documentreferences/plan-format.md if structuring PLAN.mdreferences/phase-patterns.md when breaking down work into phasesreferences/scope-estimation.md when estimating task complexityreferences/context-management.md when context limits are a concernreferences/ for ALL planning protocol standards| Document Type | MANDATED Template | REQUIRED FOR |
|---|---|---|
| Project Brief | assets/templates/brief.md | ALL project starts |
| Roadmap | assets/templates/roadmap.md | ALL multi-phase projects |
| Phase Plan | assets/templates/phase-plan.md | ALL executable phases |
| ADR Entry | assets/templates/adr-entry.md | ALL architecture decisions |
| Issue Entry | assets/templates/issue-entry.md | ALL deferred enhancements |
| Issues File | assets/templates/issues.md | ISSUES.md creation |
Project Documents: .cattoolkit/planning/{project-slug}/
assets/templates/brief.mdassets/templates/roadmap.mdassets/templates/adr-entry.mdassets/templates/issues.mdPhase Documents: .cattoolkit/planning/{project-slug}/phases/XX-name/
assets/templates/phase-plan.mdMANDATORY FORMAT FOR ALL DOCUMENTS:
BRIEF.md:
---
project: [Project Name]
version: 1.0
status: in_progress
---
ROADMAP.md:
---
project: [Project Name]
version: 1.0
status: in_progress
---
PLAN.md:
---
phase: XX-name
type: execute
domain: [optional]
status: in_progress
---
VALID STATUS VALUES: in_progress, completed
YOU MUST READ references/plan-format.md BEFORE CREATING ANY PLAN.md
REQUIRED SECTIONS:
YOU MUST READ references/git-integration.md BEFORE COMMITTING
VALID COMMIT POINTS (ONLY 3):
MANDATED COMMIT FORMAT:
feat(domain): [one-liner from SUMMARY.md]
- [Key accomplishment 1]
- [Key accomplishment 2]
- [Key accomplishment 3]
STRICTLY PROHIBITED: Separate commits for PLAN.md creation, RESEARCH.md, FINDINGS.md, minor planning tweaks.
YOU MUST VERIFY ALL PLANNING DOCUMENTS AGAINST THESE STANDARDS:
BRIEF.md COMPLIANCE:
ROADMAP.md COMPLIANCE:
PLAN.md COMPLIANCE:
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.