Git-Fg

Create single-file commands with dynamic content injection (@path and !command). Use when building commands that need filesystem access, git state, runtime context, or argument handling with $1 placeholders. Includes @file injection, !shell execution, <injected_content> wrappers, and single-file structure patterns. Not for skills (use skill-development) or audit workflows.

Create and refine single-file commands with @/! injection. Use when authoring new commands or improving existing ones. Includes namespacing rules, thin interface patterns, and delegation best practices. Not for skills or agents.

Master Claude Code's context primitives (Skill, Task, Command) and orchestration patterns. Use when designing agent workflows, understanding why some patterns work while others fail (e.g., Task→Task is forbidden but Skill→Skill is allowed), or implementing Chain of Experts architectures. Not for writing prompts or content generation.

Verify completion with evidence using 6-phase gates and three-way audits. Use when claiming task completion, committing code, or validating components. Not for skipping verification or bypassing quality gates.

Audit skill files against quality standards. Use ONLY within Manager Pattern workflow via TaskList. Receives taskId, reads draftPath from task metadata, validates against skill-development rules, writes auditResult to task metadata. Not for manual use.

Create portable skills with SKILL.md. Use when building new skills or documenting patterns. Includes frontmatter syntax, quality standards, and primitives. Not for commands or agents.

Creates skills with automatic quality validation. Use when you need a new skill created with all quality gates enforced (frontmatter, navigation, critical_constraint). Uses TaskList for stateful retry loops with skill-auditor. Not for quick prototypes or when manual skill creation is preferred.

Create and audit Claude subagents. Use when building specialized workers with isolated context. Includes frontmatter, allowed-tools, and agent patterns. Not for commands or skills.

Design, build, and evaluate MCP servers end-to-end. Use when user says 'design an MCP server', 'decompose MCP tools', 'write a tool schema', 'implement an MCP server in Rust', 'call an MCP server from an agent', or 'evaluate MCP quality'. Five modes: DESIGN (decomposition, contracts), SCHEMA (JSON Schema), IMPLEMENT (Rust + rmcp), CLIENT (agent as consumer), QUALITY (8-dimension rubric, forked orchestrator spawns 8 parallel judge subagents).

Run a Plan-Do-Check-Act (PDCA) cycle to test a hypothesis with measurable success criteria. Use when user says 'run a PDCA cycle', 'test this hypothesis', 'A/B test this change', 'validate the improvement worked', or 'standardize this change'.

Archive completed plans, deduplicate stale memory, and clean auto-memory at the end of a project. Use when the user wants to wrap up a plan, clean up files, or run a memory cleanup pass.

Review a PR, simplify complex code, polish prose, or capture a project learning. Use when the user wants to improve the quality of an artifact (code, doc, PR) or consolidate insights into memory. Do NOT use for bug diagnosis or for creating new features.

Analyze Claude Code session transcripts to extract metrics, diagnose behavioral anti-patterns, and file GitHub issues from findings. Use when user says 'parse session log', 'session metrics', 'review session for anti-patterns', 'capture a session', 'cross-analyze artifacts', or 'create a meta-issue'. Modes: CAPTURE, INSPECT, REVIEW, ISSUE, CROSS-ANALYZE, ADJUDICATE.

Drive the Claude Code CLI from Bash — headless sessions, structured output, model/permission control, and code reviews. Use when an agent needs to run Claude programmatically.

Create, optimize, and test Claude Code skills, including metadata refinement and trigger benchmarking.

Add a feature, refine a spec, implement it, and update docs through a 4-stage task lifecycle. Use when user says 'add a feature', 'refine this spec', 'implement the task', 'build a feature', 'update the docs', or names a draft / spec path. Modes: CAPTURE (draft), REFINE (spec), IMPLEMENT (code + verify), DOCUMENT (docs).

This skill should be used when the user needs structured thinking frameworks to analyze decisions, problems, or tasks. Apply multiple decision-making methodologies (10/10/10, 5 Whys, Eisenhower Matrix, First Principles, Inversion, Occam's Razor, The One Thing, Opportunity Cost, Pareto, Second-Order Thinking, SWOT, Via Negativa) to ask probing questions and guide deep reflection. Use when the user asks to "think through", "analyze", "evaluate", "reflect on", or "brainstorm" decisions or problems.

Creates, refines, ingests, and evaluates agent skills using archetype-driven design. Use when building skills from scratch, extracting knowledge from documentation, or auditing skill quality. Do not use for non-skill related tasks or when other specialized skills are more appropriate.

General-purpose guidance for Claude Code (terminal) and Claude Dev (platform). Covers stable principles (progressive disclosure, hooks, security) and volatile details with lookup workflows.

Test Model Context Protocol (MCP) servers using the MCP Inspector CLI

Help design, refine, and validate OpenClaw skills, including SKILL.md structure, workflows, and helper scripts. Use when creating or updating skills that extend the OpenClaw agent with specialized knowledge, tools, or domain workflows. Not for general code development, system administration, or content creation without skill structure focus.

Hetzner Cloud VPS management via hcloud CLI. Use when: creating/deleting servers, power control (poweron/poweroff/reboot), SSH key management, server listing and status checks, quick SSH access. Requires hcloud CLI installed and HCLOUD_TOKEN configured.

Use when looking up OpenClaw documentation, CLI command references, configuration options, troubleshooting guides, or feature explanations. Fetches latest docs from docs.openclaw.ai.

Teaches Flutter MCP + Dart MCP best practices for vibe coding. Use when developing Flutter apps, running tests, debugging, or need hot reload/restart. Not for backend-only TypeScript/Node.js projects.

Runs, debugs, and fixes Flutter tests including unit tests, widget tests, and Patrol E2E tests. Use when tests fail, need updating after code changes, or when creating new tests. Not for general code debugging or feature implementation.

Executes automated tests on mobile apps via MCP. Use when testing iOS/Android apps, verifying UI states, automating interactions, or performing end-to-end validation. Not for web testing, API validation, or desktop applications.

Guide for building and auditing CLI tools optimized for AI agent consumption. Use when building or refactoring CLIs for agents, when users mention "agent-friendly CLI", "optimize CLI for AI", "token-efficient output", or when auditing CLI tools for agent usability. Key principles: zero-transformation returns, self-teaching --help, semantic density (text over JSON), and teaching forgotten patterns.

Unified planner+executor for continuous workflow

MUST BE USED when creating, improving, or reviewing Skills. Use PROACTIVELY when user mentions "create a skill", "new skill", "write a skill", "improve skill", "skill description", or "progressive disclosure". Guides through specification-compliant skill design with three-level progressive disclosure.