Browse skills

Define and develop plugin mission statements — purpose, values, anti-patterns, and trade-offs. Use when creating a new plugin, auditing an existing plugin's alignment, or providing a reference for the alignment check loop to evaluate decisions against. Produces mission.json with [draft] status and writes an interview file for the human to refine it.

The English summary is being prepared. Showing the original description.

Optimize existing CLAUDE.md, SKILL.md, agent definitions, and other AI-facing files for Claude comprehension and economy. Scope: optimization of existing content only — not upstream sync, not read-only auditing. Measures baseline metrics, delegates to the ai-doc-optimizer agent with file-type-specific context, runs independent verification via second agent, measures post-optimization metrics, and presents comprehensive before/after report. Supports iterative mode for large targets. Use when improving prompt effectiveness, reducing token waste, or rewriting instructions for LLM consumption. Invoke with /optimize-claude-md <file-or-directory>.

The English summary is being prepared. Showing the original description.

Use when writing delegation instructions to subagents, authoring CLAUDE.md files, rules, skills, or agent definitions, or auditing existing AI-facing content for bloat. Activates on "write a rule for", "add to CLAUDE.md", "create an agent", "update memory", or any request to author AI-facing instruction content. Removes discoverable data, explained-away knowledge, invented constraints, and stale cached facts.

The English summary is being prepared. Showing the original description.

Create, validate, and diagnose Claude Code output styles — the file that sets Claude's role, tone, and response format for every turn. Use when asked to write, bundle, or force an output style for a plugin, to set keep-coding-instructions or force-for-plugin, when a style is not taking effect or the wrong one applies, or when choosing between an output style, CLAUDE.md, a skill, and an agent for a persistent behavior change.

The English summary is being prepared. Showing the original description.

Plugin creator documentation index. Load when needing to read about plugin validation error codes, skill creation, agent creation, or plugin structure.

The English summary is being prepared. Showing the original description.

Per-project plugin configuration via .local.md files — covers the .claude/plugin-name.local.md pattern for storing user-configurable settings with YAML frontmatter and markdown body. Use when implementing plugin settings, reading YAML frontmatter from hooks, creating configuration-driven behavior, managing agent state files, or adding per-project plugin configuration. Covers file structure, parsing techniques, common patterns (temporarily active hooks, agent state management, configuration-driven behavior), security considerations, and best practices.

The English summary is being prepared. Showing the original description.

Create or adapt Claude Code agent definitions. Use when creating an agent, changing subagent configuration, selecting agent scope, or designing a specialized delegation role.

The English summary is being prepared. Showing the original description.

Knowledge reference for Autonomous Refinement Loop research — pattern research into prerequisites for autonomous execution without synchronous human blocking gates. Defines failure categories, prerequisites, and conditions for replacing human judgment with machine-verifiable checks. Use when designing or evaluating autonomous agent loops, gate conditions, or HOOTL execution patterns.

The English summary is being prepared. Showing the original description.

Audit agent lifecycle — validates agent execution capability against configuration. Accepts plugin path, runs 8 semantic audits (capability vs config alignment, skill loading correctness, inter-agent contracts, prompt contradictions, tool sufficiency, dead agents, scriptable patterns, pattern learning), writes reports to .plugin-creator/audits/. Use when auditing agent lifecycle, checking agent capabilities, verifying tool access, finding dead agents, validating agent contract alignment, or confirming agents can execute workflows.

The English summary is being prepared. Showing the original description.

Audit skill lifecycle by tracing call chains, detecting circular dependencies, finding instruction contradictions, identifying duplicated datasets, analyzing bidirectional coherence, discovering scriptable sequences, and learning patterns. Use when checking skill coherence, validating skill workflow, finding semantic gaps in plugin structure, or auditing plugin before marketplace submission. Generates audit reports to .plugin-creator/audits/ with findings by dimension.

The English summary is being prepared. Showing the original description.

Claude Code plugin and marketplace router. Use when creating plugins, configuring component paths, resolving installed files, validating plugin roots, or distributing local, Git, and archive sources.

The English summary is being prepared. Showing the original description.

Claude Code runtime skills router. Use when configuring SKILL.md frontmatter, discovery, invocation, hooks, context forks, substitutions, loading behavior, or headless skill dispatch.

The English summary is being prepared. Showing the original description.

This skill should be used when the user asks to install Perl modules, use cpanm, create a cpanfile, manage Perl dependencies, set up Carton, configure local lib, or mentions CPAN, cpanminus, module installation, or Perl package management.

The English summary is being prepared. Showing the original description.

Validate whether an implementation plan can achieve its stated outcome before execution. Use to check requirement coverage, task contracts, dependencies, data/artifact flow, testability, ownership, impact coverage, and executable ordering without checking whether implementation already exists.

The English summary is being prepared. Showing the original description.

Verify one falsifiable factual claim against evidence appropriate to the claim. Use when a concrete assertion about software, documentation, configuration, releases, or repository behavior must be classified as VERIFIED, REFUTED, or INCONCLUSIVE.

The English summary is being prepared. Showing the original description.

Use when asked to find a rage moment, analyze a direct transcript path, or analyze a session time range. RTFP finds the strongest instruction-following failure in Claude or Codex sessions and renders a rage receipt.

The English summary is being prepared. Showing the original description.

Discover and run configured quality gates for requested or changed work, preserve diagnostics as evidence, route failures to the appropriate causal/domain capability, and verify corrections. Use for linting, formatting, type-checking, configured hook checks, or pre-completion quality verification.

The English summary is being prepared. Showing the original description.

When calling LLM APIs from Python code. When connecting to llamafile or local LLM servers. When switching between OpenAI/Anthropic/local providers. When implementing retry/fallback logic for LLM calls. When code imports litellm or uses completion() patterns.

The English summary is being prepared. Showing the original description.

Spawn and manage persistent interactive Claude Code CLI sessions with bidirectional communication via tmux. Provides spawn, send, read, status, list, and kill subcommands for orchestrating parallel peer sessions. Uses built-in --worktree and --tmux flags. Sessions stay alive for multi-turn steering. Triggers on "spawn claude session", "launch separate claude", "peer session", "inter-session communication", "shadow clone", "kage bunshin".

The English summary is being prepared. Showing the original description.

Use when a diff needs four parallel perspective reviewers (Security, Performance, Quality, Accessibility). Creates an ephemeral SAM plan, collects structured verdicts, synthesizes them into one deduplicated cross-referenced punch list, prints one summary line per perspective, and exits non-zero if any perspective returns REJECT. SKIP is a passing outcome.

The English summary is being prepared. Showing the original description.

Use when Stage 1 Discovery is complete and design must begin — transforms the ARTIFACT:DISCOVERY into an actionable ARTIFACT:PLAN via RT-ICA prerequisite verification. Produces approach, components, success criteria, acceptance tests, and risks. Blocks on missing prerequisites before design proceeds.

The English summary is being prepared. Showing the original description.

Synthesis step in the multi-angle technical research pipeline. Receives structured outputs from all four research angles (api-state, ecosystem-research, impact-measurement, codebase-auditor), applies cross-angle signal weighting and conflict resolution, and produces a single synthesized Research section. Invoked by the technical-researcher orchestrator after all angle skills complete. Returns content to the orchestrator — does not write to the backlog.

The English summary is being prepared. Showing the original description.

Review changed user-interface or CLI presentation behavior for accessibility failures. Use for an independent accessibility perspective on a defined change set.

The English summary is being prepared. Showing the original description.

Review a change for material performance regressions or unbounded resource behavior. Use for an independent performance perspective on a defined change set.

The English summary is being prepared. Showing the original description.