文件操作
文件系统与批量文件任务
phase-review
mcouthon
"Review implementation plans for a particular phase in a larger plan for flaws before committing to them. Use when reviewing phase plans from .tasks/ directory. Triggers on: 'use phase mode', 'review phase', 'review the plan', 'check phase', 'validate phase', 'review phase N', 'check the plan for phase'."
deep-research
mcouthon
"Exhaustive investigation with citations and structured findings. Use when thorough coverage is needed, all sources must be cited, or research will inform critical decisions. Triggers on: 'use deep-research mode', 'deep research', 'exhaustive investigation', 'thorough research', 'cite all sources', 'comprehensive analysis', 'leave no stone unturned', 'research everything'. Read-only mode - investigates and documents but doesn't modify code."
deep-research
mcouthon
"Exhaustive investigation with citations and structured findings. Use when thorough coverage is needed, all sources must be cited, or research will inform critical decisions. Triggers on: 'use deep-research mode', 'deep research', 'exhaustive investigation', 'thorough research', 'cite all sources', 'comprehensive analysis', 'leave no stone unturned', 'research everything'. Read-only mode - investigates and documents but doesn't modify code."
phase-review
mcouthon
"Review implementation plans for a particular phase in a larger plan for flaws before committing to them. Use when reviewing phase plans from .tasks/ directory. Triggers on: 'use phase mode', 'review phase', 'review the plan', 'check phase', 'validate phase', 'review phase N', 'check the plan for phase'."
consolidate-task
mcouthon
"Use when you need to summarize a completed task into an architectural decision record, reducing clutter in .tasks/. Triggers on: 'use consolidate-task mode', 'consolidate-task', 'consolidate task', 'summarize task'."
tree-view
Dwsy
Display directory tree structure with customizable depth, using fd and Python3 for fast and beautiful tree visualization.
context7
Dwsy
Search GitHub issues, pull requests, and discussions across any repository. Activates when researching external dependencies (whisper.cpp, NAudio), looking for similar bugs, or finding implementation examples.
clawddocs
jdrhyne
Clawdbot documentation expert with decision tree navigation, search scripts, doc fetching, version tracking, and config snippets for all Clawdbot features
claude-code-plugins
melodic-software
"Validate the education plugin's quiz, report-library, and teach workspace-root configuration and explain how to change it through Claude Code's plugin configuration prompt. Use when: 'set up education', 'configure education', 'education setup', quiz offers feel wrong, report recall cannot find prior quizzes, or teach workspaces land somewhere unexpected. Actions: check (read-only verification, default and only action — this plugin's entire configuration is native userConfig, so there is nothing an apply could write)."
claude-code-plugins
melodic-software
"Read-only progressive-disclosure audit for agent-facing instruction markdown — grades every target against a three-tier load-cost model (always-loaded / invocation-loaded / on-demand) and classifies seven finding shapes in two lanes: split opportunities (oversize vs tier-calibrated Anthropic-prescribed caps, mixed-concerns, tier-mismatch — procedures, path-local, or sometimes-only content sitting in an always-loaded file) and disclosure-structure defects (blind-pointer lacking a when-to-read clause or read-vs-run intent, orphan-spoke, deep-nesting past one level, missing-toc on long references). Emits Tier 1/2/3 findings with per-shape treatment guidance; read-only, no edits applied. Use when: 'progressive disclosure', 'split this file', 'this file is too long', 'too much context', 'mixed concerns', 'hub and spoke', 'is my CLAUDE.md too big', 'audit context loading', 'what should always be loaded', or before splitting any instruction file — not for prose flavor (/docs-hygiene:compress), in-page noise (/docs-hygiene:audit-noise), whole-doc existence (/docs-hygiene:audit-derivability), or skill frontmatter QA (/skill-quality:check)."
accelint-ts-audit-all
gohypergiant
Comprehensive TypeScript file audit system. Command-only skill (no natural triggers). Accepts file or directory path to systematically audit through accelint-ts-testing, accelint-ts-best-practices, accelint-ts-performance, and accelint-ts-documentation skills. Maintains progress tracking across sessions with interactive change approval. Uses isolated git worktrees to enable parallel audits without conflicts.
accelint-ac-to-playwright
gohypergiant
Convert acceptance criteria to Playwright test specs. Use when user asks to: (1) turn AC into tests, (2) generate tests from acceptance criteria, (3) convert .md bullets or .feature Gherkin files to Playwright specs, (4) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.
skill-creator
quran
Guide for creating effective skills. This skill should be used when users want to create a new
humanizer
DaleSeo
AI가 생성한 한국어 텍스트의 특징적인 패턴을 감지하고 자연스러운 인간의 글쓰기로 변환합니다. 과학적 언어학 연구(KatFishNet 논문, 94.88% AUC 정확도)에 기반합니다. 쉼표 과다, 띄어쓰기 경직성, 품사 다양성, AI 어휘 과용, 대명사 과다, 복수형 과다, 구조적 단조로움 등 24가지 패턴을 분석합니다. ChatGPT/Claude/Gemini가 생성한 한국어 텍스트를 자연스럽게 만들거나 LLM 출력에서 AI 흔적을 제거할 때 사용하세요.
grafema-codebase-analysis
Disentinel
Analyze codebases using a graph database instead of reading source files. Use when understanding code architecture, finding functions or call patterns, tracing data flow, checking dependencies, or answering "where is X used?" questions. Grafema builds a queryable code graph from static analysis — prefer querying the graph over reading files manually.
moonbit-agent-guide
moonbitlang
Guide for writing, refactoring, and testing MoonBit projects. Use when working in MoonBit modules or packages, organizing MoonBit files, using moon tooling (build/check/run/test/doc/ide etc.), or following MoonBit-specific layout, documentation, and testing conventions.
gh-cli
tenequm
GitHub CLI for remote repository analysis, file fetching, codebase comparison, and discovering trending code/repos. Use when analyzing repos without cloning, comparing codebases, or searching for popular GitHub projects.
gog-cli
steveclarke
Interact with Google Workspace services via command line using gog-cli. Use when user wants to work with Gmail (search, send, labels, filters), Calendar (events, scheduling, availability), Drive (upload, download, share), Sheets (read, write, format), Docs/Slides (create, export), Contacts, Tasks, Chat, or Classroom. Triggers on "Google", "Gmail", "Calendar", "Drive", "Sheets", "Docs", "Slides", "Contacts", "Tasks", "Google Chat", "Classroom", or any gog command.
obsidian-vault-context
steveclarke
Work with Steve's Obsidian vault at /Users/steve/Documents/Main using direct file operations. Knows folder structure, daily note format (YYYY-MM-DD.md), and research capture templates. Use when reading/writing Obsidian notes or capturing research. Triggers on "obsidian", "daily note", "vault", "capture research".
steveclarke
Print files on Mac or Linux using the lp command with sensible defaults (double-sided, black & white). Supports PDF, markdown (via md-to-pdf conversion), and common print options like copies, page ranges, color, and printer selection.
post-mortem
walterra
Analyze chat history to identify successes, failures, and improvement opportunities. Generates actionable recommendations for updating project rules, skills, and system prompts. Use when the user asks for a post-mortem, retrospective, session analysis, or wants to improve agent configuration based on past interactions.
superthread
steveclarke
Interact with Superthread project management via CLI. Use when creating/managing cards, viewing boards, searching tasks, or tracking work.
tanstack-router
tenequm
Build type-safe React applications with TanStack Router. Use when implementing file-based or code-based routing, type-safe navigation, search params validation, data loading, code splitting, or route-level error handling. Triggers on "tanstack router", "file-based routing", "type-safe routing", "search params", "route loader", or file patterns like routes/*.tsx, __root.tsx, routeTree.gen.ts.
skill-finder
tenequm
Find and evaluate Claude skills for specific use cases using semantic search, Anthropic best practices assessment, and fitness scoring. Use when the user asks to find skills for a particular task (e.g., "find me a skill for pitch decks"), not for generic "show all skills" requests.