content-planner
|
commit
Create conventional commits. Use when: committing staged changes. Triggers on: '/commit', 'conventional commit'.
comment-cleanup
Clean up code comments. Use when: improving comment quality, removing redundant comments. Triggers on: 'clean up comments', 'comment cleanup'.
code-quality
Code quality standards. Defines complexity management, modular design, code smell detection. Applied automatically when writing or reviewing code.
agent-browser
Browser automation for web testing, screenshots, data extraction. Use when: navigating websites, filling forms, testing web apps. Triggers on: 'open browser', 'screenshot', 'click element'.
opencode-delegate
Delegate a coding task to OpenCode via ACP. Claude Code constructs the prompt, dispatches via acpx, then reviews the result (spec compliance + code quality). Use when: offloading implementation to OpenCode, using OpenCode as implementer backend. Triggers on: '/opencode-delegate', 'delegate to opencode', 'let opencode handle this'.
nix-darwin
nix-darwin dotfiles configuration for macOS with Nix flakes and home-manager. Use when: adding/modifying programs, writing nix modules, editing host configs (workstation/homelab), debugging darwin-rebuild errors, managing homebrew packages via nix, or improving nix architecture.
ios-app-design
iOS app design guidelines based on Apple HIG and iOS 26 Liquid Glass. Use when: (1) Designing iOS app interfaces, (2) Reviewing iOS UI code, (3) Building SwiftUI/UIKit views, (4) Adopting Liquid Glass design, (5) Creating app icons. Triggers on: iOS design, SwiftUI layout, tab bar, navigation bar, Liquid Glass, SF Symbols, Dynamic Type, safe area, app icon, HIG.
investigate
Systematic root-cause debugging. Use when: diagnosing bugs, investigating failures, debugging flaky tests, tracing unexpected behavior. Triggers on: '/investigate', 'debug this', 'why is this failing', 'find the root cause', 'flaky test'.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
english-mode
Toggle English-only mode. Forces English input and provides grammar feedback. Use when: '/english', 'english mode', 'toggle english'.
diffx-review
Run a diffx code review session. Use 'start' to launch the browser UI for inline comments, then 'finish' to apply them. Use when the user invokes /diffx-review.
peer-review
Independent second-opinion code review using Codex CLI. Use when: wanting an external AI reviewer's perspective, cross-validating before push, getting a 'second pair of eyes'. Triggers on: '/peer-review', 'codex review', 'second opinion', 'peer review my changes'.
rust-design-patterns
Rust idioms and design patterns for writing idiomatic code. Use when: (1) Writing new Rust code, (2) Reviewing Rust code, (3) Solving borrow checker issues, (4) Designing Rust APIs. Triggers on: Rust ownership problems, lifetime errors, API design questions, 'how to do X idiomatically in Rust'.
skill-creator
Guide for creating Claude skills. Use when: creating or updating skills. Triggers on: 'create skill', 'new skill', 'skill template'.
slow-is-fast
Research → Plan → Code workflow. Enforces evidence-based reasoning, codebase research, and structured planning before code modifications. Applied automatically for moderate+ tasks.
react-best-practices
React best practices from react.dev and Vercel. Use when: (1) Reviewing React code, (2) Debugging performance issues, (3) Optimizing bundle size, (4) Writing effects or state logic. Triggers on: React performance, re-render, bundle size, waterfalls, code splitting, memo, useCallback, useMemo, useEffect, SSR flicker, initial load slow, React Compiler, state structure, immutable update, setState array object.
no-useeffect
>
review
Self-review of code changes (branch diff, staged, or uncommitted). Use when: reviewing code before pushing, checking diff quality, self-reviewing a PR, creating a PR (always use --peer), reviewing uncommitted work. Triggers on: '/review', 'review my changes', 'review this branch', 'self-review', 'pre-push review', 'review uncommitted', 'review staged', 'create PR', 'open PR', 'submit PR'.
zero-skills
|
data-analysis
>-
commute
>-
frontend-design
>-
data-base
Data acquisition for web scraping and data collection. Use when user needs "爬取数据/抓取网页/scrape data". Outputs structured JSON/CSV for analysis.
data-files
File router that routes uploaded files to appropriate analysis skills. CSV/Excel/JSON → data-analysis, Images → data-viz, PDF/HTML → data-base.
data-viz
Data visualization for charts and graphs. Use when user needs "画图/图表/可视化". Creates static PNG or interactive HTML charts from data.
Email operations via IMAP/SMTP. Trigger for inbox checking, reading, drafting, or sending emails. Requires `.config/email.json` setup.
featbit
>-
flight
Flight status lookup workflow. Use for flight status, delays, cancellations, airport departures/arrivals, or “today/real-time” aviation updates. Prefer airline/airport official sources; always include source link + local update time; NEVER fabricate.
food
>-
fx
Exchange rates / FX lookup workflow. Use for currency exchange rate questions (USD/CNY, EUR/CNY, etc.), “today/latest/real-time” rates, conversion requests, or when you need to cite FX numbers. Default to market mid rate unless user asks for official/bank rates. Must include source link + local update time; NEVER fabricate.
hotel
>-
itinerary
>-
knowledge
External knowledge capture and retrieval. Trigger when user wants to save notes, bookmarks, code snippets, or reference material for later access.
memory
Persistent memory for cross-session personalization. Trigger when user shares identity, preferences, relationships, or facts worth remembering.
news
News briefing + verification workflow. Use when the user asks for news, headlines, daily briefing, “today's news”, “latest updates”, breaking news, or requests specific current numbers/events that require reliable sources and timestamps. Requires source links + local published time; NEVER fabricate.
rail
High-speed rail / train lookup workflow (China-focused). Use for timetables, ticket availability, delays, cancellations, or “today/latest” rail updates. Prefer official sources; always include source link + local update time; NEVER fabricate.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
verify
>-
weather
Weather/current-conditions verification workflow. Use when user asks for weather, temperature, forecast, rain/snow/wind, typhoon alerts, air quality, or other time-sensitive local conditions. Requires location + source links + local update/publish time; NEVER fabricate.
ruanyifeng-weekly-skill
搜索阮一峰科技爱好者周刊 GitHub issues 中的工具和资源。当用户想找工具、开源项目、网站或资源时使用，尤其是提到「阮一峰」「周刊」「ruanyifeng」或在中文语境下询问工具推荐时触发。
brainstorming-skill
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or when users request help with ideation, marketing, and strategic planning. Explores user intent, requirements, and design before implementation using 30+ research-validated prompt patterns.
agent-orchestration
Scientific delegation framework for orchestrators coordinating sub-agents. Provides WHERE-WHAT-WHY context patterns while preserving agent autonomy. Use when delegating tasks, structuring sub-agent prompts, planning multi-agent workflows, or coordinating specialist agents.
verification-gate
Enforce mandatory pre-action verification checkpoints to prevent pattern-matching from overriding explicit reasoning. Use this skill when about to execute implementation actions (Bash, Write, Edit) to verify hypothesis-action alignment. Blocks execution when hypothesis unverified or action targets different system than hypothesis identified. Critical for preventing cognitive dissonance where correct diagnosis leads to wrong implementation.
holistic-linting
Comprehensive linting and formatting verification workflows. Provides automatic format-lint-resolve pipelines for orchestrators and sub-agents. Use when running linters, fixing ruff/mypy/bandit errors, ensuring code quality before completion, or resolving linting issues systematically.
async-python-patterns
Use when writing asyncio Python code — async/await coroutines, concurrent I/O with asyncio.gather, task creation and cancellation, semaphore rate limiting, producer-consumer queues, async context managers, async generators, WebSocket servers, aiohttp web scraping, async database operations, run_in_executor for blocking calls, or testing async code with pytest-asyncio. Covers FastAPI and aiohttp patterns, synchronization primitives, timeout handling, and common pitfalls like event loop blocking and missing await.
litellm
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.
toml-python
Handles TOML configuration file operations in Python using tomlkit for comment-preserving read-modify-write cycles. Use when reading or writing pyproject.toml or any .toml config file, selecting between tomlkit and tomllib, modifying TOML while preserving comments and whitespace, implementing atomic config file updates, integrating TOML with Python dataclasses, handling TOML parse errors, or applying XDG base directory patterns for config file locations.
xdg-base-directory
When an application needs to store config, data, cache, or state files. When designing where user-specific files should live. When code writes to ~/.appname or hardcoded home paths. When implementing cross-platform file storage with platformdirs.
pre-commit
Configures and implements git hooks using pre-commit or prek (Rust-based drop-in replacement) for automated code quality checks, formatting, linting, and commit message processing. Use when setting up .pre-commit-config.yaml, implementing prepare-commit-msg or commit-msg stage hooks, designing .pre-commit-hooks.yaml hook definitions for distribution, troubleshooting hook installation or execution, or managing hook stages across multi-language projects.
Page 737 of 1713 · 85620 results
