tdd
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
story-splitting
Detects stories that are too big and applies splitting heuristics. Identifies linguistic red flags (and, or, manage, handle, including) and suggests concrete splitting strategies. Use when breaking down requirements or splitting large work.
small-safe-steps
Small Safe Steps (S3): breaks work into 1-3h increments with zero downtime. Use when asking "how do I implement/migrate/refactor", "what steps to do X", "plan safe migration", or handling risky DB/API changes. Applies expand-contract pattern for migrations, refactorings, schema changes.
review-fix-loop
用三个相互隔离的干净 subagent 并行做代码审查、由主 agent 判断审查意见价值、修复有效问题并提交推送，直到同一批三个 reviewer 都没有有价值审查意见。适用于用户要求 review/fix loop、clean review cycle、创建新 subagent 审查当前修改、反复 review 到没有问题、或“三个独立 reviewer 都没有有效建议”这类任务。
tampermonkey-cli
通过 Tampermonkey Editors 管理浏览器里的 Tampermonkey userscript；适用于需要从 Codex 安装、更新、读取、列出或删除本机油猴脚本，或把本地 .user.js 同步到 Tampermonkey 时使用。
ticktick-cli
使用 Python CLI 与 Dida365 Open API 交互以管理滴答清单任务/项目，适用于需要通过脚本或命令行调用滴答清单接口的场景（如项目/任务的查询、创建、更新、完成、删除）。
upstream-pr-staging
在向 GitHub 上游提交 PR 前，先用用户 fork 中的中文预审 PR 审查 AI 辅助产出的代码、提交、PR 文案和 CI 证据，并通过独立 comment 收敛内部记录；适用于 fork 预审、低干扰验证、内部 review/CI、red/green 证据和正式上游 PR 重放。
uv-cli-creator
创建或修改 uv --script 风格的 Python CLI；当需要把重复命令封装成 `./scripts/...` 直接执行的工具，或需要统一这类脚本约定时使用。
confluence-cli
查询、检索与阅读 Confluence 文档/页面。
jira-cli
通过内置 Python CLI 直接调用 Jira Server/Data Center REST API v2，查询、创建、编辑、流转和删除 Issue、Epic、Sub-task、评论、附件、关联、Watcher、Vote 与 Worklog，并查询项目、字段、Board 和 Sprint。适用于需要可控地操作 Jira、保留 Jira wiki markup 并精确管理请求与输出的场景。
grilling
针对用户的计划、决策或想法持续深入追问。适用于用户希望对自己的思路做压力测试，或使用“grill”“拷问”“盘问”等触发词的场景。
gitlab-cli
使用 GitLab CLI（glab）与 GitLab 资源交互；适用于 project、issue、MR、comment、wiki 等查看、更新或创建场景，含自建实例。
dcjanus-preferences
记录 DCjanus 在不同语言中偏好的第三方库与使用场景，供 AI 在选型、引入依赖或替换库时优先参考。适用于 Python/Rust/Go 的库选择、技术方案对比、或需要遵循 DCjanus 个人偏好进行开发的场景。
golang-lo
Go >= 1.18 项目中希望用 samber/lo（Lodash 风格泛型库）简化集合/映射/字符串、错误处理、重试/节流/防抖、通道并发或指针空值场景时使用。
google-sheets-cli
使用 Python CLI 与 Google Sheets API 交互以读取、更新、批量写入、追加或清空 Google Sheets 在线表格；适用于需要通过 OAuth 授权操作 Google Workspace 表格的场景。
fetch-url
获取并提取链接正文（默认 Markdown）；内置 X/Twitter URL 处理，提升受限页面的抓取成功率。
domain-modeling
构建并持续校准项目的领域模型。适用于需要明确领域术语或统一语言、记录架构决策，或其它 skill 需要维护领域模型的场景。
github-cli
使用 GitHub CLI 与 GitHub 资源交互；适用于 repo、issue、PR、comment、release、workflow 等查看、更新或创建场景。创建任何 GitHub Issue 时，统一使用本 skill 的 github_issue.py，保留模板 labels/assignees 并在创建后回读验证。
codex-thread-namer
为当前 Codex thread 设置名称；仅当用户手动调用或明确要求命名、重命名、整理当前 Codex 会话标题时使用，永远不要自动调用。
git-workflow
处理 git 提交、推送、分支命名与提交信息规范；当任务涉及 commit、push、起分支或整理 commit message 时使用。
change-request-writing
编写或更新 GitHub/GitLab Issue、PR、MR 的标题与正文；适用于创建、修改、重写 reviewer-facing 描述、Risks、Breaking Change、避免低价值验证噪声与本地路径泄露等场景。PR/MR 正文默认禁止 Validation；只有 CI/diff 看不到的高信噪比行为证据才允许写。
omarchy
Manage and configure Omarchy Linux systems. Use when user asks about Omarchy, Hyprland, themes, keybindings, system config, or any omarchy-* commands.
reanimated-skia-performance
Write and review high-performance React Native animations and 2D graphics using react-native-reanimated (v4+) and @shopify/react-native-skia (Canvas scenes, runtime effects/shaders). Use for: gesture-driven interactions, spring/timing transitions, layout/mount animations, Reanimated CSS transitions/animations, Skia drawings, animated shader uniforms, path/vector interpolation, dev-mode tuning panels (sliders), and diagnosing animation jank (JS thread stalls, excessive re-renders, per-frame allocations).
polymarket-api
Deep integration guide for Polymarket's CLOB API, Gamma API, and on-chain data. Use when building trading functionality, fetching market data, or implementing order execution.
trading-strategies
Framework for developing, testing, and deploying trading strategies for prediction markets. Use when creating new strategies, implementing signals, or building backtesting logic.
trader-analysis
Analyze Polymarket traders, identify profitable traders to follow, and track their performance. Use when building copy trading features or trader discovery.
agent-manager
Employee agent lifecycle management system. Use when working with agents/ directory employee agents - starting, stopping, monitoring, or assigning tasks to Dev/QA agents running in tmux sessions. Completely independent of CAO, uses only tmux + Python.
oracle
Get a second opinion by bundling a prompt + a curated file set, then asking another powerful LLM for debugging, refactor advice, design checks, or code reviews.
browser-tools
Interactive browser automation via Chrome DevTools Protocol. Use when you need to interact with web pages, test frontends, or when user interaction with a visible browser is required.
git-clean-history
Reimplement the current Git branch on a fresh branch off `main` with a clean, narrative-quality commit history.
git-commit
Commit changes with an emphasis on tidiness and reviewability: small, focused commits, with clear rationale in messages.
homeassistant-ops
Operate a Home Assistant instance via the official REST/WebSocket APIs and backups, with safe plan/apply workflows for bulk, reviewable changes.
web-design
Design and implement distinctive, production-ready web interfaces with strong aesthetic direction. Use when asked to create or restyle web pages, components, or applications (HTML/CSS/JS, React, Vue, etc.).
search
Unified web search with automatic provider selection (Kagi, Brave Search, Claude Code, Codex CLI). Use for searching documentation, facts, or current information.
update-changelog
Update CHANGELOG.md following Keep a Changelog (https://keepachangelog.com/en/1.1.0/)
sentry
Fetch and analyze Sentry issues, events, transactions, and logs. Helps agents debug errors, find root causes, and understand what happened at specific times.
openscad
Create and render OpenSCAD 3D models. Generate preview images from multiple angles, extract customizable parameters, validate syntax, and export STL files for 3D printing platforms like Printables.
brainstorm-synthesis
Use when facing hard architectural decisions, multiple valid approaches exist, need diverse perspectives before committing, or want M-of-N synthesis on complex problems
brainstorming
Use when rough ideas need design before code, requirements are fuzzy, multiple approaches exist, or you need to explore options before implementation
ship
Use when shipping code - complete workflow: merge main, run tests, multi-review with auto-fix, commit, push, create PR. Replaces manual commit-push-pr flows.
research
Use when current web info needed, verifying APIs still work, checking latest versions, or avoiding outdated implementations
playwright-browser
Use when automating browsers, testing pages, taking screenshots, checking UI, verifying login flows, or testing responsive behavior
mcp-debug
Use when testing MCP servers, debugging MCP tool responses, exploring MCP capabilities, or diagnosing why an MCP tool returns unexpected data
limitless
Use when recalling conversations from Limitless Pendant, finding what was discussed in meetings, searching lifelogs, or answering 'what did I say about' questions
learn
Use when managing project learnings - view, add, search, prune, or export operational knowledge that persists across sessions
kungfu
Use when finding new AI agent skills, discovering capabilities, installing skills from GitHub, searching skill marketplaces, or expanding what Claude can do - like Neo downloading martial arts in The Matrix
youtube-transcript-analyzer
Use when analyzing YouTube videos, extracting insights from tutorials, researching video content, or learning from talks and presentations
fireflies
Use when finding meeting transcripts, searching Fireflies recordings, getting action items from calls, or answering 'what was discussed in the meeting' questions
writing-for-llms
Use when writing prompts, agent instructions, SKILL.md, commands, system prompts, Task tool prompts, prompt engineering, or LLM-to-LLM content
systematic-debugging
Use when debugging bugs, test failures, unexpected behavior, or needing to find root cause before fixing
Page 895 of 1693 · 84646 results
