dispatching-parallel-agents
Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently
Discover Content & media skills, compare source repositories and read the instructions for each workflow.
Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently
Generate clear, concise commit messages from git diffs. Use when writing commit messages, reviewing staged changes, or formatting git history.
Test-Driven Development guidance. Use during feature-dev Phase 5 (Implementation) or any code implementation. Ensures tests are written BEFORE implementation code, following Red-Green-Refactor cycle.
Manage tasks in Notion. List, create, update tasks. Use for any Notion task-related operations.
Create stacked pull requests for GitHub repositories. Use when breaking large features into sequential, dependent PRs with conventional commit titles. Triggers on requests to create stacked PRs, split work into...
Applies current Go testing best practices. Use when writing or modifying Go test files or advising on Go testing strategies.
Publish the easier package to PyPI. Validates versions, checks git state, updates files, and guides through the complete release workflow. Use when ready to release a new version.
Guide for writing React code without unnecessary useEffect. Use when writing or editing React components. Avoid anti-patterns like derived state, chained state updates, and event handlers in effects.
This skill should be used when the user asks about "AIR", "algebraic intermediate representation", "ZK constraints", "trace design", "constraint soundness", "polynomial commitments", "FRI", "STARK", "lookup arg...
This skill should be used when agents need to extract data from websites, APIs, or web pages. Use when scraping content, fetching structured data, or processing web responses. Key principle: always use programm...
This skill should be used when the user asks about "rust workspace", "rust best practices", "cargo workspace setup", "rust code organization", "rust dependency management", "rust testing strategy", "rust projec...
This skill should be used when the user asks to "coordinate document writing", "manage doc writers", "create a design document with multiple writers", "orchestrate documentation", "delegate doc sections", "cos...
This skill should be used when agents need to log into websites, retrieve passwords, or access credentials. CRITICAL - always use find_credential with the website URL, never guess item names.
This skill should be used when the user asks about "coordinate coding agents", "orchestrate agent team", "manage multiple agents", "vibekanban workflow", "task delegation to agents", "agent swarm coordination",...
Implements Spec-Driven Development (SDD) methodology where specifications drive code generation. Use when users build new features, plan implementations, create technical specs, or want structured development w...
Roast a repository to identify issues, then translate to constructive feedback. Use when user wants code review, wants to find problems, asks to "roast" their code, or wants honest feedback about their codebase...
强制规范:AI 改动模块代码时需同步创建/更新模块文档与索引,保持文档与代码一致。
当用户提到 GitHub URL、GitHub 仓库链接、开源库、或询问特定框架/库的使用方法时,自动使用 context7 MCP 获取最新的文档和代码示例。处理 github.com 链接、npm 包、开源项目参考时触发。
当用户提供飞书 MCP URL 并请求配置时触发。自动同时配置到 Claude Code 和 Cursor,简化团队成员的环境设置流程。
当用户用自然语言请求提交代码时触发(如「帮我提交」「commit 一下」「提交代码」)。自动应用 Git 提交规范,从分支名提取任务 ID,生成符合规范的提交信息。
测试中, 用户明确指定执行 implementing-from-task 时候才执行, 其余情况一律不执行
测试中, 用户明确指定执行 merging-parallel-work 时候才执行, 其余情况一律不执行
排查问题、修复 BUG、定位代码、查找模块、功能开发前,必须先读取此 SKILL 并使用模块索引定位目标,不可跳过
AI 驱动的代码审查能力,当用户提到代码审查、code review、审查代码、查看代码质量等关键词时自动触发。使用 9 个并行 Agent 进行全维度分析(Bug/质量/安全/性能)。
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.