Loading...
Loading...
Found 10,134 Skills
Create a release checklist and GitHub issue for an R package. Use when the user asks to "create a release checklist" or "start a release" for an R package.
Fetch a Notion page by title, export to Markdown, convert Markdown to HTML with a user-provided CSS file, and create a Weixin draft via node-wxcli. Use when asked to publish Notion content into Weixin draftbox, or when moving Notion pages into Weixin draft as HTML.
Generate a pull request description from branch changes. Use when creating a PR or preparing PR documentation.
Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
Manage your AI team. /crew = roster, /crew add [name] "[domain]" = new member, /crew [name] [task] = assign task.
Document lessons, update rules/templates/docs. Use to capture learnings after review.
Use Copilot Spaces to provide project-specific context to conversations. Use this skill when users mention a "Copilot space", want to load context from a shared knowledge base, discover available spaces, or ask questions grounded in curated project documentation, code, and instructions.
通用发布工作流。自动检测版本文件和变更日志。支持 Node.js、Python、Rust、Claude 插件和通用项目。当用户说"发布"、"release"、"新版本"、"bump version"、"push"、"推送"时使用。
Summarize current work, commit, push, and create or update a PR. Automatically write conversation context into the PR description to ensure reviewers can quickly understand the background.
Archive completed plans from plans/active/ to plans/completed/, supplement verification results and completion time. Suitable for calling after implementation is finished.
Execute update iterations of existing features (Single Agent Mode). Trigger condition: Requirements or design of completed features change (plan.md + summary.md exist in the directory). Responsible for the complete process from creating update-xxx.md to implementation and review. If the update scale is large and requires multi-role collaboration, create a new Spec and follow the spec-start process.
Use before claiming work is done, fixed, or passing — requires running verification commands and confirming output before any success claim. Prevents false completion claims, unverified assertions, and "should work" statements.