Coding standards, frameworks, refactoring, and code review (16.6K skills)
Execute a development phase by grouping plans into waves, sets of tasks that can run together based on dependencies. Collect results, verify completion, and update progress, with options to run a selected wave or work sequentially with checkpoints.
Configure GSD through one command, covering model choice, research, plan checks, verification, and branching. Additional modes handle detailed workflow settings, external service integrations, and model profiles, which are named groups of model settings.
Build and maintain TypeScript MCP servers and MCP Apps with mcp-use, giving AI assistants tools and interactive views. Guides implementation, authentication, debugging, migration, review, and verification against the package version installed in the project.
Turn an OpenAPI or Swagger specification into an MCP server, a bridge that lets AI assistants call an API. Covers tool generation, authentication, local testing, and deployment to mcp-use cloud.
Build and maintain TypeScript MCP servers that connect AI to tools, plus interactive MCP Apps, using mcp-use. The skill guides implementation, authentication, migration, and verification based on the package version and types installed in the project.
Build and maintain TypeScript MCP servers that connect AI to tools, plus interactive MCP Apps, using mcp-use. The skill guides implementation, authentication, migration, and verification based on the package version and types installed in the project.
Learn how to organize an AI agent skill using a sample SKILL.md file. It covers basic metadata, procedural instructions, supporting folders, and relative paths, and serves as an example for testing the OpenSkills loader.
Find where code lives, understand how it works, and trace connections between functions using a repository index. Results include file locations and line numbers to help plan edits and assess which other code a change could affect.
Compare the installed Claude Code version with release notes and recent bug reports to decide whether to stay, update, or use a specific version. Recommendations account for reported problems, relevant fixes, and how Claude Code was installed.
Review recent conversation history against global and project CLAUDE.md files, which hold agent instructions. Identify rules that were missed, useful additions, and outdated guidance, then organize findings into shared and project-specific improvements.
Search across public and private GitHub repositories using local copies and ripgrep, a text search tool. Find which repository or file contains an implementation, phrase, or setting, with results drawn from the default branch.
Edit and validate Bazel build settings using conventions specific to CodeQL development. Follow established helpers for packaging and operating system differences, add dependencies with checksums, and check changed targets while respecting the standalone build setup.
Review medium to large code changes using checks selected for the actual patch. Analyze the change and surrounding code, assign focused reviews by function, file, or feature, and combine findings with locations, confidence levels, and supporting evidence.
Run a quick first review of code changes with six specialist agents working in parallel. They check logic, input and output, shared state, resources, missing behavior, and API completeness, then combine duplicate findings into a report ranked by confidence.
Explain code structure and behavior with text diagrams, including before-and-after views of changes. Trace data flow and state changes, clarify design choices, and examine assumptions, possible failures, and interactions between tasks running at the same time.
Review changes of 1,000 lines or more by dividing work across files, focused areas, and commits. Combine several review methods, check consistency across subsystems, verify bug fixes, and report validated findings alongside a checklist showing review coverage.
Analyze Git history to find frequently and recently changed files and lines, then rank review targets. Use the results to focus pull request reviews, bug investigations, or security audits on specific code regions and risks.
Review selected files for bugs by reading full source code, callers, and related implementations. Apply detailed checklists and investigate suspected issues, then report evidence, confidence levels, and suggested fixes.
Analyze bug-fix commits in a Git repository to uncover recurring failure patterns. Produce individual bug analyses and a reusable pattern guide that removes project-specific details, helping inform future code reviews.
Build Node.js, Express, and TypeScript APIs with consistent structure. Separate request handling, business logic, and database access, while following guidance for input validation, error tracking, configuration, and tests when adding features or refactoring existing services.
Build React and TypeScript pages with guidance for data fetching, loading states, styling, and navigation. Organize code by feature and apply lazy loading, which loads components when needed, using patterns for MUI v7 and TanStack Router/Query.
Create and maintain Claude Code skills with clear file structure and activation rules. Get guidance on hooks, which run at specific workflow events, plus troubleshooting, edit restrictions, and splitting detailed instructions into reference files.
Find where code lives, understand how it works, and trace connections between functions using a repository index. Results include file locations and line numbers to help plan edits and assess which other code a change could affect.
Prepare English pull requests for Apache SeaTunnel from a change summary, branch history, and file differences. It builds titles and bodies that follow project conventions, records actual testing, and can submit the pull request when requested.