Discover DevOps skills, compare source repositories and read the instructions for each workflow.
Proactively suggests tests when code changes are detected. Activates when functions are created, logic is modified, security-sensitive code is added, or bug fixes are implemented. Provides non-intrusive test re...
Document user-facing features in a codebase. Use when asked to document features, explain what software does, or generate feature docs. Identifies features (not technical layers), then produces numbered markdow...
List and resolve GitHub PR review comments. Use when working with PR feedback, addressing review comments, or marking threads resolved.
Generates clear commit messages from jj diffs. Use when writing commit messages or reviewing staged changes.
Automatically submit pull requests with full autonomous workflow. Use when the user mentions creating a PR, submitting a PR, merging changes, opening a pull request, or wants to get their changes reviewed. Also...
Organizes a flat backend directory structure into a clean, modular architecture with proper Python packages and updated import paths. Transforms a flat backend structure into a modular, organized architecture f...
Systematic approach to diagnose and resolve backend service issues including dependency conflicts, database schema mismatches, import errors, and middleware configuration problems in FastAPI applications.
分析代码质量并提供改进建议
根据文本描述生成图像（返回生成参数和预览URL）
执行网页搜索并返回结构化结果摘要
分析结构化数据并生成统计报告和可视化建议
将长文本压缩为简洁摘要，支持多种语言
Self-feedback review loop to verify implementation matches specification. Use with --mode quick/standard/thorough to control review depth. Default is thorough (3 consecutive passes). (user)
Analyze test coverage and add new test cases to improve coverage without changing implementation
Translate specification files to Japanese while preserving technical accuracy and formatting
Expert guidance for creating and maintaining GitHub Actions workflows and reusable workflows with security best practices
Review specifications for completeness, clarity, testability, and quality. Use with --mode quick/standard/thorough to control review depth. Default is thorough (3 consecutive passes). (user)
Analyze specification files for contradictions, inconsistencies, and ambiguities
Analyze and fix CI/CD pipeline failures including build errors, test failures, and linting issues
Fix lint and static analysis warnings one at a time with proper prioritization
Generate Japanese documentation from spec files. Use AUTOMATICALLY after writing or editing any file matching specs/**/*.md (excluding specs/**/docs/*). Also use when user says "generate spec docs", "spec docs"...
Deep security analysis for Solidity smart contracts with DeFi context
Comprehensive code review for pull requests with quality, security, and best practices analysis
Generate a specification file from user input/requirements. Use when user says "generate spec", "create spec", "write spec", "spec from requirements", or provides feature requirements and asks to create a spec....
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.