发现 devops cicd 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
Build and run deterministic evaluation suites for agent workflows (single-turn or agentic). Use when you need reproducible eval runs with manifests, graders, metrics, and JSONL logs for capability or regression...
Fast environment briefing for agents and subagents. Use at session start to learn OS/shell, container/WSL/VM status, git repo + upstream + dirty state, Python venv status/locations, markdown folders to read, an...
Audit tool integrations for deterministic behavior, error contracts, and logging before agents depend on them. Use when adding or updating tools or MCP servers.
comprehensive 12-step project development workflow from initialization through deployment. use when starting a new project, continuing project development, or user mentions project steps, architecture planning,...
6-step feature implementation workflow for building specific features, components, or modules. use when implementing features from todo lists, user requests feature work, or invoked by pydev-workflow step 07. h...
comprehensive project analysis identifying issues, missing documentation, and improvement opportunities. use when reviewing codebase health, onboarding to existing project, or conducting code quality assessment...
Choose architecture, patterns, tech stack, trade-offs in MacroFlow.
Comprehensive forensic analysis skill for enterprise codebases across Azure, Dynamics 365, C#, SAP, Mulesoft, Power Platform, and more. Covers security, performance, architecture, and compliance in multi-langua...
Execute project release workflows by locating and following project-specific RELEASE_GUIDE.md in the repository root or docs/. Use when asked to perform a release, publish a release, cut a tag, run release step...
Run CI-friendly API test suites (REST + GraphQL) from a single manifest, delegating to rest.sh/gql.sh and emitting JSON (+ optional JUnit) results. Use when the user asks to reduce CI boilerplate and provide a...
Find, triage, and fix bugs with or without user input. Autonomously scan codebases, produce an issues list, implement a fix, create a fix branch, commit via semantic-commit, and open a PR with gh.
Level 3 patterns - test-smart, deploy, migrate, logs, status (production systems)
Analyze problems, design solutions, plan task breakdowns. Use for epic planning, architecture design, and task specification. Outputs planning artifacts for GitHub issue creation.
Working in isolated worktree directories for parallel work - work normally, tests isolated, orchestrator handles cleanup
Use when setting up GitHub Actions CI/CD for pull request checks - provides workflow templates for Python, JavaScript, and polyglot projects that run quality gates on every PR
Verify development environment health (Docker, API, auth, database)
Provides systematic code review with focus on quality, security, and best practices. Use when reviewing code, doing PR reviews, or asking for code feedback.
Hierarchical task execution with planning, verification, and replanning. Use for complex multi-step tasks with dependencies. Planner creates manifest, workers execute steps, inspector verifies.
Generate architecture documentation, create codebase maps, document code structure. Create ARCHITECTURE.md, generate mermaid diagrams, label modules and processes, write READMEs describing the codebase. NOT for...
Deploys specified app(s) to Vercel staging environment with build verification, smoke tests, and multi-channel notifications. This skill should be used when the user wants to deploy to staging, test a staging d...
Runs Playwright E2E tests with smart targeting by app and feature, supports multiple environments (local/staging/production), and can generate new E2E test files. This skill should be used when running E2E test...
Creates a streamlined pull request from v2 (staging) to main (production) with change summary, affected apps detection, and deployment checklist. This skill should be used when ready to deploy staging changes t...
Verifies system health across all apps, edge functions, and database connectivity. This skill should be used for quick deployment verification, debugging service issues, daily operations checks, or before/after...
Create or update a quality gate decision for a story or code changes. Runs quality checks, specialist reviews, and produces a persistent YAML gate file with actionable findings. Supports PASS, CONCERNS, FAIL, o...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。