发现 tools 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。
Configure Wheels applications for production deployment with security hardening, performance optimization, and environment-specific settings. Use when preparing for production, configuring servers, or hardening...
Comprehensive end-to-end test creation, and management. You MUST activate this skill when the user mentions "e2e", "end-to-end", "playwright", or any work involving the `e2e/` folder.
Use when user provides workflow syntax with arrows (-> || ~>), says "run workflow", "execute workflow", "run this", mentions step1 -> step2 patterns. Executes orchestration workflows with real-time visualizatio...
Test feature branches on Vercel preview deployments using Chrome automation and Gmail OTP
Strict test-driven development state machine with red-green-refactor cycles. Enforces test-first development, meaningful failures, minimum implementations, and full verification. Activates when user requests: '...
Run this repo’s Units+Checkpoints research pipelines end-to-end (survey/综述/review/调研/教程/系统综述/审稿), with workspaces + checkpoints. **Trigger**: run pipeline, kickoff, 继续执行, 自动跑, 写一篇, survey/...
Execute exactly one runnable unit from `UNITS.csv` (first TODO whose dependencies are DONE), then update unit status and artifacts. **Trigger**: unit executor, run one unit, next unit, step-by-step pipeline, 逐...
Capture wrong assumptions you made about the codebase. TRIGGER when reality differs from expectation (e.g., "assumed Jest but it's Vitest", "assumed AbstractUseCase exists but found AbstractMemberUseCase", "ass...
Enforce git commit best practices using gitmoji + Conventional Commits format. TRIGGER when creating commits. Ensures quality-gate passes, prevents issue auto-closing (no Close/Fix keywords), includes Co-Author...
Automatically capture reusable task patterns as command candidates after completing coding work. This skill identifies multi-step workflows that could benefit other developers across projects and logs them to c...
Version management, release verification, and deployment procedures for software releases. Includes semver guidance, version consistency checks, and platform-specific constraints.
Code review checklist, severity definitions, and document templates. Load when performing code reviews or defining review criteria.
Common software architecture patterns, ADR templates, and anti-pattern detection. Supports architectural review, design decisions, and system documentation.
Create architectural decision records (ADRs), system documentation, API documentation, and operational runbooks. Use when capturing design decisions, documenting system architecture, creating API references, or...
Pipeline design, deployment strategies (blue-green, canary, rolling), and CI/CD platform patterns. Use when designing pipelines, implementing deployments, configuring quality gates, or setting up automated rele...
Auto-detect project tech stacks (React, Vue, Express, Django, etc.). Recognize package managers and configuration patterns. Use when starting work on any project, analyzing dependencies, or providing framework-...
Create and validate implementation plans (PLAN). Use when planning implementation phases, defining tasks, sequencing work, analyzing dependencies, or working on implementation-plan.md files in docs/specs/. Incl...
Navigate, search, and understand project structures. Use when onboarding to a codebase, locating implementations, tracing dependencies, or understanding architecture. Provides patterns for file searching with G...
Initialize and manage specification directories with auto-incrementing IDs. Use when creating new specs, checking spec status, tracking user decisions, or managing the docs/specs/ directory structure. Maintains...
Apply consistent security, performance, and accessibility standards across all recommendations. Use when reviewing code, designing features, or validating implementations. Cross-cutting skill for all agents.
Detect divergence between specifications and implementation during development. Use during implementation phases to identify scope creep, missing features, contradictions, or extra work not in spec. Logs drift...
Coordinate multi-agent code review with specialized perspectives. Use when conducting code reviews, analyzing PRs, evaluating staged changes, or reviewing specific files. Handles security, performance, quality,...
Iterate on a PR until CI passes. Use when you need to fix CI failures, address review feedback, or continuously push fixes until all checks are green. Automates the feedback-fix-push-wait cycle.
Analyze a repository to generate recommended Claude Code settings.json permissions. Use when setting up a new project, auditing existing settings, or determining which read-only bash commands to allow. Detects...
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。