deploy
Deployment automation with pre-flight checks, rollback plans, and post-deployment verification
Discover tools cicd skills, compare source repositories and read the instructions for each workflow.
Deployment automation with pre-flight checks, rollback plans, and post-deployment verification
Browser automation for UI testing, screenshots, and workflow verification. Routes to optimal tool based on context.
Specialized skill for writing and maintaining tests including unit tests, integration tests, E2E tests with Playwright, and accessibility tests. Use when writing tests for new features, debugging failed tests,...
Guide la création de commits bien formatés, push vers origin et création de Pull Requests documentées. Utilise ce skill lorsque l'utilisateur demande de commiter des changements, créer une PR, ou finaliser un t...
Run the full multi-agent workflow with approvals, validation, and verification phases.
Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive full-stack implementation plans with exact file paths, complete code examp...
Full autonomous feature development with single approval gate. Orchestrates: Research -> Plan -> APPROVAL -> Work (Atlas) -> Review -> Compound.
Run after wave implementation complete. Executes test + review gate sequence. Usage: /wave-gate
Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skil...
Define and run multi-container Docker applications with Compose. Covers service orchestration, networking, volumes, development environments, and production configurations. Use when setting up local development...
Reviews code for ClaudeMix project, verifying adherence to 3-layer architecture, TDD principles, and coding standards. Generates detailed review reports with scoring and improvement recommendations.
This skill should be used when the user asks to "deploy to Kubernetes", "configure Docker", "create Helm chart", "Kubernetes deployment", "container orchestration", "Docker Compose", "kubectl", "pod configurati...
This skill should be used when auditing the complete agent ecosystem - CLIs, skills, rules, prompts, roles, and meta docs. Triggers include "audit my ecosystem", "verify all tools", "check CLI health", "ecosyst...
Comprehensive testing skill covering unit, integration, and E2E testing with pytest, Jest, Cypress, and Playwright. Use for writing tests, improving coverage, debugging test failures, and setting up testing inf...
Perform language-agnostic code reviews focusing on correctness, regressions, security, and tests. Use when the user asks for a review.
Execute the next phase from the project plan with full TDD workflow, 100% coverage, PR review, and quality gates. WHEN: Use to continue development on a project with phase-based plans. Invoke with "/plan:execut...
Execute all plans in a phase with wave-based parallelization
Semantic Versioning 기반 릴리스 관리. version.txt, CHANGELOG.md 자동 업데이트.
多 Agent 並行審查框架 - 多視角程式碼審查,問題分類與優先排序
Setup and troubleshoot GitHub Actions workflows using anthropics/claude-code-action for automated PR reviews. Use when creating CI/CD workflows that leverage Claude for code review, research validation, or auto...
Debug and fix GitHub Actions CI/CD failures
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before as...
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
Use this skill when the user asks about "Cloud Tasks", "background jobs", "delayed processing", "rate limit handling", "async queue", "enqueue task", or any task queue work. Provides Cloud Tasks patterns for ba...
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.