playwright
Playwright browser automation and E2E testing. Use for browser testing, screenshots, debugging, MCP tools, page objects, and visual verification.
Playwright browser automation and E2E testing. Use for browser testing, screenshots, debugging, MCP tools, page objects, and visual verification.
Complete code review workflow for PR/MR with multiple reviewers and automated checks. Triggers: PRW, 審查流程, review workflow, PR review, MR review, pull request, merge request, 程式碼審查流程, full review, 完整審查.
Generate comprehensive test suites including static analysis (vulture dead code), unit tests, integration tests, E2E tests, and coverage reports. Triggers: TG, test, 測試, 寫測試, coverage, 覆蓋率, pytest, unittest, 驗證, check, 檢查, quality, 品質, dead code, 死碼, vulture, static analysis, 靜態分析, lint, type check.
Use when Codex needs to run CI/CD or cross-service automations through the Composio MCP server.
Configure repository with development branch workflow, main branch protection, and PR validation per agent-guide-development-branch-setup.md. Executes setup steps atomically. Use for new repository setup, fixing validation failures, or recovering from configuration drift. Always uses Git MCP server for safe execution.
Enforces strict GitHub workflow hygiene and best practices. Use this skill for ALL git and GitHub operations including commits, branches, pull requests, and repository management. Core rules - NEVER commit directly to main/master, ALWAYS work on feature branches, use GitHub MCP for all GitHub API operations (issues, PRs, reviews), require PRs for all merges. Triggers on any git command, GitHub operation, or when starting new feature work.
Generate exhaustive user-flow and edge-case test scenarios from an app's codebase, produce scenario .md files, execute tests using connected or newly created MCPs, and produce an app.qa.report.md summarizing failures and suggested fixes.
Automatically deploys to Vercel production, uses Vercel MCP to fetch build logs, analyzes errors, fixes them, and retries until successful deployment. Use when deploying to production or fixing deployment issues.
Security review workflow for GitHub repositories using the Security MCP (OWASP ASVS + NIST 800-53) as the primary reference and mapping layer. Use when asked to security review a repo, produce an OWASP/NIST-aligned checklist, map findings to ASVS/NIST controls, generate a prioritized vulnerability report, or create security requirements/acceptance criteria from repo code/config.
Playwright MCP browser testing. Headless E2E, cross-browser, CI/CD automation.
Tool configurations for IDEs, MCP integrations, and development tools. Use when configuring IDE settings, MCP tools, or pytest. Covers conditional tool activation, configuration hierarchy, and synchronization patterns.
Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates
Internal worker for pr-review skill. Claims file partitions, fixes comments, resolves threads. NOT for direct user invocation. Spawned only by pr-review orchestrator.
Help users evaluate whether an MCP (Model Context Protocol) tool is safe and right for them before installing it. Use when a user wants to check, scan, review, or assess a third-party MCP server from GitHub, npm, or any repository URL. Provides plain-language assessments that anyone can understand, with technical details available on request.
Generate production-ready Helm charts for Kubernetes apps. Use when: (1) Deploying applications to Kubernetes, (2) Containerizing apps for Minikube/K8s, (3) Creating reusable deployment packages, (4) Needing parameterized K8s manifests, (5) Scaffolding new chart structures. Includes security contexts, resource limits, RBAC, NetworkPolicies, and multi-environment support (dev/prod). Provides templates for frontend, backend, and MCP server components.
Guides development, updates, and refactoring across the entire MCP server codebase. Use when adding features, updating categories, refactoring code, checking test coverage, or making any code changes. Enforces consistent patterns, 100% test coverage, and principled design decisions. Essential for maintaining code quality and preventing regressions during rapid development.
Complete Test-Driven Development workflow combining Sherpa guidance, Julie code intelligence, and Goldfish progress tracking. Automatically activates for feature implementation with systematic phases, semantic code search, and persistent checkpointing. Use when implementing new features with test-first discipline.
Complete GitHub workflow from commit to PR including conventional commits, branch management, pre-push quality checks, PR creation with gh CLI, and wiki synchronization. Use when creating commits, ...