Найдите подходящую возможность для вашего агента.
End-to-end testing with Playwright for web applications. Use when writing E2E tests, browser automation, visual regression testing, or debugging test failures. Triggers on Playwright, E2E, browser testing, or test automation questions.
Test-Driven Development skill. Generates unit tests before implementation. Adapts to project type (Chrome extension, React, Express, Python, etc.). Reads/updates pattern library.
Verify that the Visions Skills architecture is functioning correctly.
Multi-perspective code review using Claude, Gemini, and Codex as specialized agents. 5-dimensional analysis (security, performance, maintainability, correctness, style) with LLM-as-judge consensus, quality scoring, and CI/CD integration. Use when reviewing PRs, auditing code quality, preparing production releases, or establishing code review workflows.
Fix non-determinism errors in Output SDK workflows. Use when seeing replay failures, inconsistent results between runs, "non-deterministic" error messages, or workflows behaving differently on retry.
Standards for writing clear, concise git commit messages. Use when creating commits, reviewing commit history, or establishing git workflow conventions.
Troubleshoot and fix failing GitHub Actions pipeline steps. Use when user reports a failing pipeline with error output.
Fix try-catch anti-pattern in Output SDK workflows. Use when retries aren't working, errors are being swallowed, seeing unexpected FatalError wrapping, or when step failures don't trigger retry policies.
Workflow patterns from go-agents-orchestration library. Use when implementing workflows, state management, checkpoints, or parallel processing. Triggers: StateGraph, workflows.Register, WorkflowFactory, state.State, Observer, CheckpointStore, ProcessParallel, MultiObserver, StreamingObserver, graph.Execute, graph.Resume, OnEvent, workflow_runs, stages, decisions. File patterns: internal/workflows/*.go, workflows/**/*.go
Enforce homelab-proxmox workflow patterns including single source of truth documentation, prompt logging, git commits, environment variables, and phase tracking. Use this skill when completing tasks, updating docs/ or CLAUDE.md files, or when workflow compliance validation is needed. Provides AI-powered fixes for violations.
Use automatically during development workflows when making claims about tests, builds, verification, or code quality requiring concrete evidence to ensure trust through transparency.
Run Codex plan validation or implementation review as a quality gate for non-trivial tasks. Use after planning or implementation.
Expert DevOps pour CI/CD, containers, Kubernetes et Infrastructure as Code. Utilise ce skill quand: (1) mise en place de pipelines CI/CD, (2) containerisation avec Docker/K8s, (3) infrastructure as code (Terraform, Pulumi), (4) monitoring et alerting, (5) optimisation des déploiements, (6) sécurisation de l'infrastructure.
Testing conventions, test runner configurations, coverage requirements, and failure interpretation for the Klassenzeit monorepo.
GitHub Actions expert for CI/CD pipelines, workflows, build failures, test failures, lint errors, format checks, gh run, gh pr checks, ESLint, Prettier, TypeScript errors, quality gates, automated fixes, pipeline debugging, workflow monitoring
Document how to group Laravel seeders between local and shared environments, ensure seeders guard against duplication, and keep reruns safe.
Enforces conventional commit format for PR titles and commit messages, automating semantic versioning and GitHub releases. Use this skill when writing commit messages, creating PR titles, understanding version bumps, configuring release automation, or troubleshooting commitlint failures.
코드 리뷰, 코드리뷰, 리뷰, PR 리뷰, 검토 - Expert at reviewing code for quality, adherence to architectural principles, security, and performance. Use this to ensure code meets project standards before merging or after implementation.
Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches core:code-reviewer subagent to review implementation against plan or requirements before proceeding
Agent-first workflow and design rails for building X07 programs with the released toolchain (no repo-only dependencies). Canonical execution is via `x07 run`.
