Найдите подходящую возможность для вашего агента.
Навык запуска и сопровождения workflow bundle project-analyse (ADR-015) в системе AI-KOD: установка bundle из git/локального пути, запуск (project-analyse)/research-structure и (project-analyse)/research-analyse, требования окружения (AI_KOD_ROOT, AI_KOD_PROJECT_ROOT), контрольные точки стадий, артефакты и расследование отклонений.
Expert Deployment Engineer specializing in CI/CD automation, containerization, and release management across diverse platforms. Proficient in Jenkins, GitHub Actions, GitLab CI, Azure DevOps, and modern deployment strategies including blue-green deployments and canary releases.
Spawn 5 parallel agents applying quality principles across planning, building, and validating code. Use when designing features, making decisions, or checking work. Triggers on "launch a swarm" or when ensuring solid, maintainable, secure software.
Run comprehensive audit on completed work. Use after implementation is done, or when user says 'audit this', 'review the work', 'check for issues'. Spawns specialized auditors and fixes found issues.
ALWAYS USE when working with Helm charts, Kubernetes deployments, kubectl commands, pod debugging, or container logs. Provides context-efficient strategies for chart development, K8s troubleshooting, and log analysis. MUST be loaded before any Helm or K8s work.
Safe Railway deployment with pre-flight guards and rollback procedures
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 assertions always
PR 作成後に .github/workflows/ci.yml が失敗したときの対応手順。ローカルで pytest 全ケースを実行し、エラー有無で分岐。エラーがあれば修正して commit-push スキルでコミット・プッシュ、無ければ GitHub Actions のログを確認して原因を特定する。
Review code changes for bugs, quality, and project compliance. Works on PRs or local changes. Use when asked to review a PR, review changes, check code quality, or audit for bugs.
User-specific git workflow preferences and edge case handling. Documents commit message format requirements and pre-commit hook retry logic specific to this user. Use when creating commits or handling pre-commit hook failures.
Expert guidance for Docker Compose including multi-container applications, service definitions, networks, volumes, environment variables, health checks, and orchestration. Use this when working with Docker Compose files and container orchestration.
Expert Docker DevOps engineer for infrastructure optimization, networking, storage, and deployment. Specializes in creating highly optimized Dockerfiles, managing complex networks and volumes, and implementing professional deployment strategies. Use this skill when the user asks for Dockerfile optimization, multi-container architecture, networking deep dives, or deployment automation.
Brutal Vibe Audit for engineering quality. Auto-activates on: "code review", "technical audit", "engineering quality", "is this production ready", "vibe check", "slop check", "AI-generated code", "technical due diligence", "can we ship this", "quality assessment"
Comprehensive guide to regression benchmarks for AI systems including test suite creation, CI/CD integration, and continuous benchmarking strategies
Manage QA test case workflows, status transitions, and verification checklists. Use when working with QA status states (Reviewing, DevError, ProdError, DevDone, ProdDone, Hold, Rejected, Duplicate), progress tracking (Waiting, Checking, Working, DevDeployed, ProdDeployed), activity logging, or test case management.
Kyverno resource governance policies enforcing CPU/memory limits, HPA requirements, and storage constraints for Kubernetes workloads.
Debug guide for failing GitHub Actions workflows. Use when CI fails, tests fail on Actions, or logs show exit code != 0.
Multi-agent code review orchestration following 2024-2025 best practices. Use when: - Reviewing code changes before commit or merge - PR review with comprehensive analysis needed - Security audit of code changes - Architectural review of significant changes - AI-generated code needs validation - Team code quality enforcement Do NOT use for: - Simple typo fixes (direct review is faster) - Documentation-only changes - Single-line changes without logic
