CI failure diagnosis, workflow linting, and runner health management for self-hosted GitHub Actions runners
npx claudepluginhub kinginyellows/yellow-plugins --plugin yellow-ciDiagnose CI failure and suggest fixes. Use when user wants to analyze a failed GitHub Actions run, understand why CI broke, or get actionable fix suggestions.
Lint GitHub Actions workflows for self-hosted runner issues. Use when user wants to check workflows before pushing, asks "lint CI", "check workflows", or wants to find common pitfalls in their GitHub Actions configuration.
Diagnose a CI failure and create a Linear bug issue. Use when CI has failed and you want to track the fix in Linear. Requires yellow-linear to be installed.
Clean Docker images/containers, old logs, and caches on self-hosted runner. Destructive operation with dry-run preview and confirmation. Use when runner disk is full, Docker space needs freeing, or old CI logs need pruning.
Check self-hosted runner health via SSH. Use when user asks "runner status", "is runner healthy", "check runner", or wants to verify infrastructure before diagnosing CI failures.
Configure runner pool targets, routing rules, and semantic metadata for CI workflow optimization. Supports interactive wizard, YAML import, and GitHub API discovery. Use when setting up runner-aware CI optimization or after changing your runner fleet.
Inventory available self-hosted runners and optimize workflow jobs to use the best runner based on labels, OS, and live load. Use when runner assignments look suboptimal, jobs are queuing on the wrong runner, or after registering new self-hosted runners.
Check CI prerequisites and configure self-hosted runner SSH config. Use when first installing the plugin, after adding runners, or when ci commands fail with auth or connectivity errors.
Show recent CI workflow run status. Use when user asks "CI status", "recent builds", "what's running", or needs to find run IDs for diagnosis.
CI failure diagnosis specialist that analyzes GitHub Actions logs against a failure pattern library (F01-F12). Use when CI builds fail and you need to identify root cause, when user asks "why did CI fail?", "diagnose the build", "what broke?", or when analyzing exit codes from failed runs.
GitHub Actions runner assignment specialist. Analyzes workflow jobs against available self-hosted runner inventory to recommend optimal runs-on values. Use when spawned by ci:setup-self-hosted with a fenced runner inventory.
GitHub Actions workflow optimization specialist. Use when analyzing CI performance, suggesting caching strategies, or improving workflow efficiency. Triggers on "optimize workflows", "why is CI slow?", "add caching", or when lint finds optimization opportunities (W02, W04, W08).
Deep runner diagnostics specialist for self-hosted GitHub Actions runners. Use when runner infrastructure issues are suspected (not application failures). Triggers on "check runner health", "runner offline", "investigate runner", or when failure-analyst identifies runner-side patterns (F02 disk full, F04 Docker, F09 runner agent).
Shared conventions for CI analysis — validation rules, failure patterns, error catalog, and security patterns. Use when agents or commands need CI-specific validation or pattern matching reference.
CI debugging workflow guide for self-hosted runners. Use when learning CI debugging workflows, understanding failure patterns (F01-F12), or troubleshooting GitHub Actions on self-hosted runners.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
Semantic search for Claude Code conversations. Remember past discussions, decisions, and patterns.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research
Context-Driven Development plugin that transforms Claude Code into a project management tool with structured workflow: Context → Spec & Plan → Implement