claude-code-reference
Reference guide for Claude Code extensions. CONSULT BEFORE implementing skills, creating hooks, slash commands, or MCP servers. Use when building Claude Code extensions, understanding extension differences, or troubleshooting extension issues. Covers skills vs commands vs hooks vs MCP disambiguation.
hf-spaces-expert
This skill should be used when creating or configuring Hugging Face Spaces, including ZeroGPU hardware, secrets/env variables, persistent storage, repo-based deploys, and build/memory troubleshooting.
skill-authoring
Guide for authoring effective skills that extend Claude's capabilities. Use when creating, updating, or improving skills, learning skill structure, progressive disclosure, or troubleshooting skill issues.
gh-cli-setup
Use when gh CLI is not installed, not configured, or authentication fails - provides installation steps, authentication methods, and troubleshooting for all platforms
analyzing-apm-data
Monitor application performance using the RED methodology (Rate, Errors, Duration) with Observe. Use when analyzing service health, investigating errors, tracking latency, or building APM dashboards. Covers when to use metrics vs spans, combining RED signals, and troubleshooting workflows. Cross-references working-with-intervals, aggregating-gauge-metrics, and analyzing-tdigest-metrics skills.
home-assistant
This skill should be used when helping with Home Assistant setup, including creating automations, modifying dashboards, checking entity states, debugging automations, and managing the smart home configuration. Use this for queries about HA entities, YAML automation/dashboard generation, or troubleshooting HA issues.
dapr-troubleshooter
Proactively detect and diagnose DAPR runtime issues based on error patterns, log analysis, and common misconfigurations. Provides immediate solutions for service invocation failures, state management issues, pub/sub problems, and deployment errors. Use when encountering DAPR errors or unexpected behavior.
zsh-completions-setup
This skill should be used when the user asks to "set up shell completions", "fix zsh completions", "configure tab completion", "add completions for brew/npm/cargo", "troubleshoot missing completions", or mentions fpath, compinit, or Oh My Zsh completion issues.
docker-debugging
Container debugging and troubleshooting techniques for production issues
llamafile
When setting up local LLM inference without cloud APIs. When running GGUF models locally. When needing OpenAI-compatible API from a local model. When building offline/air-gapped AI tools. When troubleshooting local LLM server connections.
debug-like-expert
Deep analysis debugging mode for complex issues. Activates methodical investigation protocol with evidence gathering, hypothesis testing, and rigorous verification. Use when standard troubleshooting fails or when issues require systematic root cause analysis.
model-equivariance-auditor
Use when you have implemented an equivariant model and need to verify it correctly respects the intended symmetries. Invoke when user mentions testing model equivariance, debugging symmetry bugs, verifying implementation correctness, checking if model is actually equivariant, or diagnosing why equivariant model isn't working. Provides verification tests and debugging guidance.
troubleshooting
Diagnose and resolve common issues during spec-driven development and implementation. Learn strategies for handling spec-reality divergence, dependency blocks, unclear requirements, and other execution challenges.
