$ skills --list

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dependencies, and rust-documentation skills.

Rust documentation practices for HASH codebase. Use when writing doc comments, documenting functions/types/traits/modules, creating error sections, using intra-doc links, or following rustdoc conventions.

Meta-skill for creating and managing Claude Code skills

Automatically trace Claude Code conversations to Braintrust for observability. Captures sessions, conversation turns, and tool calls as hierarchical traces.

Scrape web pages and extract content via Firecrawl MCP

Use when implementing any feature or bugfix, before writing implementation code

Systematic hook debugging workflow. Use when hooks aren't firing, producing wrong output, or behaving unexpectedly.

Fast codebase search via WarpGrep (20x faster than grep)

Code quality checks, formatting, and metrics via qlty CLI

Analyze Claude Code sessions via Braintrust

Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "learn from sessions", "compound learnings", or "what patterns should become skills".

Template for chaining multiple MCP tools in a single script

AI-powered web search, research, and reasoning via Perplexity

Complete Claude Code hooks reference - input/output schemas, registration, testing patterns

Analyze brownfield codebase and create initial continuity ledger

Search GitHub code, repositories, issues, and PRs via MCP

Use RepoPrompt CLI for token-efficient codebase exploration

Search library documentation and code examples via Nia

Fast file editing via Morph Apply API (10,500 tokens/sec, 98% accuracy)

AST-based code search and refactoring via ast-grep MCP