claude/skills/tooling/SKILL.md
Tooling and verification. Apply when encountering unfamiliar third-party libraries, framework updates, uncertain parameter types, verifying best practices, or uncertain API parameters.
npx skillsauth add channinghe/dotfiles toolingInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
"RTFM (Read The Fing Manual)." Don't guess API signatures. Don't assume library behavior. Before writing code, ensure you have evidence.
When encountering unfamiliar third-party libraries, framework updates, or uncertain parameter types:
resolve-library-id to convert library name (e.g., "shadcn/ui", "stripe-js") to accurate system IDget-library-docs to fetch latest official documentation snippetsApplicable scenarios:
Documentation tells you theoretically how to use it; GitHub tells you actually how to use it. When documentation is unclear or you need to reference best practices:
searchGitHub to search specific function or pattern implementations in real codebasesApplicable scenarios:
development
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
development
# Verification Loop Skill A comprehensive verification system for Claude Code sessions. ## When to Use Invoke this skill: - After completing a feature or significant code change - Before creating a PR - When you want to ensure quality gates pass - After refactoring ## Verification Phases ### Phase 1: Build Verification ```bash # Check if project builds npm run build 2>&1 | tail -20 # OR pnpm build 2>&1 | tail -20 ``` If build fails, STOP and fix before continuing. ### Phase 2: Type Check
development
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
tools
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.