Anthropic's official skill for building new Claude Code skills, testing them with evals and benchmarks, and tuning descriptions for reliable triggering.
Search and rewrite code across 25 languages by syntax shape (AST) instead of text, with a safe two-pass codemod workflow.
Runs your diff through three hostile reviewer personas so you never get a lazy "LGTM" before merging.
A three-phase Scan/Fix/Verify skill that finds WCAG 2.2 A and AA violations and writes framework-specific fixes for React, Vue, Angular, Svelte, Next.js and plain HTML.
Gives Claude a domain-organized Biopython playbook for sequences, NCBI/Entrez, BLAST, structures, and phylogenetics.
Ports CPU-bound scientific Python to NVIDIA GPUs and proves the result is both correct and actually faster.
A safety-first guide and CLI toolkit for reading, writing, converting and de-identification-preflighting local DICOM data with pydicom 3.0.2.
Official skill that scaffolds a React + Tailwind + shadcn/ui app and bundles it into a single self-contained HTML artifact.
Official Anthropic skill that grounds Claude Code in current API facts — model IDs, pricing, streaming, tool use, agents, caching and migrations.
Official skill that lets Claude drive a real headless browser with Playwright to click, screenshot, and read console logs while testing your local web app.
Anthropic's official skill for researching, building, testing, and evaluating high-quality MCP servers in TypeScript or Python.
Analyzes every open issue and PR in parallel and writes permalink-backed triage reports to /tmp — without ever mutating anything on GitHub.
Runs a 9-dimension, file-cited technical debt audit and writes a prioritized TECH_DEBT_AUDIT.md report.
Scans, LSP-verifies and deletes unused TypeScript code, delegating per-file batches to parallel agents that commit atomically.
Runs five specialized sub-agents in parallel — goal verification, hands-on QA, code quality, security, and context mining — and only passes the review when all five pass.
Search, read, and reconstruct local coding-agent sessions across Codex, Claude Code, OpenCode and 20+ other agents from one command.
A Git-focused skill for atomic commits, safe rebases, and evidence-backed history forensics.
Enforces strict typing, modern toolchains, and TDD discipline whenever Claude writes Python, Rust, TypeScript, or Go.
A frontend discipline skill that forbids saying "done" until the build passes and the result is screenshot-verified in a real browser.
Explore codebases with tree-sitter AST parsing — index first, fetch details on demand, and cut token usage several-fold.