Converts a raw git log into grouped, user-facing release notes with a headline and migration note.
Restructures a bloated CLAUDE.md/AGENTS.md into a lean Level 1 plus on-demand Level 2 references with guaranteed zero information loss.
Detects your project's stack and auto-configures lint, typecheck, test and format quality gates plus a Claude settings file.
A playbook for running multiple Claude Code sessions as a lead-plus-teammates team with shared tasks, messaging, and file locks.
A workflow skill that decomposes repetitive, large-scale code changes into independent units and runs one parallel agent per isolated git worktree.
Turns a code change or codebase slice into an animated architecture/data-flow diagram and attaches it to a pull request.
Turns a diff or part of a codebase into a validated JSON graph and renders it as animated architecture / data-flow diagrams for a canvas link or a pull request body.
Renders a CLI command's colored terminal output to PNG so Claude can visually judge contrast, alignment and highlighting instead of reading raw escape codes.
Sets up internationalization in React/Next.js/Vue codebases, replaces hard-coded strings with keys, and validates locale parity, plurals, and formatting.
Measure any OpenAI- or Anthropic-compatible LLM endpoint across six dimensions: availability, request fidelity, speed, concurrency, protocol compliance, and quality regression.
A phase-based playbook for shipping pull requests that maintainers of third-party repos actually merge.
A rigorous maintainer-grade workflow that re-reviews GitHub pull requests against the current base branch, binding every verdict to exact Git OIDs.
A field-tested guide for building iOS/macOS apps with XcodeGen, SwiftUI and SPM, plus Apple code signing, notarization and CI/CD fixes.
Rebuilds only the actionable context from local `.claude` session files so you can resume interrupted work without `claude --resume`.
Reviews Claude Code skills against official best practices, with modes for self-review, external repo evaluation, and automated improvement PRs.
A rigorous visual QA protocol that audits already-rendered web, deck, dashboard, and Electron UIs with real-browser evidence and produces an evidence-backed defect report.
Git forensics skill that recovers lost commits, branches and stashes, proves merges by content, and retires leftovers only after verified backups.
A battle-tested guide to writing, testing, registering, and debugging Claude Code PreToolUse / PostToolUse / SessionStart / Stop hooks.
A macOS network-debugging skill that isolates and fixes Tailscale conflicts with Shadowrocket/Clash/Surge/OrbStack — route hijacks, proxy env vars, SSH double tunnels, Docker proxy propagation and stalled DNS.
A hands-on skill for invoking Bedrock foundation models, generating embeddings, building RAG, and debugging access and quota errors.