Official skill for creating, reading, editing, redlining, and commenting on Word (.docx) documents.
Official Anthropic skill that lets Claude Code build, template-fill, read, and validate .pptx/.potx presentations end to end.
An official skill that guides you and Claude through a three-stage process for writing proposals, specs, and decision docs.
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.
Official Anthropic skill that turns a prompt into a generative-art manifesto plus a self-contained, seeded p5.js viewer with live parameter controls.
Official Anthropic skill that makes Claude act as a design lead, producing UI with a distinct point of view instead of templated defaults.
Anthropic's official skill for researching, building, testing, and evaluating high-quality MCP servers in TypeScript or Python.
Official skill for reading, editing, and building Excel/CSV files with real formulas, professional formatting, and verified zero formula errors.
Manus-style file-based planning that tracks complex work in task_plan.md, findings.md and progress.md — and restores context after /clear.
Audits a UI against Dieter Rams' ten principles with cited evidence, then issues a NEW / REFINE / REDESIGN verdict plus a ready-to-run `/make-plan` handoff.
Keeps plans, findings, and progress in markdown files on disk so multi-step work survives context compaction and session breaks.
A router skill that dispatches any frontend UI/UX task across four rulesets — design taste, Lighthouse perfection, a UI/UX database, and design ops — to prevent generic AI-looking interfaces.
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 router skill that loads the right taste, brand, performance, and design-ops rulesets so frontend work ships at senior-designer quality.
A Git-focused skill for atomic commits, safe rebases, and evidence-backed history forensics.
Fans out parallel research swarms across your codebase, the web, official docs, and OSS repos, then delivers a fully cited, empirically verified report.