Claude
Tools

A Claude Code skill that turns long-form agent output into a designed HTML report — TOC, callouts, framed figures, footnotes, light/dark themes, and one-click export back to Markdown.

Three complementary agent skills for academic research: WRITES papers, FINDS papers on a topic, READS any paper as a visual experience (mind maps, flowcharts, plain-English). Runtime-neutral, works with 50+ agents. Install: npx skills add aniketkrs/research-paper

A Claude Code skill that audits a repository against Anthropic's Claude Code engineering best practices and writes a scored, read-only compliance report.

The free Roast & Rebuild Claude Code skill. Audit your repo in 60 seconds. 6-module local audit with cited evidence. MIT licensed.

Opinionated Gemini Code Assist PR review loop for Claude Code & Codex. Thread-state-aware, severity-filtered, cycle cap, sticky-receipt visibility. No CI coupling.

A Claude Code skill that produces presentations worth sending — research-first, narrative-driven 5-phase workflow inspired by Genspark AI Slides.

Community skills for Claude Code: token optimization, productivity workflows, and development best practices. All skills tested with TDD methodology (RED-GREEN-REFACTOR). Features rescue-tokens skill: 90% verbosity reduction, eliminates rate limits through 9 optimization patterns.

Open-source Claude Agent Skill that generates custom AI Operating Systems for small businesses across 13+ verticals (dental, salon, restaurant, contractor, real estate, vet, photographer, fitness, insurance, CPA, law, HVAC). Built for Claude for Small Business + Anthropic Agent Skills standard. MIT licensed. https://clawvr.com

Portable, self-contained snapshot of a complete Claude Code setup — 36 specialist agents, 134 skills, plugins, MCP servers & host tooling. Clone, claude login, run one script, restore the whole orchestration stack in ~20 min.

Type prompts into Claude Code / Codex in your own language - a UserPromptSubmit hook translates them to English so the agent reasons in English.

Runtime token proxy + intelligence dashboard for LLM tools. Intercepts API calls, strips waste, tracks costs — for individual developers and Fortune 500 teams.

the network agent that keeps an eye on your network

Pi coding agent extensions that helps you connect to all coding agents from one place using ACP and maximize your AI credits across Cursor, Codex, Claude Code, Rovo

A quiet study-buddy skill for Claude Code. Body-doubling focus sessions, distraction-killing ritual, and markdown logs that prove you showed up. Made for neurodivergent brains.

Markdown → telegra.ph publisher. Stdlib-only Python 3 CLI: publish, --edit existing pages, tables, images, h3/h4 normalization.

This is a collection of skills I have created for Couchbase for Claude.ai

a claude-code extension to give claude a hobby between user inputs in a session

Migrate LLM apps between models safely — then benchmark old vs. new to prove the upgrade. Agent skill for behavior-preserving migrations + a runnable eval harness (three-arm leaderboard, prompt sweeps). Works in Claude Code, Codex & Cursor.

Give AI coding agents control of your real Chrome browser — with login sessions, cookies, and extensions.

Teach an LLM to talk like a person — It teaches a language model how to talk like a person. Not how to sound like one — that part's easy, and it's what most failures already do

VeyraSkills — A curated collection of Claude Code skills for founders, developers and AI builders

A Claude skill for professional IA — built from 7 practitioner books including Spencer, Morville & Rosenfeld, Krug, and Marquis.

VS Code extension that bridges IBM i source members to local temp files for editing with Claude Code or any local tool

A Claude Code hook that catches AI hedging and forces verification.