1,266 boosters for "claude-code" — open source, verified from GitHub, ready to install
"description": "rr CLI skill - sync code and run commands on remote machines", "name": "Riley Hilliard"
This skill encodes the complete design specification for professional business presentations — a consultant-grade PowerPoint framework based on McKinsey design principles. It includes: All specifications have been refined through iterative production feedback to ensure visual consistency, profession
"name": "lich-skills", "description": "LichAmnesia's open-source Claude Code skills — flagship spec-driven-dev workflow plus Tavily search and Nano Banana image generation.", "name": "Shen Huang (LichAmnesia)",
FastAPI Templates provides production-ready project structures with async patterns, dependency injection, and error handling for developers building high-performance APIs. Backend engineers and Python developers benefit from standardized FastAPI scaffolding that accelerates project setup.
"description": "Blueprint-driven Claude Code autopilot. Smart preparation over endless iterations - AI analyzes patterns, creates solid implementation plans, delivers working code in 15 minutes.", "name": "Croffasia", "email": "support@vibecodekit.dev",
You are managing the TLive IM Bridge — bidirectional chat with AI coding tools from Telegram, Discord, or Feishu. The Bridge uses the Claude Agent SDK (or Codex SDK) to interact with the AI coding tool. It is completely independent from the optional Go Core web terminal server. Before any command ex
A structured code review workflow that orchestrates specialized AI agents to perform quality, security, performance, and documentation reviews within a 4-hour timeline. Useful for development teams seeking systematic, multi-perspective code quality assurance.
You play the role of a director's assistant fluent in the 5-stage AI shortfilm prompt structure (first proven by Mx-Shell in Zombie Scavenger). When the user invokes this skill they want a prompt they can paste
"description": "AI news aggregator that fetches AI industry news from smol.ai RSS and generates structured markdown with intelligent summarization and categorization. Optionally creates beautiful HTML webpages with Apple-style themes.", "name": "geekjourney", "email": "skrphper@gmail.com"
"description": "Claude Code plugin for TON API — REST API, Streaming, and Webhooks for TON blockchain.", "homepage": "https://tonapi.ness.uz/", "repository": "https://github.com/nessshon/tonapi/",
"description": "Modern R development skills for Claude Code - tidyverse patterns, rlang metaprogramming, Bayesian inference, performance optimization, and more", "name": "Claude Code R Skills" "homepage": "https://github.com/ab604/claude-code-r-skills",
Zettelkasten memory for AI agents. Markdown cards in with . npm package . Distributed as CLI + MCP server + Claude Code plugin + VS Code extension + Pi extension. Build has a known TS error ( optional dep). Ignore it — it compiles fine for distribution. If you add a new MCP tool:
Smart PRD generation with deterministic operations handled by . AI handles judgment (questions, content, decisions); script handles mechanics. Activate when user says: PRD, product requirements, taskmaster, task-driven development.
"name": "claudetop", "description": "htop for your Claude Code sessions — real-time cost tracking, cache efficiency, model comparison, smart alerts, web dashboard, and session analytics", "name": "Lior Weinstein",
Automates story task orchestration by prioritizing and delegating work across subtasks, automatically advancing stories through the development workflow. Developers and project managers using Linear/Kanban boards benefit from reduced manual status management.
"description": "Agent enforcement framework — context injection, planning gates, session learning", "name": "Mark Morgan", "url": "https://github.com/markmdev"
"name": "firecrawl", "description": "Scrape, search, crawl, and map the web with a single command.", "./skills/firecrawl-agent",
A comprehensive Go testing booster that teaches TDD methodology, table-driven tests, benchmarking, and fuzzing patterns for Claude Code users. Ideal for Go developers aiming to write reliable, well-tested code following idiomatic Go practices.
Query Google's AI Search mode to retrieve comprehensive, source-grounded answers from across the web. Trigger this skill when the user: 1. Include Current Year (2026) for up-to-date results
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json", "name": "polyakov-claude-skills", "description": "Набор скиллов для Claude: работа с .docx, веб-скрапинг, управление агентами",
幫使用者把想法變成高品質的 AI 生成內容 (圖片、影片、音樂)，核心工作是 寫對每個平台的 prompt 以及 必要時自動操作網站。 1. Intent Parser — 一句話拆 9 slot (媒體/長度/畫面比/主題/風格/角色/場景/音訊/語言) 2. Fill Defaults — 沒講的用預設 (video 預設 10s 16:9；動漫預設 Shinkai+Ghibli；電影預設 Deakins DP…)
用户学完一个东西想验真伪，或隐约觉得"好像懂了但不踏实"。也是"重输入轻输出"的一次强制输出。 请他用自己的话、把你当外行，把概念讲一遍。别让他背定义——要他解释、打比方。 专挑他含糊带过、用术语糊弄、跳过的环节追问："为什么？""那这个是怎么来的？""举个例子？"命中他答不上来或开始绕的地方。
"name": "design-council", "description": "Convene parallel role-specialized peer agents (dynamic roster, plan card first) to debate a cross-domain decision or audit a codebase in real time. Invoking Claude acts as CEO: convenes, routes peer-DMs, arbitrates deadlocks, writes a one-page decision log."
用户在纠结"要不要学 X / 学到什么程度 / 精力往哪放"。这是"广度优先、兴趣队列过长"倾向的刹车。 逼问一句：你要解决的具体问题是什么？ 没有具体问题、纯"感觉该学 / 别人都在学"→ 直接进"以后再学"队列，不占当下精力。理解知识的作用，重于知识本身。 这知识多久会贬值？（技术栈 / 工具往往 6–12 个月就明显更新）相对有限的时间值不值？贬值快 + 可外包给 AI / 随时查 → 只需"知道它存在、管什么"，不必真学。
