Claude Skills Directory

5,095 agent skills from 4,020 GitHub repos for Claude Code, Claude.ai and other agents. See what's popular, search by what you need, and copy the install command.

Install any skill repo in one command

npx skills add anthropics/skills

Swap in any owner/repo from this directory. Works with Claude Code, Cursor, Codex and other agents; every skill page also has a plugin and a manual install.

Skills leaderboard

Ranked by the GitHub stars of each skill's repo, plus forks and curated-list mentions.

View all →
  1. 1Academy Guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning186k
  2. 2Algorithmic Artanthropics/skillsCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.186k
  3. 3Brainstormingobra/superpowersTransforms rough ideas into fully-formed designs. Structure your brainstorming sessions and develop ideas systematically.310k
  4. 4Diagnosing Superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.310k
  5. 5Karpathy Guidelinesmultica-ai/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.227k
  6. 6Rea Analysis Optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.414k
  7. 7Rea Changelog Updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.414k
  8. 8Firecrawl Buildfirecrawl/firecrawlIntegrate Firecrawl into application code whenever a product, agent, or workflow needs web data inside the app — web search, live search results, page scraping, structured extraction, or browser interaction. Use when building any feature that needs data from the web in code, even if the user does not mention Firecrawl explicitly and only describes wanting web data, website content, search, scraping, or interaction in an application. Trigger for Firecrawl requests, "fire girl" shorthand, and generic app-level web-data needs that should map to `/scrape`, `/search`, or `/interact`. Do not use thi197k
  9. 9Firecrawl Build Interactfirecrawl/firecrawlIntegrate Firecrawl `/interact` into product code for dynamic pages and browser actions after scraping. Use when a feature needs clicks, form fills, pagination, authentication-aware flows, or other multi-step interactions that plain `/scrape` cannot complete.197k
  10. 10Ask Mattmattpocock/skillsAsk which skill or flow fits your situation. A router over the skills in this repo.308k

Browse by category

All skills

4,228 listed, most popular first

Nextjs SEO Audit

7

thisisAhsanIqbal/nextjs-seo-audit

Comprehensive SEO audit skill for Next.js and HTML pages. Covers on-page optimisation, JSON-LD schema validation, meta tags, Open Graph, semantic HTML, site speed, mobile responsiveness, and backlink analysis. Use when a user asks to audit, optimise, or fix SEO issues on a webpage or website.

Marketing, Sales & Business

Null

7

maxfield-allison/null

A quiet thinking mode that adds no unsolicited direction. Invoke explicitly with /null or $null; discussion of null, writing, or context influence does not activate it.

Writing & Content

Openspec Agent Sdd

7

trotsky1997/openspec-agent-sdd

Use when an autonomous coding agent (no human in the loop) needs to drive OpenSpec spec-driven development end-to-end — bootstrap, propose, implement, and archive a change without slash commands or interactive prompts. Triggers on "用 openspec 自主开发", "agent-own spec-driven dev", "openspec 无人值守 / 非交互", "spec-driven 自动跑一遍", "openspec init/propose/apply/archive 全自动", "drive OpenSpec from an agent". Captures the verified non-interactive CLI loop, the status/instructions state machine, the substitutions for OpenSpec's built-in "ask the user" stops, and validation-driven self-correction.

AI, LLMs & Agents

Pelago

7

Mikebouskila/pelago

Make an AI coding Wrapped from local Claude Code and Codex history. Turns every project into a pixel-art island and adds a story-style recap, a coding archetype such as "The Midnight Harbormaster", relics, shareable cards and a short video reel, all in one offline HTML page. Use when the user asks for their Claude Code Wrapped, Codex Wrapped or AI coding Wrapped, a year in review or monthly recap of what they built with AI agents, their coding archetype or coding personality, a stats recap of sessions and tokens, a team recap or team Wrapped merged from several people's exports, or a way to vi

AI, LLMs & Agents

Persian

7

Mojtaba-Alehosseini/persian-skill

Translate English↔Persian (Farsi) so it reads like a human translator, and fix Persian text mechanics: RTL, ZWNJ (نیم‌فاصله), ی/ک vs ي/ك, digits, punctuation. Use for any Persian text task.

Writing & Content

Playing to Win

7

paultaki/playing-to-win

This skill should be used when the user asks to evaluate, sharpen, red-team, or pressure-test a business idea, offer, market choice, product, or strategic move using Roger Martin and A.G. Lafley's Playing to Win choice cascade. Triggers on phrases including "Playing to Win", "P2W", "where to play", "how to win", "winning aspiration", "build me a strategy", "red-team this idea", "pressure-test this", "Plan to Win", or "build a strategy framework around this project". Produces a structured 12-section output across four phases (Diagnosis, Cascade, Stress Test, Verdict), writes a persistent markdo

Testing & QA

Portfolio Skill

7

PRABHUSIDDARTH/portfolio-skill

Design and build professional, award-level personal portfolio websites (developer, designer, researcher, creative, founder, student) with a bespoke art direction chosen for the person, real content, choreographed motion, case-study pages, a working contact form, SEO, accessibility, and deployment. Use when the user asks to create, redesign, or substantially upgrade a personal portfolio or personal-brand site. Not for generic company landing pages, dashboards, or e-commerce.

Finance & Crypto

Product Video

7

kritikmodi/product-video-as-code

Produce product videos end to end - product demos, feature launches, explainers, walkthroughs, tutorials, release notes, onboarding and social cuts - from a script, an AI voiceover, animated HTML slides and real screen recordings, rendered deterministically to MP4 with ffmpeg. Use when asked to create, edit, re-cut, re-voice, shorten or re-brand any video about software.

Images, Video & Audio

Prompt Engineering Expert

7

S3LabsAI/prompt-engineering-expert

Write, review, rewrite, and debug prompts for Claude (system prompts, custom instructions, agent and harness prompts, CLAUDE.md files, one-off task prompts), tuned to the model that will run them. Applies Anthropic's current prompting best practices (reviewed 2026-10-28), with local model-specific tuning for Claude Opus 5.5 and Claude Fable 5.1 / Mythos 5.1, per-model notes and docs lookups for Sonnet 5.5, Sonnet 5, Haiku 5.5, Opus 5, Opus 4.8, and Fable 5, and general guidance for every other model. Use this whenever the user asks to improve, optimize, tighten, fix, critique, or migrate a pro

AI, LLMs & Agents

Qianchuansucai

7

paul-xing/qianchuansucai-skill

顶级短视频获客文案专家,专精"元麻烦"理论与"卖点可视化"创作方法。为任何产品找到用户最深的自我怀疑,用硬核视觉测试击碎它,产出可直接拍摄的80秒获客视频脚本。使用场景:(1) 千川素材 / 抖音信息流获客脚本创作;(2) 用户要求写短视频带货脚本、获客视频、投放素材、广告脚本;(3) 需要挖掘产品痛点背后的"元麻烦"、设计卖点"暴力测试"画面;(4) 需要按十节点结构生成完整分镜头脚本。触发词:千川素材、获客视频、短视频脚本、元麻烦、卖点可视化、80秒脚本、信息流投放、带货脚本。

Other

Reading Compass

7

SkylarWJY/skylar-reading-compass

Distill any of 61 books (from 行者老师's 100-book reading list) for the user's specific life stage and role. The skill auto-detects 1 of 6 reader personas (大厂员工/founder/manager/creator/investor/transitioner) and re-frames every takeaway in their vocabulary, with their concerns. Returns 直白话 (plain language) action items across 9 angles: 决策框架 / 公司诊断 / 客户工作启示 / AI 机会扫描 / 个人赚钱机会 / 反共识 / 30/60/90 行动 / 警惕清单 / cross-book stacking. Use when the user asks "this book对我有什么用", "read this book for me", "用读书库分析", "[book/author] for [my situation]", "book stack analysis", "founder lens", or any reader-relative b

Finance & Crypto

Reelwright

7

janieehe/reelwright

面向旅拍店、妆造店、民宿,以及独立摄影师、独立妆造师等本地生活内容生产者,系统产出可直接开拍的短视频内容。覆盖拆解爆款、商家档案、客群画像、账号定位、内容矩阵、选题清单、脚本、分镜表、拍摄方案九个方向,每个方向都能单独用、也能串成一条从对标到开拍的线,台词/旁白去 AI 味、逐字可念。当创作者或自媒体人想拍短视频、起号、规划账号或选题、写脚本或改稿、拆分镜、排拍摄方案,或拆解对标视频/评论区、把爆款拍法换成自己的店(换皮)时使用。

AI, LLMs & Agents

Safe Encryption

5

grittygrease/safe-encryption-skill

Encrypt, decrypt, and manage keys with the SAFE CLI — a modern GPG alternative with post-quantum support.

Software DevelopmentIn 1 list

Scientific Review

7

wuliRothschild/scientific-review

Conduct systematic literature reviews on PubMed with enforced full-text verification and independent audit loops. Use when the user asks for a comprehensive literature search, systematic review, evidence synthesis, or deep research on a biomedical topic. Trigger when the user mentions "literature review", "systematic review", "调研", "文献综述", "汇总分析", "comprehensive search", "what does the literature say", or asks to survey published research on a gene, pathway, disease mechanism, or clinical question. Make sure to use this skill whenever the user wants thorough evidence synthesis — do not skip it

Research & Science

Second Brain

7

stancsz/second-brain

Use when the user wants to save durable knowledge, recall or connect their own notes, inspect knowledge gaps, manage a local personal wiki, exchange notes with Obsidian, or create and restore verified backups. Operates a local OKF Markdown knowledge graph with a rebuildable SQLite index.

Productivity & Notes

Static to Video Ad Complete

7

holy-templar/static-to-video-ad

v1.0 — Unified two-path skill that turns ANY static ad into video on the MaxFusion AI MCP, opening with a gate that asks which treatment the user wants. PATH A — ANIMATE THE STATIC AD: a real human hand enters frame and physically organizes the ad's elements one by one in photorealistic live-action (real physics, natural shadows, smooth human motion — never stop-motion) over 0-4s, non-text elements only; then every text block animates in cleanly at the end and the finished ad holds — 6 seconds, Google Omni locked. PATH B — MAKE A VIDEO AD: the static becomes the ENDING of a live-action clip —

Images, Video & Audio

Steam Debug

7

kmturley/steam-debug

Inspect, debug, and inject custom code into a running Steam client — desktop (macOS, Linux, Windows) or Steam Deck over the network — through its Chromium Embedded Framework (CEF) Chrome DevTools Protocol endpoint. Use when developing Steam UI plugins, mods, themes, or integrations — injecting CSS/JS to try a change, locating webpack modules and obfuscated class names, reading React or SteamUIStore state, inspecting Big Picture / Quick Access Menu windows, screenshotting what actually rendered, streaming console logs, or diagnosing runtime errors in Steam's UI. The same commands run against ei

Software Development

Story Architect Skill

7

narrastory/story-architect-skill

Engineer fiction-writing projects for Claude Code from idea through final manuscript. Use when initializing or adopting a short story, novella, novel, or serial project; designing characters, worlds, plots, timelines, scenes, prose, or revisions; reviewing chapters; checking continuity, clues, promises, and payoffs; or maintaining structured story files, project commands, context packs, and writing progress.

Writing & Content

Taxue Solar Polaroid

7

taxueseek/taxue-solar-polaroid

将二十四节气、季节主题、地点记忆或任意短句编译为有真实证据、自然中文文案和动态视觉结构的原创编辑视觉提示词;支持单张、多张解释矩阵、纸本档案、摄影与混合媒介,不把主题硬编码为固定物件、色卡或版式。当用户提到节气海报、季节视觉、编辑海报、节气组图、拍立得、纸本摄影、季节中文文案、美学提示词,或只输入“冬至”“春去秋来”等主题时使用。

Other

Tidyfactor Design

7

TidyFactor/Design

Code-native UI design lifecycle engine (Figma alternative) with Contextual Decision Layer (CDL). Supports all 7 design stages with zero per-page CSS/JS and pluggable CSS foundations (Native, Tailwind, daisyUI, Pico, Hybrid). Trigger on commands 'brief', 'study', 'init', 'brand', 'tokens', 'palette', 'layout', 'components', 'page', 'dashboard', 'motion', 'i18n', 'audit', 'deploy', or design system requests.

Frontend & Design

Tier 1 2 3 Skill System

7

H-Ali13381/tier-1-2-3-skill-system

Use when creating, editing, reviewing, packaging, or organizing AI-agent skills and deciding whether a skill should be text-only, script-backed, or backed by an ML/specialist pipeline.

AI, LLMs & Agents

Video Editing Skill

7

kajisho5/video-editing-skill

Deterministic video editing from a typed edit request (trim, cut, concat with transitions, speed change, fit / fill / resize, still-image overlay) with an exact source-to-timeline mapping and per-operation provenance. Executes through ffmpeg-skill; never takes commands, argv, filter strings or executables. Use when an agent has already decided what to edit and needs the edit performed, verified and traced. Not for deciding what to cut, transcribing, captioning, colour grading or audio mastering.

Images, Video & Audio

Video Layer Skill

7

Alexander-Kz/video-layer-skill

Produces whiteboard-explainer video layers from a voiceover MP3 for *Your Channel* YouTube channel (and similar faceless curiosity-essay channels). Orchestrates a multi-agent pipeline that transcribes the audio, plans rapid-cut scenes synchronized to narration, writes per-scene image prompts in fixed whiteboard style, generates images via Replicate (Grok Imagine Image / Nano Banana 2 / Flux Schnell), reviews them with vision agents, and assembles the final MP4 with FFmpeg. Use this skill whenever the user mentions whiteboard video, hand-drawn explainer, stick-figure animation, faceless YouTube

Images, Video & Audio

Video Notes

7

iamvista/video-notes

Use when the user gives a YouTube link or a local video file and wants an automatic transcript plus key-points notes. Triggers on /video-notes, "transcribe this video", "影片重點", "整理逐字稿", "影片逐字稿".

Images, Video & Audio

Wedding Invitation

7

wyx-sg/wedding-invitation-skill

Use this skill when the user wants to design and generate a wedding invitation card in any language. The skill drives a conversational workflow — you gather the couple's info and style preferences, design a bespoke HTML template from scratch (no template selection), render it locally with headless Chrome, produce a print-ready PNG, and include a live tweak panel so the user can adjust colors, fonts, frames, and optional components without rebuilding. All data stays on the user's machine; no cloud, no signups, no data leaves.

Frontend & Design

Writer

7

zdyya/writer-skill

End-to-end Chinese writing workflow: from a rough idea to a publish-ready article with embedded HTML infographics. Guides Claude through 6 phases (idea unpacking → research → drafting → fact-check → illustration → multi-role review) and supports an Auto Plan Mode for one-shot execution. Trigger when the user says any of: 写文章 / 写稿子 / 帮我写 / 续写 / 扩写 / 公众号文章 / 长文 / 出稿 / 按我的风格写 / 帮我整理成稿子 / help me write an article / turn this into a post. Also triggers when the user hands over raw material (PDF, brief, link, voice transcript, scattered notes) with intent like 帮我写一篇 / 整理成文章. Do NOT use for: short so

Writing & Content

Xiaohongshu Images

7

iamzifei/xiaohongshu-images-skill

Transform markdown/HTML into styled 3:4 ratio images for Xiaohongshu 新手引导:输入 `/小红书配图 新手`、「这个怎么用」「第一次用」「能干嘛」时,走 SKILL.md 的〈新手上路〉,不要直接开始干活。

Images, Video & Audio

Yafa UI Dashboard

7

rejourneyco/yafa-ui-dashboard

Design, build, refactor, or review polished responsive analytics dashboards, SaaS admin dashboards, business intelligence interfaces, and data-heavy product UI using Yafa-UI. Covers sidebar navigation, one-row page headers, multi-color KPI cards, charts, tables, filters, Lucide icons, accessible states, and mobile dashboard layouts across React, Next.js, Tailwind CSS, Vue, Svelte, and other frontend stacks. Do not use this visual system as the default for marketing sites, authentication, setup wizards, account or billing settings, or unrelated public pages.

Frontend & Design

Ynm

7

RobLe3/ynm-skill

Evidence-backed project and repository review for implementation correctness, architecture, specification-versus-code conflicts, tests-versus-documentation, release or production readiness, adoption, maintenance, security claims, and conflicting project evidence. Enter through lightweight YNM-0 routing, preserve unresolved evidence as MAYBE, and escalate only when additional work can materially improve the disposition.

Software Development

Youtube to Course

7

tstfully/youtube-to-course

Turn any YouTube video, or a few videos, into a fun interactive course: one HTML file with bite-sized modules, plain-English explanations, everyday metaphors, scenario quizzes with confetti, flip flashcards, glossary tooltips, progress tracking, a final score, and timestamp links back to the video. Use this skill whenever someone wants to learn from or study a YouTube video, lecture, tutorial, or podcast; make a course, lesson, lesson plan, study guide, training module, onboarding course, quiz, or flashcards from a YouTube video or playlist; or says 'turn this video into a course', 'teach me t

Images, Video & Audio

Agent Novel Framework V12

6

RTY798/agent-novel

Structured long-form fiction workflow with chapter-type routing, factual state, and narrative-first review.

Writing & Content

Agent Teams

5

AntonioGuadagnoAI/agent-teams

Playbook operativo per creare e orchestrare agent team in Claude Code (piu istanze di Claude Code che collaborano condividendo una task list e messaggiandosi tra loro). Usa questa skill ogni volta che l'utente chiede di lanciare un team di agenti, fare spawn di teammate, parallelizzare un lavoro su piu agenti, eseguire una review o un'indagine multi-agente, coordinare lavoro su frontend/backend/test con agenti separati, o menziona "agent team", "teammate", "team lead", "team di agenti" o "agenti in parallelo", anche senza nominare esplicitamente la funzione. Usala anche quando un task e abbast

AI, LLMs & Agents

Amazon Store Manager

6

anuraagraavi/Claude-Skill---Amazon-Product-Manager---Bulk-Upload-Optimize

Act as an expert Amazon Store Manager to create, optimize, and bulk upload Amazon product listings. Use this skill whenever a user wants to: create Amazon flat file / bulk upload sheets, optimize product titles, bullet points, descriptions, or backend keywords for Amazon SEO, manage product variations (parent-child), troubleshoot flat file errors, check category compliance or gating requirements, understand the A10 algorithm and ranking factors, write CRO-optimized listing copy, or manage any aspect of Amazon Seller Central catalog operations. Trigger this skill for ANY Amazon product listing,

Marketing, Sales & Business

Apple Design

6

bowen31337/apple-design

Build web interfaces (HTML/CSS/JS, React, Vue, Tailwind) that look and feel like Apple made them — the real Apple aesthetic, not generic glassmorphism. Covers Liquid Glass / iOS-26 materials as rendered CSS+SVG (specular highlights, refraction, vibrancy, fallbacks), Apple's fluid-motion physics (springs by damping/response, velocity handoff, momentum projection, interruptibility, rubber-banding) implemented in BOTH Motion (motion.dev) and GSAP (Flip, ScrollTrigger, SplitText, Inertia), SF typography optics, a drop-in Apple design-token layer, and complete copy-paste components (glass nav, spri

Frontend & Design

Bazi Master

6

secret04725-coder/bazi-master-skill

八字命理深度分析系统。精确排盘(代码计算,非LLM推算)+ 19章深度分析报告(含调候用神、经典引用、历史校准)+ 精美HTML可视化 + 合婚配对 + 一键部署分享。 Triggers: "算八字", "看八字", "批八字", "排八字", "四柱", "命盘", "算命", "排盘", "bazi", "帮我看看八字", "分析八字", "合婚", "配对", "匹配度", "生辰八字", "命理分析", "运势", "大运", "流年".

AI, LLMs & Agents

Beautsgo Booking

6

BeautsGO/beautsgo-booking

Book appointments at 1300+ top-rated Korean dermatology & plastic surgery clinics in Seoul, Busan, Jeju directly from your AI assistant. Supports laser, injection, Botox, skin boosters, double eyelid, rhinoplasty, anti-aging, acne treatment in Chinese/English/Japanese/Thai. Keywords: Korea medical tourism, Seoul skin clinic, Korean dermatology, plastic surgery Korea, 韩国医美预约, 韩国皮肤科, 韩国整形外科, 首尔美容院, 医疗旅游韩国, 韩国整容, 水光针预约, 肉毒素预约, 韩式双眼皮. 热门医院: 江南 — 梅宗德/Barog/JD皮肤科/hev赫熙/鹿美人/secret希瑞特/金泰拉/伊美芝/爱妮/美LAB/Oganacell奥嘉娜/reberry/Shinebom/ELEV/Pind/GD医院/ID医院/陶瓷医院; 明洞 — UMI优美/reberry/丹雅/lijin/可丽/daybeau/奥缇娜/本思;

Research & Science

Blitz

6

ADM-NKH/claude-blitz

A continuously-firing background work runner for Claude Code. Queue real tasks ("/blitz add"), track long-term goals ("/blitz goal add"), and enable per-project audit rotations ("/blitz audit enable"). Blitz fires on a configurable cadence with a per-project idle gate, decomposes goals into increments on a long-lived branch, and persists every fire's output to ~/blitz/runs/<timestamp>/. Includes commands to manage the backlog, goals, audits, schedules, and kill switches (off/on/skip).

Git & Code Review

Capcut

6

mane23-ai/claude-capcut-skill

CapCut/JianYing 프로젝트 자동 편집. 타임코드 컷, 내용 기반 장면 찾기(자막+비전), 토킹헤드 무음·NG 제거, 롱폼->쇼츠 변환, 자막 생성/스타일/번역, 프로젝트 검사/롤백. 백엔드: capcut-cli 단독. 트리거: 키워드 자동 감지 + /capcut 명시 호출. CapCut 프로젝트(draft 폴더)가 입력일 때만 발화. 일반 mp4 편집은 video 스킬로 위임.

Images, Video & Audio

Codify

6

anombyte93/codify

Refactor any skill by extracting deterministic operations into a Python script and slimming the SKILL.md to only AI judgment parts. Use when user says /codify, codify a skill, or optimize a skill.

Software Development

Collage Broll Minimax

6

jiangge0804-crypto/collage-broll-minimax

将约 5 秒口播文稿、观点句或抽象概念做成高级 editorial halftone paper-collage / 半调纸拼贴 B-roll。用户说“拼贴动画”“collage b-roll”“纸拼贴 b-roll”“半调拼贴”“拼贴风格配画面”“用这段文稿做拼贴动画”“gbro-collage-broll”“collage-broll-minimax”,或希望把一句文稿转成拼贴视觉隐喻时,必须使用此 skill。强制采用三阶段审批:先只提视觉隐喻,用户确认后才生成彩色拼贴静帧,静帧再次确认后才默认调用 MiniMax H3(海螺 3.0,platform.minimaxi.com 国内直连)生成首尾帧组装动画。默认视频模型固定为 MiniMax-H3;只有用户明确指定其他模型时才切换。

Research & Science

Diagram Tour

6

centraltowerlabs/diagram-tour

Generate a narrated architecture-tour video from a codebase. End-to-end: codebase analysis → Graphviz .dot → narration script → narrated MP4. Three confirmation gates between user and final video. Use when the user asks to "explain this codebase", "tour the architecture", "make a video about how X works", or invokes /diagram-tour explicitly. Output: a versioned MP4 at <project>/.diagram-tour/renders/. Expensive — confirm runtime expectations (~15-30 min on modern hardware, longer on lighter machines) before kicking off.

Images, Video & Audio

Disk Jockey

6

bmcreations/disk-jockey

Diagnose and safely reclaim disk space on developer machines filled by AI agents, worktrees, builds, simulators, emulators and toolchain caches (Xcode, Android/Gradle, Node, Docker, Python, Rust, Go). Use when disk is low or filling fast, builds fail with "No space left on device", kernel_task shows huge disk writes, or the user asks to clean up storage.

Software Development

Douyin Content Engineer

6

why20261/douyin-content-engineer

抖音内容引擎 — AI驱动的内容电商助手。覆盖带货视频分析、竞品账号分析、抖音爆款视频挖掘、短视频爆款逻辑分析。提供4个能力:①关键词搜索(可按点赞/最新排序、时间窗、时长、图文类型筛选)②博主主页作品抓取 ③视频/图文评论抓取 ④实时热榜。输出结构化 JSON(含作者、互动数据、标签、链接)。当用户需要搜抖音视频、抓博主作品、看抖音评论、查抖音热榜、做竞品/对标账号监控、短视频选题调研、评论舆情分析、热点追踪、爆款挖掘时使用。触发词:抖音搜索、抖音热榜、抖音评论、抖音作品、博主作品、对标账号、抖音竞品分析、抖音数据分析、短视频运营、抖音舆情监控、抖音热点、舆情监控、热点追踪、爆款挖掘、douyin search、douyin content、douyin post、douyin hot search、douyin comments。

Writing & Content

Dsh Plugin Dev Skill

6

green-dalii/dsh-plugin-dev-skill

指导任何 Agent 正确、高效、符合规范地开发 DeepSeek Harness(DSH)插件。涵盖 Tool(defineTool)、LLM 适配器、服务与依赖、事件系统、配置、打包发布,以及 Cordis 框架的心智模型、代码模板与验证清单。

AI, LLMs & Agents

Fable Frame

6

AlessandroFare/fable-frame

A universal skill for Claude Code, Minimax Code, and any AI coding agent that accepts markdown skill files. Combines the Fable Brain behavioral prompt (8 modules that fix how a model responds), Karpathy's agent-orchestration mindset and workflow (program.md, AutoResearch, parallel tracks), and 50 production-ready mega-prompt templates invokable with `use template [NAME]`. Drop SKILL.md in as system instructions and the agent gets a working behavior, a working workflow, and 50 ready prompts.

AI, LLMs & Agents

Flaky Test Detector

4

sametcelikbicak/flaky-test-detector

Detect, analyze, and fix flaky tests across any test runner. Use when tests intermittently fail in CI, tests pass locally but fail on CI, tests fail non-deterministically, or need to stabilize a flaky test suite. Also for 'flaky test', 'flaky', 'intermittent failure', 'unstable test', 'test flakiness', 'test retry', 'CI flaky', 'non-deterministic test'.

Testing & QAIn 1 list

Furusato Nozei

4

tahodev/kurashi-skill

給与収入や課税所得からふるさと納税の寄附上限額(自己負担2,000円の目安)を計算する。ふるさと納税、寄附上限、寄附金控除、ワンストップ特例の相談に対応。API不要の純粋計算。確定申告書の作成や個別の税務判断は対象外。

Software DevelopmentIn 1 list

Game Quality Gates

6

abczsl520/game-quality-gates

Game development quality gates and mandatory checks. Activate when building, reviewing, debugging, or deploying any game project (H5/Canvas/WebGL/Phaser/Three.js/2D/3D). Covers state cleanup, lifecycle management, input handling, audio, persistence, networking, anti-cheat, and performance. Use as pre-deploy checklist or when diagnosing game-specific bugs (state leaks, phantom timers, buff conflicts, memory growth, touch issues).

DevOps & Cloud

About Claude skills

What is a Claude skill?

A skill is a folder with a SKILL.md file: a name, a one-line description of when to use it, and instructions (plus optional scripts and reference files). Claude reads only the description up front and loads the rest when a task needs it, so you can install many skills without filling the context window. Skills work in Claude Code, Claude.ai, the Claude app and the Claude API, and the same format is used by other agents such as Codex and Cursor.

How do I install a skill in Claude Code?

Copy the skill folder into ~/.claude/skills (for you) or .claude/skills in a project (for your team). If the repo is a plugin marketplace you can also run /plugin marketplace add owner/repo inside Claude Code and install it from /plugin. Every skill page here has the exact commands.

How is popularity measured?

Mostly by the GitHub stars of the repo the skill lives in, with forks, the number of curated awesome lists that include it, and the number of repos that carry a copy as smaller signals. Skills from a repo with hundreds of skills share that repo's stars, so they get a small penalty to keep one big collection from filling the list.

Where does this directory get its skills?

From Anthropic's official anthropics/skills repo, the largest community lists (VoltAgent, travisvn, ComposioHQ, BehiSecc, karanb192, heilcheng, skillmatic-ai and hesreallyhim) and a GitHub search for skill repos. Every SKILL.md in those repos is read for its name and description, and copies of the same skill are merged. It refreshes every day.

Are these skills safe to install?

Skills can include scripts that run on your machine, so treat a skill like any other code from the internet: read the SKILL.md and any scripts before installing, prefer official and well-starred repos, and check the license.

Sources: anthropics/skills (official), travisvn/awesome-claude-skills, ComposioHQ/awesome-claude-skills, VoltAgent/awesome-agent-skills, BehiSecc/awesome-claude-skills, karanb192/awesome-claude-skills, heilcheng/awesome-agent-skills, skillmatic-ai/awesome-agent-skills, hesreallyhim/awesome-claude-code, and GitHub search. Last updated 31 October 2026. Want your own? Try the skills generator.