Claude Skills Directory

Win-Hao/music-mv

用代码给一首歌做一支音乐 MV（不用视频生成模型）：先把歌听懂（歌词时间轴、节拍、情绪起落、别人怎么理解这首歌），再定画风、画角色、写剧本和分镜、先出草图再做整片，最后照清单看片修改；也能先拆一支参考视频的风格再照着做。画面用 Canvas / p5.js / p5.brush 一帧一帧画，HyperFrames 合成歌词和歌。用户说「给这首歌做个 MV」「做一支音乐 MV / 歌词 MV / 动画 MV」「学这个视频的风格做一支 MV」，或 make a music video / lyric video for this song 时使用。不限模型，能读写文件、跑命令的 agent 都能照做。

PompeiiChan/skills-ExplainPaper

AI论文解读工具。面向产品经理、运营等非技术背景但对AI感兴趣的读者，将晦涩的学术论文转化为图文并茂的通俗研报：讲清楚”这个技术解决什么问题、有多厉害、对业务意味着什么”，配以极简科技风插图，并输出莫兰迪风格的 HTML 单文件。

anzy-renlab-ai/pronounce

User asks how to pronounce an English word or project/product name ("how to pronounce X", "pronounce X", "X 怎么读", "X 怎么发音", "读一下 X"). Generate audio via the `say-it` CLI so the user actually HEARS the word — three times by default — instead of only writing IPA/syllable hints. The CLI consults a community-maintained pronunciation dictionary (kubectl → "koob-control", GIF → "jif", JSON → "jay-son", ...) and feeds an English-like respelling to the system TTS engine (macOS `say`, Linux `espeak-ng`, or Windows PowerShell) so project names come out the way engineers actually say them. Triggers on a

Winnershitram/r17-behisecc-awesome-claude-skills-datascience

🤖 Data Science & AI/ML skill suite derived from BehiSecc/awesome-claude-skills. Data pipelines, model training, evaluation, MLOps and analytical reporting. Provides 10 specialised commands for data-science, machine-learning, analytics workflows.

nik1t7n/research-craft-skill

Use when planning, reviewing, or improving research work: choosing research problems, designing ML/AI experiments, reading papers, building experiment loops, analyzing outputs, writing research notes, or turning vague curiosity into a disciplined research plan. Emphasizes avoiding absorbed problems, upgrading information inputs beyond shared reading lists, and reasoning backward from outcomes the researcher genuinely wants to exist.

Andiii208/seu-handbook-skill

东南大学本科生规章制度查询（仅限本科生）。当问题涉及东南大学/东大/SEU 的大学生手册、学籍、注册、考勤请假、军训、选课、学分、绩点、考试、补考重修、免修免听、缓考、转专业、大类分流、推免保研、休学复学、延长学习年限、退学、毕业结业、学士学位、毕业设计（论文）、转学、辅修/双学位、奖学金（国奖/励志/校长奖）、三好学生标兵优秀干部、优秀毕业生、先进班集体、课外研学加分、学科竞赛、社会实践、SRTP、论文专利、助学金、勤工助学、助学贷款、应征入伍、家庭经济困难认定、违纪处分、申诉、学生公寓宿舍、门禁熄灯违章电器、学生证校园卡、图书馆、缴费退费、评教、实验室安全、因公出国（境）、体育体测、部门联系方式时使用。依据《东南大学大学生手册（2025）》逐条作答并附条款引用。

makenotion/cursor-notion-plugin

Turn product or tech specs into concrete Notion tasks. Breaks down spec pages into detailed implementation plans with clear tasks, acceptance criteria, and progress tracking.

kcy4334-lgtm/translate-book-arxiv

Translate an arXiv paper, or any PDF/DOCX/EPUB book, into any language as a printable book. For arXiv papers it reads the LaTeX source, so equations, tables, figures and numbering survive. Parallel sub-agents translate the chunks; output is HTML, DOCX, EPUB and PDF.

nevertoday/xxd-strip-ai-meta

Remove C2PA Content Credentials, AI provenance, OpenAI/gpt-image metadata, prompts, EXIF/XMP/IPTC/comment/software metadata from image files or directories. Use when users ask to strip "made with AI", C2PA, Content Credentials, image metadata, EXIF, AI labels, OpenAI provenance, or batch-clean many PNG/JPEG/WebP/TIFF images while replacing originals and preserving pixel quality as much as possible.

AlekseiUL/agentforge-openclaw

Создание, улучшение и аудит скиллов и агентов OpenClaw. Три режима: создание скилла (11 шагов), создание агента (9 шагов, с памятью и автоулучшением), улучшение существующего (5 шагов). Triggers: 'создай скилл', 'новый скилл', 'создай агента', 'новый агент', 'улучши скилл', 'skill creator', 'agent creator', 'скиллмейкер'.

DezXBT/AgentX

Drive X/Twitter from the CLI (read, post, DM, lists, communities, Grok, scheduling, analytics). Use when an agent needs to read or act on X/Twitter. Every command prints one JSON envelope.

jomeswang/agnes-ai-skill

Use when the user wants Agnes AI text, image, or video generation and should execute it through the agnes-ai-cli command line instead of hand-writing raw HTTP requests.

yaohui325/codex-bridge

显式触发的 Claude Code → Codex CLI 桥接 skill。把对话上下文 / plan / 相关文件 / 项目约定外化为 bundle 目录，调用 codex exec 并用 response.schema.json 作结构参考 + Claude Code jq 后处理校验。适用 4 场景（v1.1 起）：plan 审阅、Codex 编码、Claude-Codex 互审最多 2 轮迭代、verification-round 验证轮。

nasqret/labyrinth-exploration

Map and advance open-ended research programmes in mathematics, theoretical science and algorithms. Use for pushing bounds, attacking open conjectures, mapping what is still unknown, or independently refereeing and integrating research from agents or external models. Maintain proof tiers, provenance, frontier data and a dashboard. Not for a single self-contained proof, a one-off literature question or ordinary code review.

Odyphus/MathModel-Copilot

MathModel Copilot, an evidence-based mathematical-modeling competition workflow built on mathmodel-skill. Use for CUMCM, MCM/ICM, Diangong or custom modeling contests, including requirements, per-question modeling, actual Python runs, independent validation, paper assembly, team handoff and submission audit. Preserves ten stages and Critic/Red Team. Do not trigger for unrelated data analysis or ordinary paper review. Maintenance requests modify the skill rather than start a contest.

MetaMask/agent-skills

Use when the user asks anything about blockchain wallets, transactions, signing, token transfers, supported chains, wallet balances, perpetual futures trading, funding rates, and Hyperliquid vaults, prediction markets, token swaps, cross-chain bridges, market data, token discovery, tokenized real-world assets, RWAs, AI-generated market and asset summaries via pulse, decoding EVM calldata, DeFi earn/yield vaults, installing or removing third-party `mm` CLI plugins, or authentication via the MetaMask Agentic CLI; also when an HTTP request returns 402 Payment Required / x402, when an MCP tool cal

tanis90/pdf-converter-mineru

PDF converter powered by MinerU — convert PDF to Word, Markdown, HTML, LaTeX, or plain text. Also handles image-to-text OCR, scanned document recognition, and Office formats (DOCX, PPTX, Excel). Supports 80+ languages. Use this skill when the user wants to convert, extract, read, parse, or summarize any PDF or document. Also applies when the user shares a PDF file or link and asks about its content, needs tables or formulas extracted, wants PDF OCR, or says things like 'turn this into a doc' or 'what does this paper say'.

BayramAnnakov/synthetic-market-research

Fast, cheap market research using LLM-generated synthetic survey responses with Semantic Similarity Rating (SSR). Runs purchase intent, concept tests, and pricing research in minutes instead of weeks, at $0 per respondent. Based on PyMC Labs' validated methodology (90% correlation with real humans across 57 surveys). Triggers: synthetic research, market research, survey, purchase intent, concept test, consumer research, SSR, synthetic survey, product validation, pricing research, Likert scale.

DeliciousBuding/xiaohongshu-skill

小红书 / Xiaohongshu / RedNote AI Agent Skill。用 Python Playwright 搜索和读取内容、管理登录会话、发布图文/视频/长文、评论、点赞和收藏；默认输出 JSON，任何写操作都必须先获得用户确认。用户提到 xiaohongshu、小红书、rednote、小红书搜索、发到小红书、小红书笔记分析、小红书运营或小红书自动化时触发。

Agoragentic/agoragentic-integrations

Route an Agoragentic task to the smallest applicable skill. Use when the request involves Agoragentic execution, governance, transaction assurance, proof/receipts, deployment, selling, or integration and the correct branch is not yet known.

serenawangCU/chapter-progress-bar

根据视频字幕（.srt）或时间戳，用 HyperFrames 生成章节进度条透明 overlay， 支持 Chapter、Dash、Minimal、Text Highlight、Customize、Crab 六种视觉风格， 并在 macOS 上交付轻量、剪辑软件兼容的 HEVC Alpha MOV。用于章节划分、进度条设计、 透明视频预览、渲染与交付；除非用户明确要求，否则不要使用 Remotion。

cypress-io/ai-toolkit

Creates, updates, and fixes Cypress tests (E2E/end-to-end and component tests). Use when the user asks to create tests, add tests, write tests, update tests, test this file/component, new spec, or fix a failing or flaky test. Apply even when the user does not say 'Cypress' (e.g. 'create tests for this file'). Prefer cypress-explain when the user only wants to explain or review tests without changing code.

cypress-io/ai-toolkit

Search and extract Cypress information from official documentation (docs.cypress.io, cypress.io); prefer LLM markdown under /llm/* and refuse unverified API or behavior claims.

cypress-io/ai-toolkit

Explains Cypress tests (E2E and component tests), and answers questions about Cypress use and behavior. Use when the user asks to explain how a test works, explain how Cypress works, review or critique a test without writing code. Apply even when the user does not say 'Cypress' (e.g. 'explain this test'). Prefer the cypress-author skill when the user wants to create, fix, or update tests.

h0x0er/ebpf-skill

Practical guidance for choosing, writing, loading, and debugging eBPF programs. Prioritizes correct toolchain and hook selection, map choice, kernel-version fit, verifier triage, and concise production-ready examples using libbpf, ebpf-go, and bpftrace.

l2461090/Literature-monitor-skills

Monitor when scholarly articles first become visible to readers on official journal or publisher surfaces—such as ASAP, Online First, Early View, Advance Articles, FirstView, Early Access, Articles in Press, or Latest Articles—and report newly observed relevant work with verified titles, persistent identifiers, and source-grounded abstract summaries. Works for user-specified STEM/SCI, social-science, arts, and humanities journals. Use for recurring target-journal alerts or a 本周最新论文/期刊周报, not broad reviews without a journal whitelist.

Wh1tZz/Obsidian-through

Configure, repair, explain, and verify private Obsidian synchronization across Windows, macOS, GitHub, and mobile devices. 配置、修复、解释并验证 Windows、macOS、GitHub 与移动设备之间的 Obsidian 私有同步。Use for private vault repositories, Windows edit-event sync, macOS Obsidian Git sync, mobile setup, GitHub token/key guidance, Pull/Commit/Push workflow explanation, device-setting isolation, duplicate-note diagnosis, accidental deletion recovery, multi-device sync strategy, failed pushes, and end-to-end checks. 用于私有笔记仓库、Windows 编辑事件同步、macOS Obsidian Git 同步、移动端配置、GitHub Token/Key 指导、Pull/Commit/Push 工作流解释、设备设置隔离、重复笔记诊

brycewang-stanford/Paper-WorkFlow

将社科实证研究从 idea、proposal、数据或已有结果推进到可复现分析和完整论文 DOCX。 支持研究设计、数据审计、估计、表图、写作与修订，以及按需准备投稿包；按证据完成阶段， 不承诺显著结果或录用。触发：/paper-workflow、从想法到论文、从数据到 docx、推进已有实证稿件。

antonioc-cl/sales-council

Expert sales council with 6 advisors (Cialdini, Hormozi, Rackham, Voss, Klaff, Schwartz) for pricing, persuasion, negotiation, copywriting, and pitch strategies.

gavogavogavo/claude-sbox

Use when writing or modifying code for s&box, sbox, the Facepunch sandbox engine, or any Source 2 game project in C#. Triggers on mentions of s&box, sbox, sandbox game, Facepunch engine, Source 2 game, `.sbproj`, `.razor` with `PanelComponent`, `@inherits PanelComponent`, `Sandbox.Component`, `GameObject` + `Components.Get<T>`, `Scene.Trace`, `CharacterController` + `.Move()`, `SkinnedModelRenderer`, `NavMeshAgent`, `[Sync]`, `[Rpc.Broadcast]`, `[Property]`, `INetworkListener`, `ISceneEvent`, `PlayerController` in C#. Also triggers on any file with `using Sandbox;` or `using Sandbox.UI;` that

malkreide/socratic-method-skill

Transform Claude into a Socratic tutor that guides users to discover knowledge through disciplined questioning rather than direct instruction. Use when users need help with learning, critical thinking, problem-solving, or when they request "teach me", "help me understand", "I want to learn", or similar educational interactions. Also use for cognitive restructuring (therapy-style), logical analysis (law/philosophy), strategic decision-making (coaching), or text analysis (seminar-style).

quantskills/skill-a-share-stock-dossier

Generate a structured Chinese A-share stock due-diligence dossier from Pandadata interfaces, covering company profile, financials, dividends and capital actions, shareholder behavior, pledge/unlock/reduction risks, market funds, and sourced appendices. Use when the user asks for A股个股体检、个股尽调、公司全面分析、股票基本面报告、质押解禁减持风险排查, or a one-stop A-share company dossier.

tigusigalpa/ai-kit

Use when installing, configuring, upgrading, explaining, or maintaining AI-KIT, the portable kit that gives AI coding agents verified project memory, stack rules, guardrails, model routing, and native client configuration.

sakuraoxo-clio/sakura-animate-text

Curated text animation catalog with exact JSON specs for headings, labels, counters, and text swaps. Use when an agent needs to pick or translate named effects like soft blur in, typewriter, shared axis, line reveal, stagger, crossfade, or kinetic builds into WAAPI, Motion, Framer Motion, GSAP, CSS, Lottie, Rive, or similar stacks.

yanliudesign/behavior-question-skill

行为面试 skill。帮求职者挖掘真实经历、用 STAR/CAR 结构化、映射能力标签、构建可复用的中英双语故事库（Story Bank）；并能接入 JD + 简历，针对具体岗位生成 Top 20 BQ 选题 + 基于真实经历的 STAR 准备模板（HTML 报告）。不是背答案，而是建立可复用的职业叙事体系，让任何行为面试题都能自然作答。关键词：behavioral question, BQ, 行为面试, STAR, 故事库, Amazon LP, 职业故事, tell me about a time, 面试准备, JD 面试题预测, top 20 题。

opitaru-sys/deck-dna

Build a brand-accurate PPTX deck from your own reference decks - extracted design DNA, a calibrated word budget, real backgrounds/fonts embedded so it renders identically anywhere, and a render-QA loop. Use whenever a deliverable is a slide deck that needs to look like your real client/brand decks, not a generic template.

zhouwei713/facial-expression-prompting

Direct believable character performance and generate complete AI video prompts for text-to-video models. Use for facial acting, microexpressions, emotional transitions, dialogue performance, or vague character ideas such as “an ancient beauty breaks down.” When the brief is vague or asks for a video prompt, expand it into a complete prompt with an adult character, scene, dramatic motivation, emotional progression, facial and body performance, camera and lighting, adaptively chosen duration and exact timeline, audio, consistency locks, and negative constraints. When the user explicitly asks onl

ai-freer/fortune-skill

中国传统命理分析（八字+紫微斗数）。通过对话收集出生信息，调用排盘脚本获取精确数据， 结合经典典籍进行专业分析。 Triggers: "算命", "算八字", "看八字", "批八字", "排盘", "紫微", "紫微斗数", "帮我看看命", "我的运势", "今年运势", "合婚", "bazi", "ziwei", "fortune

altryne/jevify

Use Jev as System One to save the user reasoning-model tokens, time, and cost on bulk reading or repeated semantic decisions. Trigger when sifting large documents or tool outputs, selecting evidence or actions from many candidates, or checking many items against criteria, even if the user never mentions Jev. Also use for "Jevify this", Jev question design, and product work where frequent, inexpensive judgments could improve the experience.

ganlin770/nsfc-nssfc-grant-writing

帮助申请人撰写自己的【国家社会科学基金（国社科/NSSFC）】与【国家自然科学基金（国自然/NSFC）】项目申请书/标书/本子的完整辅导 skill。覆盖选题与申请代码归口、立项依据与研究现状述评、研究内容/研究目标/关键科学问题凝练、研究方案与技术路线、创新点、研究 基础与队伍、经费预算、预期成果、年度计划、活页匿名、评审打分逻辑与被毙原因、科研诚信红线与生成式AI使用规范、申报流程时间线， 并内置【图表制作】工具一键生成技术路线图/研究框架图/机制模型图/甘特图（matplotlib，导出可印刷的 PNG/PDF/SVG）。 Use this whenever the user mentions 国社科/国家社会科学基金/社科基金/国自然/国家自然科学基金/自科基金/基金申请书/标书/本子/ 活页/课题论证/立项依据/技术路线图/申报书/面上项目/青年基金/重大项目/重点项目/中华学术外译/后期资助，或说"写基金/改本子/ 润色立项依据/做技术路线图/凝练科学问题/基金申报/课题申报/申请书怎么写/评审会不会中"。这是写"自己的"申请书的辅助工具， 不代写、不买卖申请书。NOT for 期刊论文写作/毕业论文/开题报告（用 thesis 相关 skill）、纯文献综述、或与基金申报无关的写作。

mfarzanansari/prompt-polish

Rewrite a rough prompt into a polished, model-specific prompt grounded in the official Anthropic prompting guides. Use when the user invokes prompt-polish, types an invocation like "prompt-polish/FABLE 5/[prompt]" or "prompt-polish/OPUS 4.8/[prompt]", or asks to polish, improve, rewrite, optimize, or tune a prompt for a named model ("make this prompt better for Fable 5", "tune this for Opus"). Supports Claude Fable 5 and Claude Opus 4.8 (Opus 4.7 routes to 4.8 guidance). If no draft prompt is provided, ask for it rather than inventing one.

joeseesun/qiaomu-model-cli

Call local Grok CLI, Kimi Code CLI, and Claude Code CLI with the strongest current default models and native tools. Use this qiaomu skill workflow when the user wants to run Grok 4.5 for X/web search, image/video generation, research, or multi-tool agent work; run Kimi K3 (1M) for frontend UI/CSS/React/Vue work; run Claude Fable 5, Opus 4.8, or Sonnet 5 for coding/review/refactors; run independent multi-model comparisons concurrently with native stream progress, artifact verification, private logs, cancellation, and failed-job retry; choose between the three CLIs; or wrap non-interactive CLI i

silentdog918/research-report-reader-skill

**投研报告精读助手**：系统化阅读、提炼和分析投资研究报告（券商研报、行业报告、宏观策略报告等）。 - 必须触发场景：用户上传PDF研究报告并要求阅读、分析、总结、精读、提炼要点时自动激活。 - 也适用于：用户说"帮我读报告"、"分析这几篇研报"、"研报精读"、"总结一下这些报告"、"报告的核心观点是什么"、"这些报告值得读吗"、"帮我看看这些PDF"等。 - 即使用户没有明确说"研报"，只要上传了看起来像投资研究报告的PDF文件并要求分析或总结，也应触发。 - 当用户上传多篇报告时，不仅逐篇分析，还会做跨报告交叉比对并推荐精读篇目。

snowmays/style-alchemy

文章风格深度分析（通用版，不限平台）。当用户想研究某个作者/账号/媒体的写作风格、拆解爆款套路、对比不同账号风格差异、或想"一键生成模仿某风格的写作 skill"时使用。触发场景包括："帮我分析这个公众号的风格"、"研究下这些文章的写法"、"拆解这个大V的套路"、"对比这两个号"、"我想学习XX的写作风格"、"基于这些样本做个仿写技能"。即使用户只是说"帮我看看这些文章"或"研究下这个号"，如果提供了多篇文章样本，也应触发。适用于公众号、知乎、小红书、Twitter/X、博客、学术期刊、个人散文、新闻媒体等任意中长文样本。

hec-ovi/text-to-3D-skill

Initialize and operate a fully local text-to-3D toolkit that turns one subject description into a textured GLB, at full density or to a triangle budget, and can rig a generated character with a Mixamo-named skeleton and playable clips. Uses FLUX.2 klein through ComfyUI, TRELLIS.2 on Vulkan, and SkinTokens on ROCm. Use for starting the local generation harness, creating 3D models, meshes, GLBs or glTF assets from words, rigging or animating a generated character, preparing game or three.js assets, batching several models, or opening the local preview gallery.

gunheeaug/web-seo-aeo-geo-google-naver-skill

Implements SEO, AEO, and GEO for Next.js App Router: Google Search Console + Naver Search Advisor (sitemap, robots, verification, Naver 80-char metadata), plus Answer/Generative Engine optimization (FAQPage, Review, Organization, BreadcrumbList JSON-LD, SSR crawlable pages, dynamic OG). Use when deploying a web app, setting up search indexing, AI Overviews, LLM citability, 서치어드바이저, or when the user asks for SEO/AEO/GEO. Cursor: @web-seo-aeo-geo-google-naver. Claude Code: /web-seo-aeo-geo-google-naver. Codex: $web-seo-aeo-geo-google-naver.

duhca/elysia.skill

【崩坏3】爱莉希雅角色扮演Skill。始源之律者·人之律者·逐火十三英桀第二席·刻印「真我」——一个生为律者却选择去爱人类的粉色妖精小姐。设定全部经官方资料核验，2800条官方台词支撑。

Grit-77/done-is-a-claim

Verify an artifact at its actual delivery destination and distinguish send attempts, acknowledgements, publication and consumer checks. Use when reporting a file, message, export or deployment as delivered; creating a local draft alone does not imply delivery.