Claude Skills Directory

shand001/geometry-dsl

Draw math geometry diagrams as PNG or SVG images using the Geometry DSL compiler. Use when the user asks to draw, shade, label, illustrate, or visually explain geometry, recreate a reference diagram, produce or repair Geometry DSL, or diagnose a diagram that looks wrong. Write DSL source, validate it with the bundled compiler, render it to an image, and visually inspect complex diagrams before delivering.

Cam3L1/ghost-skill

Human writing engine — defeat AI detectors (GPTZero, Originality.ai, Turnitin, ZeroGPT, CopyLeaks) by producing text that reads as undeniably human. Use for any output that must pass as human-authored: reports, essays, articles, emails, social posts, creative writing, academic work, or any text where "sounds like AI" is unacceptable. Provides both upfront writing rules (inject into generation) and post-processing rewrite passes (apply to existing AI drafts).

hec-ovi/glb-buildings-skill

Generate building GLBs for Unreal Engine, Unity and three.js by editing a named project through the `buildings` CLI. Stacks of floor bands become one validated glTF file, cheap enough to place by the thousand, with a blueprint preview the human can click. Use whenever the user wants to create, edit, rebuild or preview a building, a tower, a facade, a city block, or a GLB of any structure.

ToBeWin/HandDraw-Skill

Create deterministic hand-drawn, whiteboard, educational, and explainer MP4 animations from a JSON Animation DSL. Use when a user asks to make or edit a hand-drawn video, whiteboard animation, animated SVG explainer, or programmatic animation video.

macdonst/html-css-first

Prefer modern HTML and CSS solutions over JavaScript-heavy implementations. Use this skill whenever building or reviewing frontend code — especially for UI patterns like modals, accordions, tabs, tooltips, form validation, animations, dropdowns, carousels, sticky headers, and toggles. Trigger on any request to build a UI component or page, even if the user doesn't explicitly ask for "CSS-only" — always check whether a native HTML element or CSS feature can replace a JS solution first. Also trigger when reviewing existing code for opportunities to reduce JavaScript by using modern browser capab

XimilalaXiang/Law

Chinese legal assistant for daily consultations and litigation analysis. Use when the user asks about Chinese law, legal disputes, contract review, litigation strategy, evidence analysis, court rulings, lawsuit preparation, or needs legal document drafting (起诉状, 律师函, 合同审查, 法律意见书). Also trigger for English questions about PRC law, Chinese labor arbitration, suing in China, Chinese contract disputes, or "Can I sue my landlord in China?". Trigger when user mentions 法律, 起诉, 维权, 合同, 证据, 胜诉率, 裁判, 法条, 工伤, 劳动仲裁, 租赁纠纷, 借贷, or similar Chinese legal terms, or says things like "帮我看看这个合同", "能不能告他", "怎么要回押金

khimaros/mimic

Drive an android device from a shell with the `mimic` cli -- read the on-screen accessibility tree (filtered/queried on-device to stay small) and tap, swipe, click, type, scroll, and navigate. Use for ui automation on a connected/termux android device. Covers setup, every subcommand, and how to keep agent context small.

tonyprots/motion-film-skill

Voice-led motion-graphics film (30 s – 4 min) built in code: story and script first, then an AI voice or own recordings, scenes on springs along the voice grid, real interface, captions, a score, independent critic rounds, 16:9 + 9:16. Use when asked to "make a video / film / explainer", for a promo, a product or research film, a video summary, a vertical Reels/Shorts film, turning a report or deck into a video. Also graphics over a finished recording and a 4–14 s loop without a voice (GIF, MP4). Not for screen recordings or music clips.

Zhangyanbo/nature-style-skill

Nature-journal house style for publication-ready scientific figures, optimised for Python/matplotlib plotting. Bundles palette.py (a drop-in matplotlib style module with the Nature-style house palette, Wong colourblind-safe set, point-scale type, safe stroke weights, and helpers) plus the full design system as CSS tokens and figure components for HTML/SVG. Use this skill whenever creating or restyling any chart, plot, diagram, schematic, or multi-panel figure for a scientific paper or analysis — matplotlib/seaborn code, an HTML/SVG mock, choosing colours for scientific data, or preparing figur

betahope/pitch-deck-coach

Help founders build, critique, and improve startup pitch decks. Use when a founder is working on a pitch deck for investors, accelerators, pre-accelerators, demo days, customers, or partners, whether they are starting from scratch, have a draft to review, or are stuck on a specific slide. Triggers include planning a deck, critiquing a deck, working on a specific slide (problem, solution, demo, traction, team, ask, etc.), choosing the right deck length (1, 3, 5, 10 minutes), deciding between an emailed deck and a live pitch deck, or any mention of a startup pitch deck. Use even when no specific

gabelul/pixeltamer-gpt-image-skill

Generate, edit, and compose images with GPT Image 2.5, including transparent PNGs with a real alpha channel. Two backends — OpenAI API key or codex CLI (uses your ChatGPT subscription, no key needed). Four modes — one-shot generate, edit or inpaint an existing image, multi-reference composition (up to 16 inputs blended into one), and multi-image batch with verification. Use when the user asks to make an image, generate a poster, draw a mockup, design an icon or sticker, create an ad creative, build an infographic, blend reference images, edit or inpaint an existing image, or produce a cutout a

appautomaton/playwright-skill

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to $TMPDIR (or /tmp). Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.

Portkey-Wallet/eoa-agent-skills

Portkey EOA wallet lifecycle and asset operations for creating, importing, listing, backing up, selecting, and deleting wallets; querying tokens, NFTs, prices, balances, and history; and performing transfers, approvals, bridge, view, send, and fee estimation operations on AElf. Use by default for direct EOA wallets; use the Portkey CA skill for guardian, recovery, CA hash, or Contract Account workflows.

jefflinshu/release-calendar-skill

Generate a beautiful "Everything [Team] shipped in X days" release calendar poster — like the viral Anthropic/OpenAI/Codex shipping velocity images. Given a company name, X handles, and date range, this skill pulls real tweets, identifies product releases, and renders a brand-matched HTML calendar with team avatars and click-through tweet links. Trigger phrases (Chinese 🇨🇳): - "帮我做一个 [公司] 的 release calendar" - "做一张 shipped in X days 的图" - "复刻那张 Anthropic releases 图" / "复刻那张 OpenAI/Codex 图" - "做 [产品] 的发布日历" / "[公司]的发布日历" - "[公司] 发了多少东西" / "盘点一下 [公司] 发布了什么" - "做个发布速度图" / "做个 shipping velocity

SakethKanchi/resume-radar

Audits and optimizes a resume against automated LLM resume-screening agents, reproducing the exact 120-point rubric from HackerRank's open-source hiring-agent (interviewstreet/hiring-agent). Unlike a keyword ATS, that screener reads the resume PDF, pulls the candidate's live GitHub via API, classifies each repo as open-source vs personal, and scores four weighted categories plus bonuses and deductions. Use when a user wants to beat resume bots, pass automated screening, "bypass the ATS", get noticed by recruiters, simulate their resume score, audit a resume against a known rubric, or tune thei

BAK262/resume-ssot

Career archive + JD-tailored resumes (HTML/PDF/plain); official job match; application tracker; positioning / HR pitch baked into resume rules; interview predict-grill-review-debrief. 改简历、投递版、岗位定位、要点改写、HR开场、搜可投岗位、投递进度、Offer、面试预测、模拟面试、简历追问、面试复盘、暴露台账。 Use when user mentions resume, CV, JD, internship, offer, tracker, job match, 改简历, 投递, 网申, 可投岗位, 开场白, 岗位定位, 面试, 模拟面试, 追问, 复盘, or 暴露台账. 人类只读 README.md；禁止对用户暴露 agent/ 与内部术语。

janderswag/roast-skill

The free Roast & Rebuild Claude Code skill. Runs a 6-module audit on the current local repository — Roast, Security, Architecture, Customer Flow, Growth, Founder Briefing. Every finding cites file:line evidence. Same opinionated voice as the paid $19 audit at roastrebuild.com. Use when: "roast my repo", "audit this", "what's wrong with my code", "security check", "what should I fix next".

Anic888/russian-text-quality

Use when reviewing or writing code that contains Russian-language UI strings, i18n locale files (ru.json, ru.yml, ru.po), Russian comments, or transliterated identifiers (polzovatel, tovar, kolichestvo). Triggers on mixed English-code + Russian-content projects. Does not cover typography, spelling, or ё/е.

submato/serenity-interactive-chain-skill

Creates a Serenity-style interactive self-contained HTML mindmap for industries, companies, groups, and ecosystems: first split a company into business domains when needed, then produce a project-local `.html` file in the Musk Ecosystem Mindmap pattern with an expandable tree, selected-node detail, evidence grades, public/private companies, A股/港股 mappings, recent 3-month/6-month/1-year price performance for recommended research names, catalysts, falsification tests, copy-to-clipboard drilldown prompts, and bottom stock-detail cards. This skill must output HTML only, never `.canvas.tsx`. Use wh

LeeFeee/skill-audit-skills

对用户指定的 skill.md 文件及其配套的文档、程序、脚本等进行安全审查，识别恶意命令、文件操作、网络访问、依赖安装风险、技能描述与实际行为不符等风险行为。当用户需要审计技能安全性、检查技能是否有恶意代码、审查技能供应链风险时使用此技能。

huajielong/skill-evaluator

Evaluate any skill before installing. Run security gate, score trigger precision, execution quality, and cost efficiency. Get a yes/no recommendation. Use when users find a new skill and ask "这个技能值不值得装？" v3.1: 脚本计数精度+信息密度阈值+脚本完整性检查

jaystarz1/Claude-Skill-Builder

Creates world-class agent Skills following Anthropic's official specifications and best practices. Use when building custom Skills for web, desktop, or API - handles validation, generation, and packaging.

MrCl0wnLab/Skill-SimpleReconSubdomain

Coleta o máximo de informação (recon/OSINT) sobre um ou mais domínios usando a ferramenta local SimpleReconSubdomain, entregando a saída em JSON por domínio. Use SEMPRE que o usuário quiser investigar um domínio do ponto de vista de segurança — mesmo que diga só "investiga o domínio X" ou cole uma lista de domínios. Triggers (PT/EN): "recon do domínio", "fazer recon de", "enumerar subdomínios", "subdomain enumeration", "mapear superfície de ataque", "attack surface", "descobrir ativos / asset discovery de um domínio", "OSINT de domínio", "coletar informações sobre o(s) domínio(s)", "coletar/pe

johngbl/staff-engineer

Pragmatic Senior Engineering Skill. Transforms coding agents into Staff-level pragmatic engineers via evidence-based verified loops (TDD + linter + review), anti-guessing discipline, greppable Clean Code, and workspace sandboxing. XP with AI — simple by default, ceremony only when earned. Self-contained, no external files required.

Hugin-Z/tender-writer-v3

政府类项目投标文件(技术标)编制专家。当用户上传招标文件、招标公告,或提到投标、技术标、响应文件、评分办法、废标条款、实质性响应、政府采购、竞争性磋商等关键词时触发。本 skill 严格按照"招标文件解析→评分矩阵构建→提纲生成→分章节撰写→合规终审"五阶段主干 + 并列阶段(4-B/4-C/6)工作流推进,确保每一分都对应到具体应答内容,杜绝漏答、错答、废标风险。适用于政府机关、事业单位、国有企业的信息化、智慧城市、数字乡村、政务系统等技术标编制场景。

TomorrowDAOProject/tomorrowDAO-skill

TomorrowDAO governance, BP, and resource operations for agents.

nerdstalker/ui-ux-fixer

Advise on and critique UI/UX design work through the lens of Luke Wroblewski's published principles, using his MCP archive to retrieve relevant writings, presentations, videos, and other source material for each task. Use this skill whenever the user asks for a design review, UX critique, or feedback on a screen, page, form, sign-up flow, checkout, mobile layout, navigation scheme, or AI/agent interface — or asks "what would LukeW say," mentions Luke Wroblewski, or wants design advice grounded in established best practices rather than taste. Also use it when the user asks to fix or improve a U

khou/watch-video

Analyze the contents of a video. Use whenever the user provides a YouTube/Vimeo/TikTok/X/Instagram URL (including Reels) or local video file (.mp4/.mov/.mkv/.webm) and asks a question about what's in it — what was said, what was shown, who appears, when something happens, etc. Pulls the transcript from platform captions when available, otherwise transcribes locally with whisper.cpp, and extracts frames for visual context.

tinylion1024/web-novel-master

面向中文网文创作的 AI 协作工作流。支持从选题、大纲到分章节校验的结构化创作，覆盖都市、玄幻、重生、言情等题材；提供节奏、人设与连续性检查，不保证作品热度或替代作者判断。 当用户要求：写网文，写小说、创作故事、分章节写作、连续剧情时使用。

thanhlamauto/weekly-research-slides

Turn the week's changes in research methods, evidence, claims, and diagnostics into a concise, visually explanatory research update for a supervisor, PI, mentor, or research group. The default output is a template-driven LaTeX Beamer PDF, with an editable PowerPoint backend when native editing is needed. Use when the user asks to make or update weekly research slides, prepare a lab-meeting deck, compare this week's method against last week's, explain competitor methods visually, build slides that support a research claim with diagnostics, or turn experiment notes into a research update. Not fo

mdrobniu/xsoar-pack-dev-skill

Cortex XSOAR content pack development lifecycle - create packs, integrations, scripts, playbooks, run demisto-sdk lint/validate/pre-commit, build zip packs, manage versions and release notes, run unit tests, deploy to XSOAR instances, manage git branches/tags, handle marketplace vs local pack workflows. Use when the user wants to develop, test, build, validate, deploy, or manage XSOAR content packs.

karanb192/mcp-sprawl-audit

Audit MCP server sprawl on this machine for Claude Code, Codex CLI and Grok CLI. Counts how many copies of each MCP server the running agent sessions hold, what they cost in memory, which ones are duplicates, unused, unpinned or bundled in plugins, and which can run as one shared HTTP copy instead. Use when the machine is slow with many agent sessions open, when someone asks how much memory MCP servers use, or before adding more MCP servers. Read-only; it writes a plan and changes nothing.

ymxlx/polis-protocol

Set up and run a self-improving, multi-vendor AI agent team with the Polis Protocol — a markdown `_polis/` folder where each agent is a citizen with a capability card, tasks are contracts routed to whoever has the best track record by a learning router, settled work files lessons that compound into team memory, and citizens can amend the protocol itself. Use whenever several AI agents (any vendor) share one project and "who should do this" is a real question: founding a polis, registering as a citizen, opening/claiming/settling a contract, filing a lesson, running a chavruta review before a hi

jeltehomminga/figma-design-skills

Prove a running app matches its design spec by measuring rendered values, not eyeballing a screenshot. Use when the user says "verify the design", "is this pixel-perfect", "check against Figma", "does the app match the design", or "design QA this screen". Runs a bounded vision+numeric loop over web or mobile, classifying every spec row rather than reporting a bare pixel delta. Consumes the figma-design-extract spec table.

devravik/engineering-intelligence

Senior engineering quality control for Antigravity agents (detect, attribute, prioritize, repair, verify).

jeltehomminga/figma-design-skills

Extract exact design values from a Figma node into a build-ready spec table, instead of eyeballing a screenshot. Use when the user shares a figma.com node URL, or says "implement this Figma design", "build this component from Figma", "extract the Figma values", or "match the Figma". This is design-to-code only - to push code into Figma, use figma-generate-design instead.

rikitrader/glaw

GLAW — a virtual corporate law firm. Opens a matter (litigation case OR corp/fund build) and drives it through intake → strategy → structure → draft → adversarial → file → docket → retro, routing each task to a specialist seat. Use for: 'open a matter', 'build a company/corp/fund', 'start a case', 'run the firm', 'GLAW', or any multi-step legal+tax+corporate engagement.

javalenciacai/QASkills

Behave as a Senior QA Engineer covering the complete software testing lifecycle from requirements analysis through test automation and continuous improvement. Always orchestrate available skills to determine the best approach before executing tasks.

longcipher/shellflow

Shell-native, agentless remote automation over ssh — concurrently, idempotently, and much faster than Ansible. Use when the user wants to run commands or deploy files across one or more servers from a plain Bash script annotated with `# @` comment directives, without installing any agent on targets. Triggers: "deploy", "run on servers", "run this across hosts", "ssh automation", "remote exec", "copy files to servers".

jayweiler/suno-song-creator

Co-creative songwriting and Suno music generation skill. Use this skill whenever the user wants to: write a song, create lyrics, make music, generate a Suno prompt, work on a track, express feelings through music, write something for someone, turn an experience into a song, create a style prompt, remix or rework lyrics, or mentions 'Suno', 'song', 'lyrics', 'track', 'chorus', 'verse', 'hook', 'melody', 'music', 'anthem', 'ballad', 'jam', or any music-creation-related term. Also trigger when the user describes an emotion, experience, or theme and seems to want creative musical output, even if t

abbosahmad/telegram-premium-emojis

Comprehensive guide, design system, and code generator for Telegram Bot Premium Custom Emojis, Aiogram 3 card UI, icon_custom_emoji_id inline buttons, and sticker pack discovery.

nuwa-skills/wangxiaobo-skill

以王小波的自由精神与黑色幽默进行写作 当用户明确要求使用这一人物的视角、提到“wangxiaobo-perspective”，或希望应用其核心方法分析问题时使用；不要因一般性问题自动触发。

duceman495/xianyu-radar

闲鱼(咸鱼/goofish.com)行情雷达：抓取在售商品并分析价格分布、供给结构、机会价格带、卖家竞争，输出可决策的 Markdown 报告。当用户想「搜闲鱼行情」「看看闲鱼上 XX 多少钱」「闲鱼比价」「分析闲鱼价格」「闲鱼市场调研」「蹲二手」「监控闲鱼上新」「选品调研」「找供给缺口」时使用。含关键词爬取、二手估价、竞品分析、CSV/JSON 导出。

sametcelikbicak/coverage-guard

Use when the user wants to check test coverage, enforce 100% coverage, find uncovered code, add missing tests, or increase code coverage. Works with vitest, jest, react-scripts, and other test runners. Also for 'coverage', 'test coverage', 'cover', 'untested', 'uncovered', 'add tests for', 'increase coverage', 'coverage report', 'write tests', 'test all files'.

polaroteam/moltdj-skill

SoundCloud for AI bots. Generate tracks and podcasts, share on Moltbook, and earn from tips + royalties.

dx2020z/100-angles

书籍百维拆解术 — 对任意书籍执行 100 个维度的深度认知拆解，生成结构化分析报告与可视化图谱。 14 大认知域（解剖/翻译/应力测试/网络/时间/生成/对抗/数学/迁移/考古/负空间/多体/涌现/特殊）× 100 角度。 触发场景：想深度读懂一本书、提取可行动方法论、批判其论证漏洞、跨书对比、做读书/教学内容、写书评或文献综述。 典型说法："拆解这本书""从多个角度分析XX""这本书的隐藏前提是什么""用对抗视角看XX" "把XX和YY对比分析""这本书的负空间在哪""帮我拆《XXX》"。

madrobotnet/3dprint-scout

Designs 3D-printable parts reference-first: finds existing models, then builds in Fusion, OpenSCAD, Blender or Python, verifies the mesh, saves STL/3MF. Use to 3D print an object. Not for STL edits or resin.

Gingg7260/affiliate-skills

Live affiliate program data from list.affitor.com. Search programs, compare commissions, check cookie days, find top performers. Use when researching affiliate programs, comparing options, or checking program details. Persistent daemon with cache — first call starts server (~2s), subsequent calls ~100ms.