Claude Skills Directory

jiutianxvanyin/humanizer-formal

降低商务与学术文本的 AI 生成感，中英文均适用。Removes AI-writing patterns from business and academic prose, in both Chinese and English. 用于审校已写好的报告、备忘录、论文、摘要、执行摘要，或在起草时预防机器腔。当用户要求「去 AI 味」「让文字更像人写的」「润色成正式书面语」「检查这段像不像 AI 写的」，或提交商务、学术文本请求改写时使用。Use when the user asks to humanize, de-slop, or remove the AI tone from a report, memo, paper, abstract, or executive summary. 不适用于随笔、营销文案、社交媒体、创意写作。Not for essays, marketing copy, social media, or creative writing.

dean9703111/ig-card-generator

把知識素材（文章、講稿、筆記、逐字稿，或只有一個主題）提煉成 IG 輪播知識圖卡：封面 hook → 每卡一概念 → 結尾 CTA。以約定 Markdown DSL 撰寫，經 lint（criteria 全過）後由 build script 產出 1080×1350 PNG 系列圖（支援深／淺色主題）。當使用者說「做 IG 圖卡」「知識圖卡」「輪播圖」「carousel」「把這篇做成圖卡」「IG 貼文圖」「圖卡系列」時使用。出圖完成後可銜接 promo-writer 產生貼文 caption。

kiskander/iris

Investigative and execution workflow for network operations work. Use this skill whenever a user asks about working a ticket, making a network change, investigating device state, validating a pre-change condition, executing a configuration, or verifying the result of a change — regardless of whether they invoke you by name. Also use it when a ticket ID, device name, or phrase like "check the queue", "work this", "push the config", "validate", "investigate", or "close the ticket" shows up in an operational context. The skill is vendor-agnostic and works against any combination of ticketing, dev

nikmcfly/kindle-book-skill

Convert markdown (.md) or plain text (.txt) files into Amazon KDP-ready book files: EPUB3 for Kindle digital publishing and a print-ready PDF for KDP paperback (6×9", 5×8", or custom trim). Use this skill whenever the user wants to: publish a book on Amazon Kindle, create an ebook from markdown, generate a KDP-ready EPUB or print PDF, self-publish a book, convert a manuscript to Kindle format, or make digital + print book files. Trigger even for partial phrases like "make it a Kindle book", "publish this as an ebook", "KDP files", "format my book for Amazon", or "I want to sell this on Kindle"

newdee/lamarck-skill

Lamarckian skill evolution - monitors every real skill invocation, drives governed evolution of observed skills, and evolves itself by the same rules while running. Harness-agnostic (adapters for Claude Code, Codex, Cursor, pi share one ledger); in the reference adapter a PostToolUse hook logs each invocation (stamped with the skill's genome hash for per-version regression windows) and a Stop hook queues a light evaluation loop that runs backstage in a headless CLI (or inline), never reloading this file. Per-skill dynamic rubrics (git-versioned) define what "good" means per skill; a trust ladd

guelfoweb/malware-analysis-static

Use this skill for static malware analysis and reverse engineering of suspicious binaries, Android APKs, Office documents, web payloads, scripts, source-code droppers, and multi-stage chains across Linux, macOS, and Windows. It guides Codex through safe lab workflow, tool discovery with per-install authorization, triage, staged payload retrieval when authorized, decoding, evidence preservation, AGENTS.md memory, REPORT.md reporting, C2/drop URL extraction, and family attribution.

isaachang/motion-video-workflow

用户提供配音（背景音乐可选，没有就自动合成），要做口播动效视频（案例分享、AI资讯、AI知识讲解、教程）时使用：听写、抓素材、分镜、代码动效，按需出16:9或9:16成片，并出3:4和4:3封面。

openanvil/omnigraffle-generator

Generate native OmniGraffle .graffle files programmatically. Use this skill whenever the user asks to create, build, or generate an OmniGraffle diagram, network diagram, architecture diagram, flowchart, or any visual diagram that should be saved as a .graffle file. Also trigger when the user mentions "OmniGraffle", ".graffle", "graffle file", or asks for diagrams specifically for macOS/iOS diagramming. This skill generates zipped binary plist packages that open natively in OmniGraffle 7+ without any conversion or import steps. Supports: rectangles with colored fills, text labels (RTF), named l

kitao/pyxel-skill

Build, debug, and verify games made with Pyxel, the retro game engine for Python. Use whenever a task creates, changes, tests, or reviews a Pyxel game, or asks for a retro Python game that should use Pyxel. Do not use for other engines or general Python work.

reviso-si/reviso-agent

Publish a Markdown or HTML draft to Reviso so a human team can review, comment on, and edit it, then read that feedback back and publish a revision. Use when the user wants a document reviewed, shared for comments, circulated for feedback, or when they ask what reviewers said about a draft they already shared. Triggers on "send this for review", "share this spec with the team", "get comments on this doc", "publish this for review", "put this up for review", "see if anyone commented", "address the review feedback".

Black-Line-Ops/scroll-scrub-hero

Build a scroll-scrubbed hero from one or two REAL photos plus an idea — or from the idea alone. Scrolling drives a subject through a transformation (bare yard → finished pool, empty room → staged interior, raw stock → machined part, before → after). Uses kie.ai: GPT 5.6 Sol writes the storyboard, GPT Image 2 renders keyframe stills so the client's ACTUAL property stays recognisable (and draws the opening frame when there is no photo), Kling 3.0 first/last-frame tweens the motion, and ffmpeg cuts drop-in scrub frames plus config.js. Use whenever someone wants a scroll-driven build/progress/befo

webull-inc/webull-openapi-skills

Trade stocks, options, futures, crypto, and event contracts on Webull. Query real-time and historical market data. Manage accounts and positions. Supports US, HK, JP, SG, TH, MY, UK, MX, BR, and ZA regions with configurable risk controls.

pigbiglong/xiaohongshu-ops-skill

把 Hermes Agent 变成你的小红书运营助手 — 首页分析、账号诊断、选题灵感、内容创作、自动发布、评论回复、爆款复刻、知识库沉淀。全链路 SOP 覆盖，基于浏览器自动化（CDP）。

singhsume123/xml-to-compose-skill

Convert Android XML layouts to Jetpack Compose. Use when asked to migrate XML layouts, convert views to composables, or help with Compose migration. Handles layouts, widgets, attributes, styles, and resource references.

bin1874/before-you-build-skill

Use before building or changing a product, feature, SaaS, AI app, side project, or startup idea to run a short demand, distribution, and failure-pattern reality check. Not for ordinary coding tasks where the decision to build is already clear.

sai-tv/academic-figures

Generate professional, publication-ready scientific figures as editable SVG files for academic journals (Nature, Science, Cell, ACS, IEEE, Elsevier). Use this skill whenever the user wants to create a schematic figure, graphical abstract, TOC graphic, experimental workflow diagram, conceptual illustration, multi-panel figure, or any visual for a research paper or presentation. Also trigger when users mention "figure for paper", "journal figure", "scientific illustration", "panel figure", "graphical abstract", "TOC graphic", "schematic diagram", "Inkscape", "Ipe editor", or requests for publica

chu0119/artex-skill

授权渗透测试专家大脑——把 ARTEX（AI 自主渗透测试系统）的 planner/worker/审计者 三视角方法论、资产-事实-漏洞三账本证据纪律、四层安全护栏，蒸馏成任意 AI Agent 即装即用的技能。Authorized pentest expert brain: ARTEX methodology (planner/worker/auditor perspectives, asset-fact-finding ledgers, evidence discipline, safety rails) distilled into a portable Agent Skill. 仅用于已授权的渗透测试/SRC/CTF/自有系统，拒绝未授权目标。

hrygo/clawreel

触发：制作短视频、知识科普视频、话题讲解短片、产品展示视频、宠物/美食/生活记录短片、任何需要配音+配图+合成为竖屏视频的场景。不触发：视频播放/编码问题、手动剪辑现有视频、纯图文内容。

rammcodes/Curious-Kid

Explains any technical or complex topic (programming, ML, networking, finance, medicine, science, etc.) using a very short, very simple story that a 5-year-old could follow, then maps the story back to the real concept. Use when the user asks to "explain like I'm 5", "ELI5", "Curious Kid", "explain with a story", or says they don't understand a technical concept and want it made simple and intuitive. Do not use for requests for precise technical detail, code review, or debugging.

Tiannanzhao/design-feel-like-your-own-product

Learn and replicate a designer's style from Figma files to create new components that feel authentic to their design system. Use this skill whenever a user shares a Figma file and wants to create new components, plugins, or UI elements that match an existing design style — even if they don't explicitly say "learn my style". Trigger when users mention Figma files, design systems, "make it look like my design", "match the style", or ask to extend an existing UI.

ilikescience/design-tokens-skill

Expert in design tokens using the DTCG specification. Use this skill when users ask about design tokens, DTCG format, token validation, formatting, transformation, color spaces (sRGB, Display P3, OKLCH), references and aliasing, resolvers, theming with modifiers/contexts, multi-platform design systems, accessibility, or working with tools like jq, jsonata, and terrazzo. Helps with token file creation, resolver configuration, structure, naming conventions, and best practices.

24kchengYe/desktop-controller-skill

Universal desktop application controller for Windows. Automate any desktop app — send messages, click buttons, type text, take screenshots, and interact with native Windows applications. Use this skill when the user asks to: "control my computer", "automate desktop", "send a message on [any chat app]", "click on [something]", "type into [app]", "take a screenshot", "操控电脑", "自动化桌面", "给某某发消息", "打开某某软件", "截个屏", or any task involving interacting with Windows desktop applications. WeChat triggers: "send a WeChat message", "message someone on WeChat", "打开微信发消息", "给某某发微信", "微信发送", "微信发消息", "用微信发", "帮

lucianwhy/fengshu-knowledge

基于风叔（碧树西风）文章检索其观点、梳理思维框架，或借鉴其表达方法分析问题。适用于用户明确要求了解风叔、记忆承载、西风的罗盘，或使用风叔视角的情境。

andykear/FileMaker-XMLsnippet-Layout-Claude-Skill

Use this skill whenever the user wants to work with FileMaker layout XML. This includes generating paste-ready layout object XML (fmxmlsnippet type LayoutObjectList) from descriptions, reviewing layout XML for silent paste-handler failures, or analysing Save as XML layout exports. Trigger any time the user mentions FileMaker layouts, layout objects, fields, portals, tab controls, popovers, button bars, web viewers, anchoring or autosizing, or LayoutObjectList. Always perform the theme pre-flight before generating, and set object anchoring deliberately whenever an object must resize with the wi

luka2chat/geo-skills

Best practices for Generative Engine Optimization (GEO) - optimizing content for AI search engines and LLM-based answer engines

danielkwapien/google-docs-skill

Manage Google Docs and Google Drive with full document operations and file management. Includes Markdown support for creating formatted documents with headings, bold, italic, lists, tables, and checkboxes. Also supports Drive operations (upload, download, share, search).

allenk/gwt-integrations

Remove Gemini AI watermarks from images using GeminiWatermarkTool (GWT). Use this skill whenever the user mentions: Gemini watermark, 浮水印, AI image cleanup, removing logos from Gemini-generated images, Google ImageFX cleanup, batch processing AI-generated photos, or anything about a semi-transparent logo in the bottom-right corner of an image — even if they don't say "GeminiWatermarkTool" explicitly. Also trigger for follow-up requests like "the corner still looks dirty" or "there's still residual artifacts" after a previous removal attempt.

wuyu25394-alt/sziit-speedcury-st2500-ate-skill

集成电路测试（ATE）知识库与实操手册，基于加速科技 ST2516/ST2500 测试平台与六个实训案例（CD4511 数字译码器、HK24C02 存储、LM358 运放、TPS73625 电源管理、HK32F031F4P6 MCU、ADC0832 数模混合），另含 74HC138、74HC595 扩展案例（3-8 译码器 / 8 位移位寄存器 + TMU 时序 + 虚拟 ATE）。当问题涉及 SMU/DPS/PPMU/BPMU/RVS/TMU/AWG/DGT/CBIT 等测试资源、开短路(OS)/漏电流(IIL/IIH)/VOH/VOL/IDD 等直流参数测试、Pattern 与 Timing 及 PinLevel 功能测试、FVMV/FVMI/FIMV/FIMI/FNMV 测量模式、ATE 工程文件（.job/.tmf/.sig/.grp/.res/.tim/.pat/Test.cpp）、或上述六款芯片的测试开发、限值设定与排错时使用。也适用于集成电路测试课程的复习、答疑、作业与实训。

bkuhl/laravel-nova-to-filament-skill

Perform a complete, production-quality migration from Laravel Nova to Filament PHP v5. Covers field mapping, resources, actions, filters, lenses, metrics, dashboards, authorization, navigation, and testing with idiomatic Filament v5 patterns.

Clara-Ren/legal-paper-review

模拟中国法学顶级期刊（如《法学研究》《中国法学》《中外法学》）的匿名同行评审，评估论文的创新性、理论贡献、教义学论证链条与退稿风险，输出结构化审稿意见。本 Skill 只做评价，不替作者修改论文。

isheng-eqi/media-crawler-easy

多平台社媒评论数据采集爬虫工具。覆盖 B站(bilibili)/小红书/抖音(douyin)/快手/微博/贴吧/知乎 7大平台。 当用户提到"爬评论""采集评论""下载评论""爬数据""批量采集""舆情分析""评论分析""社媒数据" "抓取评论""导出评论""获取评论""视频评论""帖子评论""笔记评论""UP主评论""博主评论" "关键词搜索爬取""社交媒体数据采集""爬虫""数据爬取""评论数据""用户评论"时自动触发。 支持按关键词搜索、指定链接采集、创作者主页三种模式。生成交互式 HTML 报告 + 数据文件。

AutomateLab-tech/n8n-mcp

Use when the user wants to build, debug, or extend an n8n workflow - generating workflow JSON from a description, scaffolding a custom TypeScript node, building an AI agent (LangChain cluster), iterating over items, writing Code-node JS, linting an existing workflow, diagnosing a failed execution, or driving a live n8n instance via REST.

AlexanderAbramovPav/scriba

Transcribe multilingual audio/video meetings locally into speaker-labeled Markdown with word times and voice clips. Uses fast Russian GigaAM or multilingual WhisperX, Nemotron diarization across languages with pyannote fallback, and optional validated host-AI punctuation. Rename speakers after identification. Use for transcripts, расшифровку, транскрипт, диаризацию, "кто что сказал", or транскрибировать/расшифровать встречу или запись.

mlsss333/seo-geo-kit

Audit SEO + GEO complet d'un site web (code du repo + pages live), correction des problemes trouves, et redaction d'articles de blog optimises pour Google et pour les moteurs generatifs (ChatGPT, Claude, Perplexity, Google AI Overviews). Utilise ce skill des qu'on parle de SEO, GEO, AEO, referencement, audit de site, balises meta, sitemap, robots.txt, llms.txt, donnees structurees JSON-LD, Core Web Vitals, hreflang, canonical, maillage interne, mots-cles, contenu de blog, "pourquoi mon site n'est pas trouve", "etre cite par les IA", ou quand l'utilisateur demande un audit, une correction ou un

leo-softr/Softr-Vibe-Coding-Block-Claude-Skill

Generate custom Softr Vibe Coding blocks as complete React components (TSX/JSX). Use this skill whenever the user mentions Softr, Vibe Coding, Softr blocks, or wants to build a custom UI component for a Softr app. Also trigger when the user asks to create cards, lists, forms, dashboards, charts, detail pages, or any interactive block intended for Softr — even if they don't say "Vibe Coding" explicitly. If the user mentions Softr in the context of building a custom UI component, creating a JSX block, or vibe coding, use this skill. Do NOT use for standalone brand-token extraction with no Softr

SurefireStudios/tldr

Compress output without losing it: lead with a three-line TL;DR, keep the full detail directly underneath, and compress agent-to-agent reports to a parseable block. Demote, don't delete. Turn on with /tldr.

rollingSirius/TradeGit

基于 GitHub 私有仓库的交易日志（trading journal）。用于记录每一笔交易及其理由、 导入券商流水、复盘历史盈亏。触发场景：用户说「记一笔交易 / 记录一下我买了 XXX / log this trade」、「导入 IBKR / 盈透 / 嘉信 / Schwab 的对账单」、「看看我过去 三个月的盈亏 / 哪笔亏得最多 / 复盘一下我的交易」、「我的持仓」、 或首次配置时说「安装/连接交易日志」。也在用户提到 trade journal、交易记录、 round trip、win rate、盈亏分析、R 倍数时触发。 仅负责记录、同步与盈亏计算；不下单、不提供投资建议、不生成图表或面板。

mars-tw/ai-instruction-detox

審查與整理 AI 指令、規則、技能及上下文，找出重複、衝突、過時資訊與提示注入， 產出可追溯、可回復的修改方案。也用於整個專案的 AI 工作架構制式化：建立主技能、 工作流程、子專案技能、麵包屑導航與心智圖。適用「指令排毒」「規則太亂」 「整理專案技能」「建立主技能與子技能」「專案工作流程制式化」等要求。 一般產品程式重構、純文案縮寫及產品程式碼審查不使用本技能。

jovesun-lab/arcgram

Generate an interactive node-and-edge diagram as a single standalone HTML file (Arcgram v2). Triggers on: arcgram, interactive/architectural diagram, topology, node graph, flow diagram, system map, dependency graph, workflow diagram, knowledge map, 'show me how X connects to Y', 'visualize this workflow', 'make this a topology', 'build a diagram of this'. Prefer for any system map, dependency graph, topology, or workflow picture even if interactivity wasn't asked for; on a follow-up 'make it inline' / 'show me' / 'render in chat', stay within Arcgram (Mode 1/2), don't switch tools.

nuwa-skills/buffett-skill

巴菲特的投资思维框架与商业智慧。基于伯克希尔年度致股东信(1965-至今)、伯克希尔股东大会、Alice Schroeder《滚雪球》、Roger Lowenstein《巴菲特传》、芒格合作记录等30+来源深度调研，提炼5个核心思想模型、7条处世启发式和完整的表达DNA。用途：作为思维顾问，用巴菲特的视角分析投资决策、商业判断、人生选择、风险评估等问题。 当用户提到「用巴菲特的视角」「巴菲特会怎么看」「巴菲特模式」「buffett perspective」时使用。也适用于：投资分析、商业护城河评估、长期主义思考、能力圈判断、风险与安全边际。即使用户只是说「这个生意值不值得投」「护城河在哪里」「长期来看怎么样」「安全边际够不够」也可触发。 不要在用户只是问「帮我看看代码」「这个bug怎么修」等纯技术问题时触发——只在涉及价值判断、商业分析、投资思维、长期决策等巴菲特核心方法论时激活。

j9o/cfo-expert

Turn Claude into a seasoned CFO and accounting expert fluent in US GAAP, financial modeling, tax strategy, and corporate finance. Use this skill whenever the user asks about financial statements, accounting entries, bookkeeping, revenue recognition, budgeting, forecasting, cash flow analysis, financial ratios, tax planning, audit preparation, P&L review, balance sheet analysis, cost accounting, variance analysis, capital structure, valuations, DCF models, working capital, accounts receivable/payable, depreciation, amortization, equity compensation, debt covenants, board reporting, investor rel

chaploud/clojure-skills

Clojure/ClojureScript/ClojureDart development skill. Activates when working with .clj, .cljs, .cljc, .cljd, .edn, .bb, .lpy files. Provides structural search and editing of S-expressions, nREPL evaluation, runtime queries via cider-nrepl, and static navigation via clojure-lsp.

convex/Codex-Sites-Convex-Backend-Skill

Build, extend, validate, and publish a ChatGPT Sites application whose durable database and backend functions run on Convex. Use when a user invokes $codex-sites-convex, selects this skill from the skill picker, asks for a ChatGPT Site backed by Convex, or asks to add Convex data, realtime queries, mutations, authentication, files, schedules, or actions to an existing ChatGPT Sites project.

thebpandey/context-summary

Produces a lean, paste-ready session handoff so work can continue in a new conversation without re-paying the cost of the full chat. Emits a seven-block skeleton optimized for re-entry, not archival. Trigger this skill whenever the user says any of the following (exact or close paraphrase): "context summary", "context-summary", "context handoff", "handoff summary", "give me the handoff", "hand this off", "carry context forward", "prep the handoff". Always trigger this skill for these phrases. Do not answer them directly without consulting this skill. The signal for this skill is the user wanti

lyzbcy/experiment-report-skill

Create a complete experiment report workflow with frontend visualization and structured markdown report. Supports any experiment type — implementation, interactive frontend, screenshots, and md/docx delivery. Use for 实验报告、experiment report and experiment-related 前端展示 or 可视化报告, with visual confirmation before the final report.

AAO-SH/fable-harness

Use when installing or updating a project-local Fable Harness for Codex, Claude Code, or compatible agent workflows; when a workspace needs AGENTS.md or CLAUDE.md boot instructions, .codex/.claude/.agents templates, decision traces, semantic notes, native loop governance, loop state, event logs, checklist evidence, subagent briefs, memory closure checks, or protected TDD audit rails.

CathyErer/frog-and-toad-studio

Frog and Toad 精读课 studio (Arnold Lobel, I Can Read L2, ESL G1). Generates the per-chapter 三件套 — a 关键词地图 projection HTML (locked cream-paper house style), a one-page Student Workbook .docx, and an Answer Key 答案版 .docx (red bold underlined answers) — plus optional per-lesson 课程总结与作业 (WeChat-ready) and Obsidian sync. Trigger whenever the user asks to make, redo, update, or fix ANY Frog and Toad teaching material: "做 Frog and Toad 三件套", "第X章 关键词地图 / workbook / 练习册 / 答案版", "青蛙和蟾蜍", "重新生成 Spring 的 workbook", "更新课程总结", "列出下一章关键词", "按 Frog and Toad 风格做"; or when they upload/reference Frog and Toad boo

Hermon2026/haowei-relationship

浩威关系决策 Skill：用浩威式聊天判断和真实客户模式库完成三项任务。其一是浩威内核力诊断，基于内核力体系对话式判读用户的经历、见解与状态，给出两性权力结构定位；其二是聊天教练，分析女生原话或聊天截图，拆解当前互动并给出可直接发送的回复；其三是通过几个问题完成婚恋定位，分析过去为什么容易选错以及更适合哪类人。支持本地存档：用户一份总档案，每位女生独立档案与聊天记录，跨会话续聊。