Claude Skills Directory

edu-ai-builders/pedagogical-grounding-engine

将一篇或多篇学术论文，通过"教学法约束推理"转化为有理论根基的产品设计产物。 核心是构建"学术机制 → 约束交互 → 可解释推理链"的中间层， 再导出多种格式的设计产物。 本skill是一个 Pedagogical Grounding Engine（教学法落地引擎）： 它不是论文摘要工具，而是把教学法意图（pedagogical intent）编译为 可执行的系统设计结构。PRD、System Prompt、Workflow 都是下游导出格式， 核心产物是 Traceability Map——每个设计决策都有明确的教学依据、 认知机制和可追溯的设计理由。 当用户有以下意图时触发本skill： - "把这篇/这几篇论文做成产品/app/提示词/工作流" - "paper to PRD / paper to prompt / paper to product" - "pedagogical grounding / 教学法落地" - "我想基于学习科学设计这个功能/系统提示词" - "从论文提取知识图谱/三元组/TPACK分析" - "我有几篇论文，帮我提炼成一个设计方案" - "帮我把教学法嵌入到产品/提示词中" - "生成 traceability 图" / "把这篇论文可视化" - "我有一个教学场景/教育想法，帮我设计成系统"（不一定有论文） 支持 Commands 模式：流水线

SilverNine/script-to-guide

Turn a written script and real app screenshots into a narrated product walkthrough. Output is a small static web page (searchable transcript, follow-along mode, embeds with an iframe) or an MP4. Every highlight, zoom and cursor move is cued to a word of the synthesized narration, so editing the script re-times the screen. Use when the user wants a product guide, onboarding walkthrough, feature tutorial or help-center video for a web app, or for any app from screenshots.

zcx960/seedance-storyboard

把剧本/小说/文字脚本/分镜文案，转换成 Seedance（即梦 / 豆包 Doubao Seedance）文生视频用的分镜脚本——带「视觉基调 + 色彩与调影 + 情绪基调」全局头，再加按秒切分的「分镜1、分镜2…」逐镜运镜与动作描写。只要用户给一段剧情/动作/场景文字，并提到要做成视频、AI 视频、Seedance、即梦、Sora、可灵、Veo、文生视频、视频脚本、分镜、运镜、storyboard、shot list，或想把小说/桥段/广告脚本变成可生成的视频提示词，就用这个 skill。即使用户只说「帮我把这段改成视频脚本」「拆成分镜」「写成 AI 视频提示词」也要触发。

wuaishare/sharextract

Extract normalized content from public share URLs, RSS/Atom feeds, timed-text/subtitle documents, and web pages using a protocol-first fallback ladder. Use for public AI chat shares, social/media links, RSS/Atom feeds, WebVTT/SRT/TTML captions, articles, oEmbed pages, public JSON endpoints, or when an agent needs the highest-fidelity public content without bypassing authentication, CAPTCHAs, paywalls, or access controls.

mariano-aguero/solidity-security-audit-skill

Comprehensive Solidity smart contract security auditing and vulnerability analysis skill. Based on methodologies from Trail of Bits, OpenZeppelin, Consensys Diligence, Sherlock, CertiK, Cyfrin, Spearbit, Halborn, and other leading Web3 security firms. This skill should be used whenever the user asks to "audit a smart contract", "review Solidity code for security", "find vulnerabilities", "check for reentrancy", "analyze gas optimization", "review access control", "check proxy patterns", "analyze DeFi protocol security", "review ERC20/ERC721 implementation", "check oracle manipulation risks", "

Rancho-7/subtitle-optimizer

Use when reviewing or correcting SRT subtitle text while preserving timestamps, especially ASR transcript errors, product-name terminology, homophone mistakes, and visual review workflows.

howshannon/trust-issues

Adversarial, attacker-minded security review of ANY untrusted code before you trust it — a GitHub repo, a Claude/agent skill, an MCP server, a plugin, an npm or pip package, or a snippet you are about to base your own skill on. ALWAYS run this BEFORE installing a skill or plugin, BEFORE connecting an MCP server, BEFORE running or importing third-party code, and BEFORE copying external code into a skill you are authoring. Trigger whenever the user says "is this repo safe", "check this skill/plugin/MCP for malware", "review before I install", "audit this code", "can I trust this", or asks you to

leonsong09/worktree-closeout

Use when the user asks for worktree closeout, branch closeout, parallel closeout, worktree janitor, 工作树收口, 分支收口, or 并行收口, especially when work spans multiple Codex sessions and you need a date-based scan of open worktrees, closeout status, suggested merge/prune order, and prompt-ready handoff instructions.

SoulChildTc/wxmp-workflow

微信公众号内容创作与发布工作流，覆盖选题、撰写、打磨、配图、排版、发布、复盘。 个人订阅号无认证时发布会引导用户去后台手动操作。 Use when: "公众号", "写文章", "发文", "选题", "涨粉", "内容运营", "草稿箱", "帮我写篇公众号", "最近公众号没什么灵感", "公众号文章", "发布到公众号". Proactively suggest when the user mentions writing articles, content creation, or WeChat Official Account related tasks.

kigiela/16-eyes

Security audits with four subcommands — `/16-eyes init` (configure: detect quality gates, exclude patterns, output location, and design the repo's tailored investigation lenses — auto-runs non-interactively if skipped), `/16-eyes audit` (run every persisted lens across the WHOLE repo, verify every finding skeptically, adversarially re-check high-impact ones, produce a classified safe/risky report), `/16-eyes audit-diff` (the identical engine, scoped to a diff/PR instead of the whole repo — for reviewing a change before merge), `/16-eyes fix` (apply the findings — safe ones directly, risky ones

okxlin/1panel-app-adapter

Adapt, generate, migrate, and validate 1Panel App Store (AppStore/appstore) packages from Docker Compose, AppSpec, and aaPanel/Baota sources. Use when users ask for a 1Panel app skill, 1Panel application adaptation, appstore packaging or submission preparation, v1-to-v2 migration, Docker Compose conversion, localized metadata, strict-store validation, or batch app adaptation on Linux and GitHub.

kcmadden/claude-code-1password-skill

Integrate 1Password secrets management into Claude Code workflows. Use when the user wants to: store API keys or credentials in 1Password, read secrets from 1Password into scripts or config, set up .env files using 1Password secret references, rotate or update credentials, manage developer secrets across projects, use 1Password service accounts for CI/CD, or integrate 1Password with tools like Claude Desktop, n8n, Docker, Supabase, GitHub Actions, or Replit. Triggers on phrases like "store in 1Password", "read from 1Password", "op://", "secret reference", "manage API keys with 1Password", "1Pa

alexh/adobe-fonts-skill

Search Adobe Fonts (Typekit) families, create and manage web kits/projects, and return ready-to-use embed snippets plus CSS font-family values. Use when the user asks to find Adobe fonts, compare font options, set up Typekit for a website, add fonts to kits, publish kits, or generate copy/paste font embed metadata for Codex, Claude Code, or OpenCode workflows.

conorbronsdon/agent-skill-builder

Builds, reviews, or migrates agent skills. Use when creating a SKILL.md, auditing an existing skill, or converting a legacy Claude Code command.

Mirannonarbitrable290/agentic-kaggle-skill

AI Agent-driven Kaggle competition workflow. Learn from real competition experience: score stabilization patterns, submission troubleshooting, kernel workflows, GPU task delegation, and the spec-driven development approach that achieved top leaderboard positions. Use when: working on any Kaggle competition, analyzing submission failures, setting up automated pipelines, or replicating top notebook solutions.

MohamedMamdouh18/AI-News-Fetcher

Fetches and summarizes the latest AI news from across the internet — including tech blogs, research outlets, newsletters, and news sites — then renders a polished interactive digest as a React artifact in chat. Trigger this skill whenever the user asks about recent or latest AI news, developments, breakthroughs, releases, or anything like "what's new in AI", "AI news this week", "catch me up on AI", "latest AI updates", or specifies a time window like "AI news in the last 3 days / week / month". Also trigger for queries like "what happened in AI recently", "any new model releases", "AI headlin

Nana7mi0721/anima-prompt-naturalang

把中文场景描述转成 Anima/Anima Base 的英文自然语言 prompt：7 槽位、P/N 规则、负面三层、互斥自检；正负面分开输出直接复制，不输出 Params；禁止自行添加画风词/LoRA 触发词（用户没给就不写）

jcordon5/apple-container-skill

Expert guidance for Apple's `container` CLI. the open-source tool for running, building, and managing Linux containers and persistent Linux "container machines" as lightweight VMs on Apple silicon Macs. Use when the user wants to run containers or Linux dev environments on a Mac with Apple `container`, replace Docker Desktop, Colima, Lima, or OrbStack, use commands like `container run`, `container build`, `container machine create`, or `container system start`, or configure ports, volumes, networks, registries, DNS, or container networking on macOS. Also use for diagnosing Apple `container` ru

dakhlallah/arch-render

Create, improve, review, and present architectural still imagery while preserving the supplied design. Use for architectural render prompts, direct photorealistic rendering, material or lighting edits, style-reference matching, image enhancement, consistent render sets, design critique, presentation boards, architectural portfolios, typology guidance, and architect-level coordination advice. Accept sketches, plans, elevations, sections, physical models, photos, and screenshots from SketchUp, Revit, Rhino, D5, Lumion, Enscape, Blender, V-Ray, or similar tools. Produce all user-facing instructio

ttttonyhe/autogrind

Engage in 24x7 auto-work mode. Continuously grind through improvements, fixes, tests, and polish without stopping until you say so. For long-running sessions across code, ML/data, research, design, or writing. Not for single bounded tasks. Trigger phrases: /autogrind, /自己动, 'autogrind this', 'grind on this', 'keep working don't stop', 'work until I say stop', 'keep improving', 'keep going'.

bianzigege/avatar-sticker-pack

Generate a reusable sticker pack from one or more user-provided avatar images. Use when the user asks for avatar stickers, emoji packs, reaction stickers, chibi stickers, human-proportion and Q-version variants, transparent PNG stickers, or a paired sticker set for chat platforms.

capsrock/bauhaus-design-skill

Create frontends, posters, dashboards, and web UIs rooted in Bauhaus and Swiss International Typographic Style (Internationale Typografische Stil) design principles. Use this skill when the user mentions Bauhaus, Swiss design, International Typographic Style, grid systems, Josef Müller-Brockmann, Max Bill, Jan Tschichold, Herbert Bayer, László Moholy-Nagy, constructivism, De Stijl-influenced UI, or asks for designs that emphasize mathematical grids, typographic hierarchy, geometric abstraction, asymmetric layouts, or modernist clarity. Also trigger when the user wants a 'clean modernist' look,

IdanTayree/Blindspot

Turn an idea — or a half-planned project already underway — into a buildable blueprint, by interviewing the user one question at a time until the unknowns run out, then deep-reading and verifying real open-source components for each part. Use this whenever someone describes something they want to build but has not specified it ('I want to build an app that…', 'I have an idea for…', 'help me plan/spec/scope this', 'turn my idea into a plan'), whenever they ask for a PRD, a spec, a product requirements document or a build plan, AND equally whenever someone says an existing project feels under-pl

piaoyinghuang/brand-consistency-ai-skill

Universal brand guideline engine for producing, reviewing, and suggesting brand-compliant marketing materials for ANY company. Use this skill whenever a task involves brand identity, visual consistency, marketing collateral, or corporate design standards. Triggers include: brand guidelines, brand book, visual identity, corporate identity, brand compliance, brand review, brand audit, marketing materials, social media copy, poster design, banner design, PPT template, presentation template, company brochure, brand colors, typography guidelines, tone of voice, brand voice, logo usage, brand assets

poferraz/career-ops

All-in-one career operations: resume writing, CV optimization, cover letters, LinkedIn profile and content strategy, interview preparation, salary negotiation, job search strategy, career pivot planning, cold outreach messages, networking, follow-up emails, accomplishment mining, career coaching, skill stack analysis, unfair advantage identification, and anti-slop quality control. Triggers on: "help me find a job," "I have an interview," "optimize my profile," "write my resume," "tailor to this JD," "career change," "salary negotiation," "cold message," "LinkedIn optimization," "job search str

rdilruba/codebase-map

Build a persistent, evidence-based map of a software repository inside docs/codebase-map/ - TL;DR, architecture and dependency diagrams in Mermaid, real data flows traced with an archetype-specific strategy, the most important files ("the spine"), a reading order, potentially AI-assisted code, key concepts, and open questions. Five modes - "codebase-map init" builds the full map, "codebase-map update" refreshes it after changes, "codebase-map explain [topic]" covers one feature or domain, "codebase-map trace [flow]" follows one request path, "codebase-map check" reports drift without writing.

waynefu2020/competitor-kol-radar

竞品红人营销打法拆解（营销总监视角）——抓取竞品近 N 个月在 TikTok / Instagram / YouTube（国内小红书为实验功能）上的红人与 UGC 内容，判断它是"买量型""自来水型"还是"联盟铺量型"，统计博主量级、内容量、播放中位数、主打选题与卖点、销售转化渠道，对标库定位，输出带"对我们意味着什么 + 建议动作"的网页报告和明细 CSV。只要用户想研究某个品牌/竞品怎么做红人营销、KOL 投放、海外社媒种草、出海内容打法、博主合作、UGC 声量、"它在 TikTok/IG/YouTube 上投了哪些博主"、"竞品的红人投放怎么样"、"帮我拆一下 XX 的海外营销"，就应使用本技能，即使用户没说"竞品调研"。不用于：日常抖音竞品账号监控（用 competitor-radar）、单条视频解析、给自己找博主建联。

aakashH242/ctxsift

CtxShift is a skill that helps you focus on your tasks by reducing context clutter and enabling faster state recollections. \ It helps your user to save tokens and extend your work together. This is a guide on how to install the ctxsift skill.

MartinPuli/cvfit

Use when someone points at a job, hackathon, fellowship or program application and wants a resume for it. Triggers: a posting URL, a screenshot of a posting, pasted posting text, a company plus role name, or phrasings like 'adapt my CV to this', 'tailor my resume for this role', 'Harvard format resume', 'make a CV for this application', 'one-page resume'. The skill reads the posting, assembles the person's material from whatever exists (the conversation, an Obsidian vault, markdown notes, an old resume, public repos), decides the right shape for that person and that posting, renders a one-page

laoqianritan-create/daoyou

对建筑/街道/街区做空间历史考古，挖出层层堆积的演变史，交付可核查的空间考古档案。触发：daoyou、「导游一下 XX」、「把 XX 考古一遍」。

Fh-Ndiritu/design-psychology-skill

Audit or build any website/UI against research-backed conversion and design-psychology principles (Hick's Law, Von Restorff, Goal Gradient, Peak-End, Fitts's Law, the Aha moment, loss aversion, social proof, feedforward, labor illusion, and ~50 more). Use when reviewing a live URL or a local codebase for conversion/UX quality, or when designing or editing any user-facing surface — landing pages, pricing, onboarding, CTAs, forms, empty states, error flows, mobile screens. Auto-detects whether the target is a live URL or local source files. Brand-agnostic: derives the product's own tokens and vo

IrfanLee1011/dify-workflow-builder

Design, generate, review, refactor, validate, and deliver Dify Workflow/Chatflow/RAG Pipeline configurations from business requirements. Use when the user wants to create a new Dify app, convert business logic into Dify DSL YAML, review an existing Dify YAML/DSL, refactor a broken workflow, generate importable “Dify DSL YAML file”, or validate whether a workflow is directly importable through Dify Import DSL File.

digital-estate-inventory/digital-estate-inventory

Interactive tool for capturing the information and access paths your executor, attorney, partner, or family will need to manage your affairs if you die or become incapacitated. Produces a structured inventory — not a legal estate plan. Works alongside (not instead of) a qualified attorney.

mslavov/disciplined-entrepreneurship

Guide users through Bill Aulet's 24-step Disciplined Entrepreneurship framework to validate and develop business ideas. Use when users want to validate a new business idea, work through the DE framework systematically, complete specific DE steps (market segmentation, beachhead selection, persona creation, value proposition, TAM calculations, competitive positioning, unit economics), or bootstrap a startup idea with structured methodology. Triggers include phrases like "validate my idea", "help me with market segmentation", "define my beachhead", "create a persona", "quantify my value propositi

CosmoBlk/email-design

Design distinctive, on-brand emails — newsletters, campaigns, welcome series, promo, post-purchase, win-back, transactional, announcements. Use when the user wants to draft, write, compose, design, redesign, critique, polish, or improve an email; or send a campaign / blast / broadcast through any ESP (Nitrosend, Klaviyo, Mailchimp, ActiveCampaign, etc.). Produces a structured design brief and translates it into the sending tool's section format. Bakes in anti-slop principles: own a colour, restrained palettes, real imagery with sourced or prompted image slots, distinctive voice, no category-re

whewgg/skill-The-Twenty-Four-Histories-history

《资治通鉴》与二十六史（二十四史＋新元史＋清史稿）文白对照全文库：27 部 4408 卷，带检索与引文核验。【必须优先使用】凡中国正史、编年史的事实性提问，先跑 rag.py 查原文再答，禁止凭记忆——字号谥号、生卒籍贯、仕历事迹、事件始末、典章制度、原文出处与翻译、卷目定位、年表／世系表／宰辅年表／军机大臣／职官表／功臣表、同名异代朝名（刘宋／赵宋）、辨伪、讲历史故事、猜人物。触发词：史记、汉书、后汉书、三国志、魏书、隋书、旧唐书、明史、清史稿、资治通鉴、二十四史、二十六史、正史、本纪、列传、食货志、释老志、字什么、号什么、元嘉、靖康、表为什么是空的、某案出处在哪、胡惟庸案、明初八大案、文字狱、党锢、巫蛊、OCR辅助稿、伪史、AI编的历史、史实核查、讲个历史故事、讲个故事、讲一个故事、给我讲一个故事、猜皇帝、这是谁。只讲历史（正史）故事：说「讲个故事」也按讲史处理、直接开讲不反问；讲史取不到表就说「我读不到选签表」，不得编故事充数；讲史须先读 SKILL.md 正文再按流程抽签（真签号形如 # 加 6 位十六进制），跑不了抽签就如实说、严禁手搓签号。谜题／人物辨识须用题干里的独有引语反查，不得拿待猜的名字当检索词。**本环境跑不了检索时**：答「我查不到原文库，无法确定」，严禁凭记忆作答。

chinnkirsten/funded-phd-dossier

为社会科学博士申请者检索、查证并匹配全球全额资助的研究型博士项目。根据申请者的专业背景、研究兴趣、语言成绩、国籍或居留身份和目标入学季，核对 PhD、DPhil、项目制 studentship 与带薪博士职位的资助承诺、资格门槛、申请材料和截止日期，并形成可执行、可追溯的候选清单。用户想找全奖博士、判断某个项目是否真正全奖、评估个人资格、比较资助路径，或为一个学科和一批申请者建立持续更新的项目库时使用。

wang1025475397/game-cover-downloader-skill

Downloads game cover thumbnails with tiny-scraper. Invoke when user asks to find or download covers for games, ROM files, or ROM folders.

dungnotnull/game-ui-mobile-friendly-design-agent-skill

Mobile-Friendly Game UI Design & Touch-Friendly Interaction — Bulletproof production-grade harness for Mobile Game UI/UX & Touch Interaction Design analysis with zero placeholder code. Use this skill whenever the user asks for mobile game UI evaluation, touch interaction design, gesture discoverability analysis, accessibility assessment for games, one-handed mobile usability, thumb zone layout optimization, Fitts's Law application to touch targets, colorblind accessibility in games, or any mobile game interface design question. This skill provides evidence-backed analysis with academic citatio

unicodef1wn/humanizer-russian-language

Removes signs of AI generation from Russian-language blog content and social media posts (Telegram, vc.ru, Habr and similar) while keeping a lively, readable style. Universal and voice-neutral — works for long articles, short posts, notes, news breakdowns and opinion pieces. Must be used when the user says "перепиши более живо" (rewrite it more lively), "сделай менее ИИ-шно" (make it less AI-ish), "звучит как ChatGPT" (sounds like ChatGPT), "слишком сухо/шаблонно" (too dry / formulaic), "выглядит как LinkedIn-пост" (looks like a LinkedIn post), "очисти от воды" (cut the fluff). Also apply proa

alexconner-79/ill-communication

Write and review human-sounding copy, with deep UX writing craft. Use this skill for EVERY task that produces prose of any kind (chat responses, documents, presentations, emails, case studies, reports, blog posts) AND whenever the user asks to review, humanize, de-AI, edit, or improve any text or UX copy (buttons, error messages, empty states, microcopy, onboarding, notifications). It applies even when the user does not mention style, tone, or punctuation. If the task involves writing, rewriting, or judging any sentence, this skill applies.

OpenMOSS/imclaw-skill

IMClaw 跨网通信能力 — 让 AI Agent 具备实时聊天能力。用于：(1) Agent 需要与其他 Agent 实时通信，(2) 管理群聊，(3) 订阅和接收群聊消息，(4) 构建聊天机器人或协作 Agent。触发词：imclaw、跨网通信、agent 聊天、群聊、实时消息、龙虾。

shengxuan-create/interview-skill

候选人视角的面试备战助手——帮用户自己拿 offer，不是帮公司招人。Use ONLY when the USER is the job candidate: they have an upcoming interview or recruiter contact, want to prep for a specific company/role, match their resume against a JD, practice mock interviews or behavioral/STAR stories, grind company-specific LeetCode, handle AI-interviewer or async video screening rounds, calm pre-interview nerves, or debrief after an interview — even without the words "interview prep" (e.g. "明天要面字节", "phone screen this Friday"). Researches the target company with evidence discipline, generates tailored questions, runs mocks with cali

jeszhou/kandong-skill

看懂 AI 的长回答：把一大段文字做成先看全局、再点开细节的 HTML 页面。用于：用户说「看不懂」「太长了」「出 HTML」；你刚写完一段很长的回答（超过约 800 字，或有 3 个以上读者不熟的概念）；用户要把看懂页面存进知识库时。

its-me-prash/kleinanzeigen-reader

Read, scrape, and analyze ANY listing from kleinanzeigen.de — cars, electronics, furniture, real estate, clothing, or any other category. Use this skill whenever the user shares a kleinanzeigen.de URL, asks to "check this listing", wants to compare multiple ads, needs to detect if a seller is a dealer or private person, wants to find duplicate listings, or asks "is this a good deal?" for any German classifieds ad. Works without Playwright or external APIs.

chaucerj/mcd-status-codes

麦门监控台 —— 主动运维型身体 SRE。把每一笔麦当劳订单判定为 HTTP 状态码（双方向语义宪法 v4.0：18 码 + 3 指标告警），Agent 依据代谢模型（体重/身高/年龄→BMR→TDEE→分餐预算）在咖啡窗与补给窗主动探活提醒：该喝没喝的咖啡判 599 超时、减脂缺口下发 103 下午茶建议、超预算 412 否决、异常订单自动生成 P1-P3 事故复盘。当用户想回顾麦当劳订单、查看热量/营养/健康合规、生成监控面板或状态码报告、听取主动补给提醒、复盘事故或查询自己的 SRE 职级，或询问 1024 程序员节限定玩法时使用。基于麦当劳中国官方 MCP 只读采集，全部数值确定性可复算。

transicle/MGGU-LLM-NoCode-Prompt

Cut off AI code generation entirely, instead explain the how and why.

RubenGlez/mobile-design

Designs, implements, and reviews professional mobile UI for React Native and Expo, with platform-aware design and review guidance for iOS and Android. Use when the task involves mobile screens, components, navigation, visual direction, design systems, accessibility, gestures, haptics, animations, typography, color, dark mode, safe areas, adaptive windows, localization, platform conventions, App Store or Play-quality polish, iOS HIG, Material Design, Expo Router, React Navigation, Reanimated, Gesture Handler, or mobile UX critique.