Claude Skills Directory

LeoLin990405/grimoire-skill

Grimoire — turn a PDF/document/raw text into reading notes + a reusable skill pack in one parse. Auto-classifies book/paper/document, scaffolds type-specific notes for an Obsidian vault, and mines per-source skills merged per book/course. Built on the MinerU parsing API (OCR, formula/table, batch). Scripts never call an LLM and never write the vault; skill install is OPT-IN (--install / scripts/skill-install.sh) and deliberately crosses the candidate-only boundary by explicit user request, recorded in the manifest. Raw text → skill via --from-text; cross-agent install + management via the grim

moongiadventures-dev/handdrawn-ppt

내 캐릭터(IP) 이미지 한 장으로 손그림 발표자료를 통째로 만든다. 주제를 리서치해서 검증된 1차 출처를 확보하고, 차트·그래프·표·흐름도·빅넘버 같은 PPT 요소를 거친 펜선 미니 낙서 스타일로 그린 뒤, 헤드라인·설명·출처를 얹어 조립한다. 순백 배경, 콩눈, 뚝뚝 끊기는 외곽선, 깔끔한 플랫 컬러. 한국어·영어 둘 다 지원. Makes a full hand-drawn slide deck from one character image — researches the topic with verified sources, then draws charts, tables, flow diagrams and big-number slides in a rough pen-doodle style. Works in Korean and English. Trigger — /handdrawn-ppt, "내 캐릭터로 발표자료 만들어줘", "손그림 PPT 만들어줘", "손그림 삽화 만들어줘", "펜 낙서 스타일로 그려줘", "아티클 삽화 뽑아줘", "hand-drawn ppt", "doodle slide deck".

haoyiyin/instant-site

Build, deploy, update, and SEO-optimize static foreign trade independent sites using HTML/CSS/JS, DESIGN.md templates, Cloudflare Pages (Wrangler), and scheduled agent operations. Use for from-zero site generation, static deployment, scheduled content operations, SEO audits, and multi-site independent site operations.

MiaoQichuan/mqc-female-lawyer-brandcast

女律师 IP 形象内容工作台。一套固定的风格，播成多种内容形态——用内置的 53 张女律师漫画形象素材，把法律内容做成成套图文：朋友圈九宫格（八股结构）、小红书 3:4 多图、公众号（封面 + 正文插图组）、单张方图、竖版长图。凡是用户要写公众号推文、小红书图文、朋友圈九宫格、普法内容、案例解读、法律科普，或者提到"配图""插图""封面""九宫格""做成图""普法漫画""案情漫画""律师形象""IP 形象"，都要使用这个 Skill。注意：公众号要的是散落在正文段落之间的插图和两张封面，**不是一整张长图**，做公众号一律走 wechat 格式。用户直接给短句让你排版，或者丢一整篇长文、一段案情让你梳理提炼再配图，两种都用它。素材库已内置形象素材，不要调用任何文生图工具。

dd3ok/naverstock-api-skill

Read public, read-only Naver Stock (네이버증권/Npay) quotes, charts, news, research, crypto and company analysis, or audit their web APIs. Excludes private account data and trading.

Rekin226/paper-agent

Full academic manuscript skill for quantitative-science papers, with journal profiles for Hydrogeology Journal, Journal of Hydrology Regional Studies, Journal of Hydrology, Water Resources Research, HESS, Groundwater, Engineering Geology, IEEE TIM, JMBE, and Physiological Measurement, plus a field-agnostic generic profile for any other journal. Six modes: Draft, Review, Revise, Proofread, Audit, and Format. Use whenever the user wants to draft, write, review, revise, polish, proofread, or audit a journal manuscript, or respond to reviewer comments, including when they upload a .docx for feedba

YonasValentin/personal-brand-ops

Build personal brands that convert customers, not just rack up views. Use this skill whenever the user wants to define, scale, or operationalize a personal brand or content operation — including brand positioning, content strategy, posting cadence, platform selection, storytelling, media team hiring, onboarding, 1:1 cadences, work-mode design, or trust-first monetization. Trigger on phrases like "build my brand," "scale my content," "should I post on X platform," "what should I post about," "hire a content team," "FTE vs agency," "30/60/90 onboarding," "media team org chart," "monetize my audi

ddzyx/qiuxiaoce-football-data

球小策（qiuxiaoce.com）足球数据 Skill。当用户用自然语言查询足球赛程、单场赛前数据、当日赛事、积分榜、射手榜、伤停、球队/球员统计、历史交锋、转会记录、教练履历、裁判执法风格、市场参考值变化、已发布研报、历史样本复盘，或要基于这些数据生成分析/预测/文章/简报等结果文档时使用。触发词：查比赛、今天比赛、明天赛程、英超积分榜、伤停、历史交锋、转会、教练、裁判、市场参考、研报、复盘、写一篇、帮我分析、查额度、更新 Skill。不用于：投注建议或结果保证（任何表述形式）、第三方软件安装教学、与球小策数据无关的话题。

earino/resumasher

Tailor the student's resume + generate a cover letter + build an interview-prep bundle for a specific job posting. Runs in the student's working directory so it can cite evidence from their actual project files (capstone, notebooks, READMEs, PDFs). Outputs ATS-friendly PDFs in ./applications/<company-slug>-<date>/. Also investigates its own output when students report issues — if a student says the PDF looks wrong (missing content, stretched photo, weird section order, anything off), follow `docs/DEBUGGING.md` to match the symptom against known failure modes and draft a bug report for the main

riffkit/skill

Riff winning short videos — give one source (a TikTok link, an uploaded video, or an analyzed template) and the backend riffs its emotion formula into your own AI video (post-ready short-form or UGC-style ad creative), with optional digital character, product placement, and language. You riff the formula, not the video.

lanyasheng/self-improving-agent

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User explicitly corrects agent with direct correction like 'No, that's wrong', (3) User requests a capability that doesn't exist, (4) An external API or tool fails. CRITICAL: Maximum 1 learning log per user message. Do NOT chain multiple self-improvement actions.

akilrammohan/typst-skill

Write and create Typst documents (.typ files). Use when the user asks to create, write, edit, or convert documents to Typst format, write Typst markup, create academic papers, reports, or documents in Typst, convert LaTeX to Typst, or work with .typ files. Typst is a modern markup-based typesetting system alternative to LaTeX.

brenoepics/video-to-skill

Convert a video (local file or YouTube/URL) into structured, evidence-grounded knowledge — and ultimately into an installable agent skill. Use when the user provides a video file or video URL and wants it analyzed, summarized into steps, or turned into a skill; triggers include "watch this video", "learn from this tutorial", "video to skill", or a path/URL to .mp4/.mkv/.webm/.mov or youtube.com/youtu.be.

tga-cheetung/yt-digest

Turn a YouTube URL into a vault-ready research digest — transcript, key learning moments with timestamp deep-links, and screenshots of visual moments (slides, demos, dashboards). Use when the user pastes a YouTube link they're researching, says "summarize this video", "/yt-digest <url>", "youtube digest", or asks to extract key points from a YouTube talk. Output goes to vault/research/youtube/<slug>.md with screenshots in vault/attachments/youtube/<slug>/. Source MP4 is auto-deleted after frame extraction.

Jackychen-12/yuelao-aoye-skill

月老鳌烨风格的婚恋画像匹配报告。分轮采集条件（男看钱/女看脸两套算法），按鳌烨真实尺度打颜值分与梯队定位，输出上限/下限双画像与两条路子，最终生成浅色离线单文件 HTML 画像匹配报告。当用户提到「月老」「鳌烨」「婚恋画像」「帮我看看条件」「打个分」「颜值几分」「相亲定位」「择偶画像」「婚恋市场定位」「画像报告」「我能找什么样的」时使用。即使用户只说「月老模式」「用鳌烨的方式看看我」也应触发。

gncdev/fabling

Behavioral profile that makes Claude work like the Fable 5 model tier — deep but proportional code investigation, outcome-first communication, high autonomy without permission-asking, faithful outcome reporting, and disciplined turn endings. Use this skill whenever the user asks Claude to behave "like Fable", mentions "fabling", "fable mode" or "fable gibi", complains that Claude is being lazy or superficial, or asks Claude to be more thorough, more autonomous, less chatty, or to stop asking for permission mid-task. Load it once at the start of the session and follow it for every subsequent tu

Sidgit11/resume-studio

Build, tailor, and maintain job-winning resumes with a persistent career memory. Use this skill WHENEVER the user mentions a resume or CV in any capacity — creating one, updating one, tailoring one for a job description, reviewing/critiquing one, converting a LinkedIn profile into a resume, preparing a job application, or sharing details about their work history that should be remembered. Also trigger when the user shares a JD and wants application materials, says "help me apply for this job", wants to fix or rewrite resume bullets, or corrects how their resume should be written (style/framing

zincio/skills

Discover, buy, track, and return real products from Amazon, Walmart, Target and almost any other US online retailer through the Zinc API (zinc.com). Needs no account to begin — the agent mints its own test key, then earns a live key and a $5 starter credit once its operator approves it. Pay from a pre-funded wallet, per request over MPP or x402, or with a Stripe Link card.

acchuang/zh-tw-humanizer

把 AI 寫的繁體中文改寫成自然、有人味的台灣風格文字（去 AI 味、本土化）。 Use when editing or reviewing Traditional Chinese text to remove AI-generated writing tells and localize it to Taiwanese Mandarin: Taiwan vocabulary (影片/軟體/網路/資料 instead of 視頻/軟件/網絡/數據; 大數據 and 數據顯示 stay), Taiwanese tone, particles, and natural sentence rhythm. Never produces simplified Chinese or mainland-style phrasing. Supports annotation mode (list problems without rewriting), protected spans, scene-based intensity, and a pre-delivery quality self-check. Based on Wikipedia's "Signs of AI writing" and the zh-TW "AI生成文的特徵" guides. Triggers: 人性化、去AI味、A

chenmitchell/omg-payment-skill

Assist non-technical Taiwan merchants in integrating the OMG (歐買尬 / MacroWell OMG) payment gateway end-to-end via a single natural-language instruction. Triggers when the user mentions: OMG, 歐買尬, MacroWell, omgpay, 金流串接, 收款, 線上付款, 刷卡串接, ATM 收款, 超商付款, 退款, 對帳, 儀表板監控, Telegram 付款通知, Discord 付款通知, or asks to "整合歐買尬金流", "建置金流系統", "建置付款後台儀表板", or "建置付款通知機器人". Default behavior: full-stack integration including backend, admin dashboard, health monitoring, Telegram/Discord notification bots, and Taiwan regulatory disclosure templates, executed as a single automated workflow.

atdy/maoxuan-product-agent

中文产品决策 Agent。用于中国大陆互联网产品、运营、增长、商业化、数据、项目推进和组织协作场景：产品规划、需求分析、PRD、需求优先级、排期、版本规划、Roadmap、MVP、灰度、上线、迭代、增长停滞、拉新、投放、渠道、裂变、CAC、LTV、ROI、留存、转化、DAU/MAU、GMV、漏斗、社区运营、内容供给、创作者、用户运营、活动运营、私域、会员、定价、指标异常、数据口径、埋点、A/B Test、用户反馈、客服/销售反馈、竞品冲击、资源不足、项目延期、需求反复、老板临时插需求、跨部门协作、团队冲突、OKR/KPI、目标拆解、复盘等。触发时像资深互联网产品负责人一样，先判断真实问题、当前阶段、核心阻塞、关键约束、相关方和证据充分性，再给出最值得执行的下一步。默认中文回答，不讲理论、不引用原文、不解释历史、不暴露后台方法来源。

joeseesun/qiaomu-app-review-skill

Use when a user wants to analyze App Store reviews, mine product opportunities from user comments, compare competitor pain points, generate durable review insight reports, or create local HTML/Markdown evidence pages without relying on a hosted website or a specific LLM provider.

AEON-7/aeon-radio-drama

Full-pipeline radio drama and audiobook production — from creative premise to finished mixed audio. USE THIS SKILL whenever the user mentions: radio drama, audio drama, audiobook, audio play, radio play, podcast drama, audio fiction, radio theatre, audio storytelling, dramatic audio, audio production, voice acting project, audio book production, sound design for story, audio narrative, spoken word production, dramatic podcast, audio series, radio show, audio episode, voice drama, or any request to produce a complete audio production with multiple voices, music, and sound effects. Also trigger

darajoukar/reveal-rtl

Create right-to-left HTML presentations (Persian/Farsi, Arabic) with reveal.js and the reveal-rtl plugins — correct RTL layout, Persian or Arabic digits, Jalali/Hijri dates, bundled Vazirmatn font, toolbar, speaker notes, PDF/PNG export. Use when the user asks for slides, a presentation, a deck or a talk in Persian or Arabic, or an RTL reveal.js presentation.

CtriXin/agent-2-agent

a2a (Agent-to-Agent) — 跨模型对抗式 code review。Claude 写的代码让 Codex 审，Codex 写的让 Claude 审，互相找茬不留死角。

brkhzn/adhd-operating-system

Pervasive filter adapting all Claude interactions to inattentive ADHD cognition. Affects BOTH response formatting/structure AND content recommendations. Trigger aggressively for: productivity, organization, project management, task management, learning, studying, note-taking, communication, email, meetings, habits, routines, daily planning, time management, tool selection, workspace setup, career decisions, writing, creative work, prioritization, or anything involving executive function, working memory, attention, motivation, or emotional regulation. Also trigger for mentions of ADHD, focus, d

owgit/ai-collab-bridge

A collaboration protocol for Claude, Codex, and other CLI-capable AI models to review each other's code via CLI handoffs. Use this skill whenever the user mentions AI-to-AI collaboration, Claude-Codex bridge, peer review between AI models, "let Claude check what Codex did", "have Codex verify Claude's work", multi-agent code review, AI handoff, two AIs reviewing each other, or wants two different AI models to verify each other's output before completing a task. Also use whenever you (the running AI) want a second opinion from another model and need a structured way to request that review, even

Caspian98/ai-prd-skill

Generates a complete, structured AI Product Requirements Document (PRD) in Markdown format, covering background, requirements, model selection, prompt engineering, evaluation system, and stability strategy.

areaox/akshare-open

A股全覆盖 + 港股 + 美股 + 指数 + 财务 + 宏观经济数据。 免费、无需 API Key、Python 原生。支持实时行情、历史K线、板块分析、资金流向、 财务三表、股东研究、龙虎榜、涨跌停、融资融券、宏观数据等。 提到A股、港股行情、财务报表、财报、宏观、GDP、CPI、PMI、板块、资金流、 龙虎榜、涨跌停、融资融券、IPO、解禁、研报 时自动使用。

crisak/anki-connect-skill

Manipulate Anki flashcards via curl using the Anki-Connect API. Create cards, manage decks, search notes, customize note types, and control Anki entirely through HTTP requests.

bozhouDev/anthropic-mind

用 Anthropic 的判断框架给出一个决策建议——回答「按 Anthropic 会怎么做这个取舍」。基于 428 篇一手材料（Claude's Constitution、工程博客、alignment 研究、两份 postmortem、Dario Amodei / Jack Clark / Amanda Askell / Chris Olah / Boris Cherny 的长文与访谈）蒸馏出的 8 条世界观模型、18 条领域模型和 21 条决策先例。触发场景：(1) 问「Anthropic 会怎么判断这个」「按他们的思路」「Dario / Jack Clark / Amanda 怎么看」；(2) 在做 agent 工程、产品、研究或内容决策时想要一个有出处的判断，而不是通用建议；(3) 要写关于 Anthropic 立场的内容，需要准确观点、英文原文引用和内部分歧。不要用于：Claude API 的用法、定价与模型 ID（用 claude-api）、Claude Code 的功能操作（用 claude-code-guide）、纯事实查询（发布时间、参数、榜单数字）。

keemanxp/apa-referencing-skill

Format, check, correct, and verify references and citations in APA 7th Edition style. Use whenever the user asks to format, check, proofread, or fix references or citations; verify references are real (not fabricated); convert from other styles to APA 7th; or generate in-text citations and reference list entries. Trigger on mentions of 'APA', 'APA 7th', 'referencing', 'reference list', 'in-text citation', 'cite this', 'check my references', 'bibliography', or when references are pasted for review. Covers all source types: books, journals, conference papers, reports, white papers, theses, newsp

Caoran1314/apple-cn-checkout

用 bsk_* 浏览器工具在苹果中国官网（apple.com.cn）完成 iPhone 选购与结账。含实测的稳定选择器、5 级门控的一轮批量配方、以及会造成静默失败的坑（networkidle 永不满足 / CSS 猜选择器会打偏 / 点击后立刻读取是旧 DOM）。当用户要求在 Apple 中国官网买手机、加购物袋、或走到微信支付时使用。

sojuhub/aside-free-llm-autopilot

Set up and maintain free LLM APIs for Aside first, adapting to other agents when requested: discover providers, onboard eligible accounts, adapt model routing to the user's environment, retire unavailable routes, and register one daily maintenance routine. Use for free-tier setup or maintenance, not every browser task.

0x68616F4C/auto-popsci

Generate math/science popularization videos with Manim animations and AI narration. Use when the user asks to create an explainer video, science animation, math tutorial, or pop-sci content on any topic. Handles the full pipeline from narrative design to final rendered video with synced audio.

Wattson-Law/avoid-over-ai-writing-skill

降低论文、技术方案、专利和正式 Word 文稿中的模板化 AI 文风，并把 Word、Markdown 或粘贴文本整理为可交付 DOCX。统一表达、标题编号、字体、段落、黑白表格、分页和目录；保留用户事实、证据、指标与结论，不代替事实核验或技术评审。

Thomaszhou22/better-readme

Use when the user asks to create, improve, fix, or audit a README.md file, score their README, document an open source project, or set up new project docs. Provides 8-dimension 0-100 quality scoring, 5-type template matrix (Library, CLI, App, Skill, Data), and pre-publish checklist. Do NOT use for API docs, wikis, inline code comments, or general technical writing.

Roxy-ljy/bilibili-video-summary-skill

Create local Markdown summaries for Bilibili, b23.tv, and YouTube videos by extracting metadata and subtitles/transcripts first, then having Codex write the summary and detailed notes. Use when the user asks to summarize, outline, extract key points from, or prepare notes for Bilibili/B-site/BV videos, b23.tv short links, or YouTube videos, especially when they want a local .md document.

pascalorg/blaze

Quietly reuse and improve verified coding lessons across agents. Use for a nontrivial debugging or implementation problem where an earlier solution could help, when a Blaze offer or receipt appears, or when the user asks to inspect, install, update, contribute to, or link Blaze. Check applicability, verify locally, and close the lookup with an honest outcome and contribution disposition without adding routine user-visible narration.

pcauhi/bolo-de-camadas

Edita um vídeo falado (você falando para a câmera) num reel vertical 1080×1920 com motion graphics em 5 camadas — o take, a legenda palavra por palavra, o rosto num card, gráficos que desenham o que você fala, zoom e som em cada movimento — com o Claude Code e o Remotion (ou HyperFrames). Tem estilos prontos por nicho (corretor de imóveis, personal trainer, professor de inglês, chef, finanças) e um modelo para criar o estilo de qualquer outra profissão. Use quando a pessoa quiser editar um reel/vídeo falado, fazer motion graphics, legendas animadas, ou mencionar um desses nichos.

Receiptor-AI/bookkeeping-skills

Small-business bookkeeping skills for converting financial evidence into accountant-reviewable outputs, including setup/context, receipt processing, expense categorization, bank reconciliation, tax preparation, monthly close, jurisdiction-aware tax references, plus specialized skills for home office, vehicle, meals, depreciation, 1099 contractors, and estimated taxes. Trigger on "help me with my bookkeeping", "set up my bookkeeping", "bookkeeping context", "chart of accounts", "process my receipts", "categorize expenses", "reconcile my bank statement", "get my books ready for taxes", "close th

jasnonaz/chaos-agent

Chaos agent for skills — a vigilance-training layer that keeps humans reviewing AI output instead of rubber-stamping it. Consult this skill on EVERY substantive request (code, analysis, writing, SQL, configs, explanations — anything with a checkable answer). 95% of requests get your genuine best work; a deterministic 5%, chosen by hash, get a polished answer containing exactly one subtle, findable flaw. Trigger on all real work; skip only trivial chit-chat.

dylan-buck/Clippos

Local video clipping automation for /clippos requests, attached video files, video links, social clip generation, captioned shorts, crop/framing, and rendered 9:16, 1:1, or 16:9 exports. Use this skill whenever the user wants an agent to turn a video into high-potential clips, score clips with the current harness model, approve selected clips, and render final MP4 outputs.

hoaile2kdev/cocos-agent-skills

Use when Codex needs Cocos Creator 2.4.x/2.4.15 engine-specific guidance for TypeScript cc.Component scripts, cc._decorator/@property editor bindings, prefab/UI creation from screenshots or mockups, serialized .prefab/.fire scene authoring, cc.Node hierarchy/events/transforms, cc.assetManager/resources/bundles, cc.tween/actions, Spine sp.Skeleton, web-mobile builds, or fixes that must avoid newer Cocos APIs.

quanru/code-review-skill

Perform architecture- and maintainability-focused code reviews. Use when the user asks for code review, style review, refactoring feedback, or review of architecture, cohesion, coupling, TypeScript rigor, naming, tests, responsibility boundaries, or unnecessary abstractions.

woaillr-crypto/code2wiki

为大型后端项目生成和维护面向业务的 Business Context Layer（业务语义层 / 项目知识地图）。当需要总结、梳理、文档化、wiki 化、构建上下文、创建领域 skill、提升 LLM 对既有后端代码库的理解时使用——尤其适用于 10w+ 行、50w+ 行这类需求主要由业务驱动而不是技术模块驱动的系统。支持 Java/Spring、Kotlin（Spring/Ktor）、Python（Django/FastAPI/Flask）、Go（Gin/Echo/gRPC）、TypeScript/JavaScript（NestJS/Express）等多种后端栈；扫描器自动识别项目语言，混合语言 Monorepo 会并行扫描所有命中插件。也适用于多级业务域目录、项目知识地图、API/Database/Code Entrypoint 映射、风险清单、分层上下文（L0/L1/L2/Source）建设等任务。

Asixa/codemap-skill

Generate and incrementally maintain an interactive architecture map plus a per-module code-quality audit (health scores 0-100, smell findings, lines-of-code, and a clickable dependency graph) for any codebase. Use when the user wants to visualize a project's functional modules, audit or score code quality, check whether the architecture map is stale / up to date, incrementally refresh it after code changes, or auto-fix the findings of a specific module. Module audits are run by independent subagents against a fixed rubric. Triggers: "architecture map", "module map", "audit the codebase", "scor

adonis-cyril/codex-automation-audit

Audit recent Codex automation and personal skill runs, compare task behavior with prompts and local docs, then prepare numbered patch-ready recommendations without changing files during the scheduled run.