Directorio de Agent Skills

Índice de Agent Skills, página 35

Explora este índice de skills públicas o usa la búsqueda para acceder a la biblioteca completa.

Abrir búsqueda

N.º: 3401
agent-research에이전트 팀을 구성하여 종합 리서치 보고서를 작성하는 스킬. 조사 대상을 분석하여 전문가 풀에서 최적의 에이전트를 동적으로 선택·구성한다. (1) '조사해줘', '리서치해줘', '보고서 작성해줘' 요청 시, (2) '~기업 분석해줘', '~회사 조사해줘' 요청 시, (3) '~사람 조사해줘', '~인물 분석해줘', '~에 대해 알려줘' 요청 시, (4) 미디어 반응, 커뮤니티 의견, 경쟁 환경 등을 종합적으로 파악해야 할 때, (5) '에이전트 팀으로 조사', '팀 리서치' 요청 시, (6) 영상 스크립트, 기사, 보도자료 등을 바탕으로 배경 조사가 필요할 때.
Idioma del contenido del Skill: coreano
Repositorio: revfactory/skills
Estrellas en GitHub: 161Actualizado: 12 abr 2026
N.º: 3402
agentdb-learning-pluginsCreate and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience.
Idioma del contenido del Skill: inglés
Repositorio: ruvnet/RuView
Estrellas en GitHub: 103.115Actualizado: 13 ene 2026
N.º: 3403
industry-resume-toolkit为中国 industry 求职者打造的简历优化方法论。把"资深 HR 顾问怎么改简历"codify 出来,让用户用 AI 自助优化自己的简历。覆盖大厂(互联网/科技)/ 国央企 / 银行金融 / 外企 4 种企业性质,12 个常见岗位(运营/产品/数据/市场/财务/审计/HR/销售/开发/法务/战略/设计),实习/校招/社招都适用,中英文都做。当用户需要改自己的简历、点评简历、做 JD 匹配、按目标企业性质定制简历内容时,使用此 skill。核心方法是"三层框架"(信息卫生 / 业务价值翻译 / 经历挖掘)。区别于通用 AI 简历生成器,此 skill 是 HR 顾问视角的方法论,强调保真原则(不夸大职责)、industry-specific 内行知识。Industry resume editing methodology for Chinese job seekers — used by the resume owner themselves, not by a consultant.
Idioma del contenido del Skill: chino
Repositorio: shangsitongshizaitiantang/industry-resume-toolkit
Estrellas en GitHub: 509Actualizado: 6 jun 2026
N.º: 3404
origin-auto-skillDrive OriginLab Origin via COM automation to create publication-grade scientific figures from CSV/Excel data. Use when the user asks for Origin plots (.opju source files), says "用Origin画图", "Origin绘图", "科研绘图", "出版级图表", or needs journal-submission figures that must NOT be made with matplotlib. Supports line/scatter/line_symbol/column plots, log axes, multi-Y series, Chinese/English labels, reference lines, and exports PNG/PDF/TIF/EPS plus .opju project saving.
Idioma del contenido del Skill: chino
Repositorio: simcrq/origin-auto
Estrellas en GitHub: 3Actualizado: 22 sept 2026
N.º: 3405
douyin-style-profiler提取抖音作品 DNA：单篇作品（视频 / 图文）生成 report，按 dna-id 聚合选题、标题与封面、内容创意、业务植入套路、互动引导与 CTA 套路、视频形态与制作指向、制作规格、口播文案子模块与账号运营子模块，推导 main agent 的 Brief / 图文生产 template。
Idioma del contenido del Skill: chino
Repositorio: TeamWiseFlow/xiaobei
Estrellas en GitHub: 8701Actualizado: 27 oct 2026
N.º: 3406
hand-drawnUse when users ask for a hand-drawn or illustrated image prompt, name one of the repository's 22 numbered styles or the 3.1 stable variant, or mention triggers such as 亲子手绘、家庭蜡笔画、蜡笔、吉卜力、水墨、像素、淡彩速写、动画概念、水粉、北欧绘本、纸雕、软胶潮玩、墨线绘本、暖色扁平绘本、圆头红线、暖黄墨线、family-crayon-card、warm-flat-storybook、roundhead-redline、warm-yellow-ink-story、朱墨写意、朱墨水墨漫画、vermilion-ink-wash、ink-comic-transfer、皮影、皮影彩染、shadow-puppet、backlit-puppet. Produces prompt text or a formal reference-bearing call bundle and does not generate images.
Idioma del contenido del Skill: chino
Repositorio: threerocks/hand-drawn-styles
Estrellas en GitHub: 2637Actualizado: 23 oct 2026
N.º: 3407
z-docx-format-brushdocx 格式刷：从模板 Word 文档提取格式指纹（字体/字号/行距/缩进/对齐/表格边框/封面/分页），然后统一应用到目标 docx，做到与模板格式完全一致。触发词：格式刷、格式统一、统一格式、套用模板格式、参照模板格式、docx格式修复、Word格式不一致、pandoc转出来的docx格式乱、按模板生成docx、公文格式。凡是'参照某个 docx 模板写/改/修复另一个 docx'的任务都用本 skill，包括新建文档按模板排版、修复其他工具（pandoc/其他模型）产出的格式混乱 docx。
Idioma del contenido del Skill: chino
Repositorio: tjxj/z-skills
Estrellas en GitHub: 592Actualizado: 3 ago 2026
N.º: 3408
flowchart生成教育/科普类流程图、概念图、原理演示的动画 HTML 页面。用 CSS/SVG 绘制节点和连线，支持流动箭头、逐步出现、hover 高亮等动画效果。适合技术讲解、视频科普、PPT 配图场景。
Idioma del contenido del Skill: chino
Repositorio: unclecheng-li/ai_animation
Estrellas en GitHub: 1751Actualizado: 21 jun 2026
N.º: 3409
grill-me一个用来打磨计划或设计的持续追问式访谈。
Idioma del contenido del Skill: chino
Repositorio: vinvcn/mattpocock-skills-zh-CN
Estrellas en GitHub: 5627Actualizado: 21 sept 2026
N.º: 3410
playwright-bddEnforces Behavior Driven Development. Use when: implementing new features, making significant code changes, adding functionality, refactoring behavior. Requires writing a Gherkin feature file first, getting user approval, then implementing.
Idioma del contenido del Skill: inglés
Repositorio: vitalets/playwright-bdd
Estrellas en GitHub: 822Actualizado: 27 ago 2026
N.º: 3411
research-refineTurn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-6-Astra review. Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.
Idioma del contenido del Skill: inglés
Repositorio: wanshuiyin/Auto-claude-code-research-in-sleep
Estrellas en GitHub: 18.891Actualizado: 19 oct 2026
N.º: 3412
ai-wedding-photoCreate personalized AI wedding-photo prompts and, when image-generation tools are available, generate wedding photos from uploaded reference portraits. Use when users ask for AI wedding photos, 婚纱照, 情侣写真, pre-wedding portraits, wedding style selection, model-specific image prompts, or one of the nine curated styles bundled with this skill.
Idioma del contenido del Skill: inglés
Repositorio: wenyachen/ai-wedding-photo-skill
Estrellas en GitHub: 54Actualizado: 8 jun 2026
N.º: 3413
academic-writing-skillsFrame and outline academic papers, plan and revise connected paragraphs, and align claims with evidence across manuscript sections, abstracts, supplements, references, and reviewer responses. Use for scoped drafting, substantive revision, proofreading, or cross-file integration. Preserve the author's research goal, terminology, clear wording, and inference limits; scale checks to the requested passage, section, or submission package.
Idioma del contenido del Skill: inglés
Repositorio: WenyuChiou/academic-writing-skills
Estrellas en GitHub: 265Actualizado: 28 oct 2026
N.º: 3414
get-prompt-from-imageAnalyze user-provided reference images and reverse-engineer high-fidelity AI image-generation prompts. Use when the user asks to recreate, imitate, reverse-engineer, or extract prompts from photographs, illustrations, 3D renders, products, characters, landscapes, typography, logos, posters, or other visual references. Do not use for requests that only require OCR or an ordinary image description.
Idioma del contenido del Skill: inglés
Repositorio: wuyoscar/GPT-Image2-Skill
Estrellas en GitHub: 6042Actualizado: 4 sept 2026
N.º: 3415
ponytail-review代码审查只关注过度工程。找到要删除的内容：重新发明的标准库、不必要的依赖关系、推测性抽象、死灵活性。每个发现一行：位置、剪切内容、替换内容。当用户说“审查是否过度工程”、“我们可以删除什么”、“这是过度工程吗”、“简化审查”或调用/马尾辫审查时使用。这是对以正确性为重点的审查的补充，它只追求复杂性。
Idioma del contenido del Skill: inglés
Repositorio: zzz2929/skills-zh-CN
Estrellas en GitHub: 0Actualizado: 2 sept 2026
N.º: 3416
multi-agent-meeting项目管理专家与产品经理在做项目决策、技术评审或商业策略制定时，当需要多视角碰撞以打破思维局限，请用此技能模拟多智能体真实会议辩论，一键生成包含决策结论、核心论据与风险提示的完整会议记录，让复杂决策高效落地！
Idioma del contenido del Skill: chino
Repositorio: anbeime/skill
Estrellas en GitHub: 9320Actualizado: 26 ago 2026
N.º: 3417
read-imageUse when the user asks to read, analyze, describe, or understand the content of an image file (local path or URL). Supports screenshots, photos, diagrams, charts, UI mockups, and any visual content.
Idioma del contenido del Skill: inglés
Repositorio: ardenlab/claude-skills
Estrellas en GitHub: 0Actualizado: 1 feb 2026
N.º: 3418
natural-japanese仕事の日本語文書を、自然で読みやすく、わかりやすい日本語で書く・直すためのスキル。議事録、調査レポート、顧客向けのレポート、社内ガイド、技術記事、PR の説明文、リサーチメモ、企画書、メール、スライド構成などの作成や推敲と、note やブログ、エッセイの執筆に使う。文字起こしから議事録を作るときにも使う。自然な日本語にしたい、読みやすくしたい、簡潔にしたい、結論から書きたいといった依頼のほか、読みづらい、わかりにくい、何を言っているかわからない、AI っぽい、AI 臭い、英語の直訳っぽい、日本語として不自然、違和感があるといった指摘にも使う。書き換えずに AI らしさを判定・採点してほしいという依頼や、自分の文体を学ばせたいという依頼にも対応する。
Idioma del contenido del Skill: japonés
Repositorio: coji/natural-japanese
Estrellas en GitHub: 2031Actualizado: 4 nov 2026
N.º: 3419
party-application生成"入党申请书"docx。大学期间首次申请入党专用，标准 4000 字左右，书信体 4 段结构（入党志愿表达 / 对党的认识 / 个人经历与思想变化 / 个人不足与今后努力方向）。必含习近平新时代中国特色社会主义思想、党的二十大、共产主义、全心全意为人民服务四个政治要点全称。党支部会查重，禁抄网络模板与党章原文。直接输出可提交的 Word 文档。
Idioma del contenido del Skill: chino
Repositorio: cuic19053-hue/-skills-
Estrellas en GitHub: 9Actualizado: 25 jul 2026
N.º: 3420
watercolor-travel-cardTurn uploaded photos into full-canvas 3:4 perforated watercolor travel-card posters. Use for watercolor memory cards, perforated ticket cards, travel archive layouts, or when this skill is invoked.
Idioma del contenido del Skill: inglés
Repositorio: GZ-L/photo-to-poster-skills
Estrellas en GitHub: 35Actualizado: 24 ago 2026
N.º: 3421
ai-social-media-contentCreate AI-powered social media content for TikTok, Instagram, YouTube, Twitter/X. Generate: images, videos, reels, shorts, thumbnails, captions, hashtags. Tools: FLUX, Veo, Seedance, Wan, Kokoro TTS, Claude for copywriting. Use for: content creators, social media managers, influencers, brands. Triggers: social media content, tiktok, instagram reels, youtube shorts, twitter post, content creator, ai influencer, social content, reels, shorts, viral content, thumbnail generator, caption generator, hashtag generator, ugc content
Idioma del contenido del Skill: inglés
Repositorio: inference-sh/skills
Estrellas en GitHub: 793Actualizado: 18 sept 2026
N.º: 3422
si-planningSI 프로젝트 요구사항 공학 스킬. 소크라테스식 요구사항 수집 → 도메인별 체크리스트 검증 → 산출물 자동 생성(요구사항분석서/기능정의서/화면정의서/추적표) → 변경 영향 분석. 대시보드 연동으로 고객 공유 지원.
Idioma del contenido del Skill: coreano
Repositorio: insightflo/claude-impl-tools
Estrellas en GitHub: 17Actualizado: 29 mar 2026
N.º: 3423
pkpd-modelingPharmacokinetic and pharmacodynamic modelling and simulation - non-compartmental analysis, compartmental and population PK, PK/PD and exposure-response, TMDD, PBPK orientation, bioequivalence, allometric scaling and first-in-human dose, drug interaction prediction, and Bayesian therapeutic drug monitoring. Use when analysing concentration-time data, deriving exposure metrics, fitting PK or PD models, or evaluating dosing regimens. Triggers include "pharmacokinetics", "pharmacodynamics", "PK/PD", "NCA", "non-compartmental", "AUC", "Cmax", "lambda z", "half-life", "clearance", "volume of distribution", "compartmental model", "population PK", "popPK", "NONMEM", "nlmixr2", "Pharmpy", "Monolix", "exposure-response", "Emax", "EC50", "indirect response", "effect compartment", "TMDD", "PBPK", "bioequivalence", "RSABE", "ABEL", "allometric scaling", "first-in-human", "MABEL", "drug-drug interaction", "DDI", "ICH M12", "concentration-QTc", "therapeutic drug monitoring", "MIPD", and "dosing regimen".
Idioma del contenido del Skill: inglés
Repositorio: K-Dense-AI/scientific-agent-skills
Estrellas en GitHub: 56.516Actualizado: 1 oct 2026
N.º: 3424
identity-work当用户发现自己在为立场辩护、看不清现实、或反复立志却改变不了自己时调用。核心理念: 身份是认知牢笼也是行为杠杆——放下身份才能看清真相(痛苦=真相时刻), 更新自我形象才能替代自律(对外承诺)。不适用于: 需要专业心理咨询的深层创伤。 Triggers: 立场/身份/自我/看不清现实/改变不了自己/自律失败/identity/self-image
Idioma del contenido del Skill: chino
Repositorio: kangarooking/cangjie-skill
Estrellas en GitHub: 12.390Actualizado: 30 ago 2026
N.º: 3425
meta-ads-connectConnect to Meta Marketing API to pull real Facebook and Instagram ad data — campaign performance, creative fatigue, audience saturation, ROAS by ad set, frequency analysis, and Learning Phase status. Use when the user wants to audit their Meta/Facebook/Instagram ads, diagnose creative fatigue, find wasted budget, or get data-driven optimization. Enhances paid-ads and ad-creative skills with real Meta data. Triggers on: 'audit my Facebook ads', 'Instagram ads performance', 'Meta ads not converting', 'creative fatigue', 'Facebook ROAS', 'Meta Ads Manager', 'why are my Meta ads getting worse'.
Idioma del contenido del Skill: inglés
Repositorio: LeoYeAI/openclaw-marketing-skills
Estrellas en GitHub: 1054Actualizado: 22 may 2026
N.º: 3426
java-optimization执行 Java 代码性能优化，包括 JVM 调优、并发编程、内存管理、缓存策略、数据库优化、集合框架优化等。Invoke when user needs to optimize Java code performance.
Idioma del contenido del Skill: chino
Repositorio: LeoYeAI/openclaw-master-skills
Estrellas en GitHub: 2169Actualizado: 29 jun 2026
N.º: 3427
navigation-without-screensPhysical navigation skills without digital devices. Use when someone wants to learn map reading, compass use, natural navigation, or needs to navigate when technology fails.
Idioma del contenido del Skill: inglés
Repositorio: LeoYeAI/openclaw-master-skills
Estrellas en GitHub: 2169Actualizado: 8 jun 2026
N.º: 3428
qmt-trader通过统一 CLI 脚本驱动大 QMT 迅投量化交易端的全部能力，含实时行情查询、K线历史数据、账户资产与持仓查询、委托与成交查询、买入卖出下单、撤单、板块龙虎榜北向资金财务数据等，并内置 xtquant_big_convert 桥接服务的安装部署引导（装包/同步 QMT 端文件/配置/启动验证/排错）。适用于大模型辅助量化交易分析、行情研判、持仓监控、半自动下单等场景。当用户需要查看股票行情、分析K线、查询持仓资产、查看今日委托成交、下单买卖、撤单、查询北向资金龙虎榜财务数据，或需要安装部署 QMT RPC 桥接服务时触发此 skill。
Idioma del contenido del Skill: chino
Repositorio: litaolemo/xtquant_big_convert
Estrellas en GitHub: 801Actualizado: 23 sept 2026
N.º: 3429
install-skillSearch and install skills from skills.sh and GitHub repos. Use when users ask to find skills, install skills, download skills, add skills from GitHub, search for skills, browse skills, get a skill, or want new capabilities. Trigger phrases include "install skill", "find skill", "search skills", "add skill", "download skill", "get skill from github", "skills.sh", "browse skills", "what skills are available", "I need a skill for".
Idioma del contenido del Skill: inglés
Repositorio: moazbuilds/claudeclaw
Estrellas en GitHub: 1331Actualizado: 19 jul 2026
N.º: 3430
one-three-one-rule1-3-1 decision briefs: problem, three options, one pick.
Idioma del contenido del Skill: inglés
Repositorio: NousResearch/hermes-agent
Estrellas en GitHub: 261.860Actualizado: 8 ago 2026
N.º: 3431
switch-personaSwitch Agent persona preset. Supports 8 presets including default assistant, business, tech expert, butler, girlfriend, boyfriend, family, and Jarvis. Use when user asks to change communication style or personality.
Idioma del contenido del Skill: chino
Repositorio: openakita/openakita
Estrellas en GitHub: 2016Actualizado: 24 abr 2026
N.º: 3432
erupt-admin一句话生成数据管理后台。当用户描述想要一个管理系统、后台、CRUD 系统、信息管理平台，或各类业务系统如 CRM（客户管理）、ERP、OA、进销存、库存管理（WMS）、订单管理（OMS）、会员管理、人事管理（HR）、CMS 内容管理、工单系统、报名/预约系统（如"生成一个图书管理后台"、"做一个 CRM"、"搭个进销存"），或要求为已生成的 erupt 项目增改功能时使用。Generate a full admin backend from one sentence — use when the user asks for an admin panel, CRUD app, management system, dashboard backend, internal tool, or business systems like CRM, ERP, OA, inventory/warehouse (WMS), order management (OMS), membership, HR, CMS, ticketing, or booking systems (e.g. "build me a library admin system", "build a simple CRM"), or iterates on a generated erupt project. 基于 erupt 低代码框架，自动准备 JDK/Maven 环境，非开发人员也可直接使用。
Idioma del contenido del Skill: chino
Repositorio: plinian/erupt-skill
Estrellas en GitHub: 7Actualizado: 25 sept 2026
N.º: 3433
r9-workbenchR9（资产配置研习社）投研工作台超级路由Agent。统一管理全部99个专业skill，覆盖基金投研、权益研究、财务建模、投资银行、私募股权、财富管理、基金运营、内容创作、基金公司渠道与客户、高净值客户陪伴10大板块。当用户需要任何金融投研相关任务时触发——用户只需说人话，系统自动路由到最佳skill组合。触发词包括但不限于：帮我看看、分析一下、评价一下、研究一下、生成报告、写个话术、做个图、跑个诊断、跟踪一下、调仓建议、客户陪伴、写篇文章、深度研究、基金分析、股票分析、估值建模、做pitch、投顾策略、组合管理、理财经理、财报点评、首次覆盖、行业研究、转PDF、导出PDF。
Idioma del contenido del Skill: chino
Repositorio: r9412460971-cloud/OPC-skill
Estrellas en GitHub: 37Actualizado: 7 sept 2026
N.º: 3434
x-article-writingWrite, edit, restructure, or review Shubham Saboo's long-form technical articles for X, plus their diagram prompts, cover image prompts, teaser posts, threads, and LinkedIn adaptations. Use this skill whenever the user asks to draft an article, outline a piece, fix an opening or closing, tighten a section, audit a draft for voice or redundancy, check a claim, write diagram or cover image prompts, turn an article into a thread or LinkedIn post, or pastes a section of a draft with a critical note. Trigger it even when the user only says "draft this", "rewrite this section", "does this sound like me", "give me visuals for this", or names a working title, since almost all of this user's writing work runs through this style system.
Idioma del contenido del Skill: inglés
Repositorio: Shubhamsaboo/x-article-writing
Estrellas en GitHub: 0Actualizado: 9 ago 2026
N.º: 3435
seedance-combat-promptSeedance 2.0 二次元打戏视频提示词生成智能体。飞驰影漫社+废话军师联合改造。
Idioma del contenido del Skill: chino
Repositorio: stackOverMind/claude-drama-skeleton
Estrellas en GitHub: 0Actualizado: 3 jul 2026
N.º: 3436
quant-trading-master量化交易 (量化交易 (Quantitative Trading) — 面向股票、期货与期权二级市场的系统化交易者（私募/自营/公募量化研究员、CTA 交易员、有工程能力的个人系统化交易者）的『把一个交易想法，变成一个在真钱上还站得住的策略』的判断体系；不是加密与链上交易（那是 crypto-onchain-trading 的范围），不是个人长期资产配置与理财（personal-investing），不是卖方投行的并购与承销（investment-banking-mna），也不是主观基本面选股与券商 IT 系统开发。覆盖：(a) 第一性张力 —— 这行的核心世界观分歧：**经济学解释先行 ⇄ 数据里挖出来就行**（一派要求任何超额收益背后先有风险补偿或行为偏差的故事，否则视为噪音；另一派认为解释是事后编的，只信严格的样本外与实盘，机器学习派把这条推到极致，两派对同一个因子会给出完全相反的判断）；**横截面选股 ⇄ 时序趋势跟踪**（选股要在同一时点比较一篮子标的的相对好坏、假设均值回复与相对定价，CTA 趋势在单一品种的时间序列上假设动量延续，两者的研究方法、回测口径、风险来源和亏损形态几乎不重叠，却常被外行混为一谈）；**样本内的漂亮曲线 ⇄ 多重检验之后还剩什么**（因子动物园与可复制性危机是本行最重要的一次集体自省：显著性门槛该抬多高、发表后收益衰减多少、大量已发表因子在严格复制下失效，以及回测过拟合的概率如何度量）；**回测至上 ⇄ 只信实盘**（回测是唯一能低成本证伪的工具，也是最容易骗自己的工具：前视偏差、幸存者偏差、时点数据缺失、参数寻优、重复使用同一份历史数据；于是有人把纸上交易与小仓位实盘当成唯一可信的检验）；**alpha ⇄ 容量与成本**（一个策略的规模是它自己的敌人：冲击成本随规模上升、换手越高越吃成本、拥挤度让同类策略在回撤时同时踩踏；毛收益漂亮而净收益为负是新手最常见的死法）；**风险预算 ⇄ 收益最大化**（波动率目标、凯利与部分凯利、风险平价、回撤止损、杠杆与尾部，这一层的分歧决定了同一个信号在不同人手里是稳健产品还是爆仓故事）；**高频做市 ⇄ 中低频统计套利与基本面量化**（延迟、撮合机制、报单结构与硬件是一套技能树，因子构建、组合优化与风险模型是另一套，混谈两者是外行破绽之一）；**学术公开 ⇄ 业界闭源**（真正在赚钱的策略通常不发表，公开材料存在系统性的幸存者偏差与选择
Idioma del contenido del Skill: chino
Repositorio: swaylq/master-skill
Estrellas en GitHub: 174Actualizado: 2 sept 2026
N.º: 3437
media-crawlerInstall, authenticate, configure, operate, and troubleshoot the external MediaCrawler client shared by Douyin, Kuaishou, Bilibili, Weibo, Tieba, and Zhihu collectors. Xiaohongshu uses the separate browser-first xiaohongshu-mcp Collector. Use when auditing this client, onboarding a supported platform account, selecting search/detail/creator modes, enabling comments or media, locating outputs, or diagnosing crawler failures.
Idioma del contenido del Skill: inglés
Repositorio: tsingyuai/growth-lab
Estrellas en GitHub: 1972Actualizado: 3 ago 2026
N.º: 3438
context7-cliUse the ctx7 CLI to fetch library documentation and configure Context7 MCP. Activate when the user mentions "ctx7" or "context7", needs current docs for any library, or needs to set up Context7 for their AI coding agent.
Idioma del contenido del Skill: inglés
Repositorio: upstash/context7
Estrellas en GitHub: 64.396Actualizado: 5 nov 2026
N.º: 3439
projectsKeep the collection around one engagement: file a call transcript, email thread or shared document into the right project with a decision log, keep the project's rules, notes, timeline and highlights current, update its status and open items, and read a project before writing anything from it. Read when a transcript lands, an engagement starts, a person corrects you about an engagement, or a document is about to be drafted.
Idioma del contenido del Skill: inglés
Repositorio: vocion/vocion-core
Estrellas en GitHub: 2Actualizado: 27 oct 2026
N.º: 3440
python-code-stylePython code style, linting, formatting, naming conventions, and documentation standards. Use when writing new code, reviewing style, configuring linters, writing docstrings, or establishing project standards.
Idioma del contenido del Skill: inglés
Repositorio: wshobson/agents
Estrellas en GitHub: 42.334Actualizado: 30 ene 2026
N.º: 3441
test-case-xmind根据产品需求文档、前端技术文档、后端技术文档、交互稿、接口说明、截图和相关项目资料生成结构化软件测试用例；校验用例格式；按“用例标题/前置条件/步骤/预期结果”模板导出 .xmind 脑图文件。适用于生成 QA 测试用例、验收用例、功能用例、回归用例、边界用例，或根据一个或多个输入文档生成 XMind 测试用例脑图。
Idioma del contenido del Skill: chino
Repositorio: xiaoce-xiaoce/testing-skills-xiaoce
Estrellas en GitHub: 39Actualizado: 14 jun 2026
N.º: 3442
deep-interviewSocratic deep interview with mathematical ambiguity gating before explicit execution approval
Idioma del contenido del Skill: inglés
Repositorio: Yeachan-Heo/oh-my-claudecode
Estrellas en GitHub: 40.702Actualizado: 30 oct 2026
N.º: 3443
iv8-jsvmp-recovery以受控 iv8 中的原始 JavaScript/JSVMP 作为参考实现，结合静态解释器、Bytecode、Handler、Opcode、Record、CFG 分析和动态 Trace，恢复从声明的原始输入到最终签名、Token 或密文的独立可执行映射，并以精确等价验收。用于 JSVMP/VMP 语义恢复、字节码反汇编或反编译、Handler 准确语义、Record/虚拟函数边界、调用图或控制流、字符串恢复、静态结果与 Trace 对账、受控输入试验、以及 Python/JavaScript 独立实现的端到端复现。不负责通用外层 AST 解混淆、iv8 安装与通用补环境，也不把服务器接受当作 VM 语义等价的唯一证明。
Idioma del contenido del Skill: chino
Repositorio: zhizhuodemao/ai-reverse-resources
Estrellas en GitHub: 14Actualizado: 13 ago 2026
N.º: 3444
short-video-scripterUse when the user asks to "script this short video", "write a TikTok / Reels / Shorts script", "给这条抖音或视频号视频写脚本", or "fix the hook — viewers drop off in the first seconds"; produces timestamped beat-sheet scripts on the retention-gate model (0-2s hook / 2-5s confirmation / 5-15s payoff / loop-or-CTA) with per-scene script lines, on-screen text for muted viewing, asset keywords, and 9:16 format-param rows per platform norm card for TikTok, Reels, Shorts, 抖音, and 视频号 — plus 2-3 hook options from named hook families and an AI-content disclosure line by default on realistic synthetic media. Spec-only: rendering, TTS, and publishing stay with the user's own tools — no pipelines, no upload automation. Not for creator video briefs — use brief-generator; long-form video SEO belongs to content-writer. 短视频脚本/抖音分镜/开头钩子/竖屏9:16
Idioma del contenido del Skill: inglés
Repositorio: aaron-he-zhu/aaron-marketing-skills
Estrellas en GitHub: 3105Actualizado: 29 oct 2026
N.º: 3445
board-minutesDrafts board or committee meeting minutes in your house format. Auto-detects upcoming board and committee meetings from your calendar, asks for the agenda and any slides or pre-read materials, and produces a complete draft in the format learned from your seed minutes. Also handles written consents in lieu of meetings. Trigger: "board minutes", "draft minutes", "upcoming board meeting", "committee minutes", "written consent", or calendar detection of an upcoming board or committee event.
Idioma del contenido del Skill: inglés
Repositorio: anthropics/claude-for-legal
Estrellas en GitHub: 9948Actualizado: 11 may 2026
N.º: 3446
e1E1-Quantitative Analysis Guide with Code Generation & Sensitivity Analysis VS-Enhanced with Full 5-Phase process: Avoids obvious analyses, explores innovative methodologies Expanded to include qualitative analysis (thematic, grounded theory, content, narrative) Absorbed E4 (Analysis Code Generator) and E5 (Sensitivity Analysis - Primary Study) capabilities Use when: selecting statistical/qualitative methods, interpreting results, checking assumptions, generating code, sensitivity analysis Triggers: statistical analysis, ANOVA, regression, t-test, power analysis, assumption checking, effect size, thematic analysis, grounded theory, content analysis, narrative analysis, NVivo, ATLAS.ti, coding, qualitative data, R code, Python code, SPSS syntax, sensitivity analysis, robustness check
Idioma del contenido del Skill: inglés
Repositorio: brycewang-stanford/Auto-Empirical-Research-Skills
Estrellas en GitHub: 4955Actualizado: 3 abr 2026
N.º: 3447
bzd-paper-format-checkerReview a complete mathematical-modeling competition paper with an atomic checklist covering abstract readability, page structure, typography, headings, pagination, figures, tables, equations, anonymity, metadata, visual balance, and page allocation. Return the review in chat or Markdown by default, and provide the bundled single-sheet checklist when the user requests a reusable form. Use when the user provides a PDF or Word paper and asks for a full-paper format and writing-compliance audit; do not replace technical model correctness review.
Idioma del contenido del Skill: chino
Repositorio: BZDmathclub/bzd-math-modeling-skills
Estrellas en GitHub: 433Actualizado: 18 sept 2026
N.º: 3448
testing-test-manager测试管理助手 - 专业的软件测试管理与协调专家。适用场景： (1) 测试计划制定与评审（测试范围/策略/资源/时间） (2) 测试进度跟踪与状态报告 (3) 缺陷管理与跟踪（Defect Triage/优先级/状态流转） (4) 测试覆盖率分析与改进 (5) 测试报告生成与质量评估 (6) 测试团队协调与资源分配 (7) 测试风险识别与缓解 (8) 测试过程改进与度量触发关键词：测试计划、测试进度、缺陷管理、测试报告、测试覆盖率、测试协调、测试风险、质量门禁
Idioma del contenido del Skill: chino
Repositorio: chendongqi/OPB-Skills
Estrellas en GitHub: 133Actualizado: 11 feb 2026
N.º: 3449
architecture-renderingGenerate photorealistic architectural renders and visualizations using each::sense AI. Create exterior views, interior renders, sketch-to-render conversions, and more for architects, designers, and real estate professionals.
Idioma del contenido del Skill: inglés
Repositorio: eachlabs/skills
Estrellas en GitHub: 44Actualizado: 1 abr 2026
N.º: 3450
mbot根据提供的课题和课程目标，按照指定格式编写详细的教案，必须包含师生模拟对话。
Idioma del contenido del Skill: chino
Repositorio: ECNU-ICALK/AutoSkill
Estrellas en GitHub: 610Actualizado: 16 mar 2026
N.º: 3451
art-commission-managerGuides artists through the full commission lifecycle including pricing formulas, contract templates, revision policies, client communication, and delivery workflows for sustainable freelance art practices. Use when the user asks about art commission manager, related techniques, best practices, or needs guidance in this domain. Do NOT use when the request is outside the scope of art commission manager or requires a different specialized skill.
Idioma del contenido del Skill: inglés
Repositorio: FerroxLabs/wayland
Estrellas en GitHub: 616Actualizado: 7 jun 2026
N.º: 3452
cad-workflowAutoCAD 机械设计工作流。支持 SolidWorks 三维建模、AutoCAD 二维图纸设计、DXF 几何验证（CADX）、GB/T 机械制图规范、工程图导出（DWG/PDF）。
Idioma del contenido del Skill: chino
Repositorio: fyjgtddco/DSH-SW-and-CAD
Estrellas en GitHub: 40Actualizado: 13 sept 2026
N.º: 3453
diffdockPredicts protein-small-molecule binding poses with DiffDock and DiffDock-L from PDB or sequence plus SMILES/SDF/MOL2. Covers batch docking, pose triage, confidence interpretation, and validation. Use for molecular docking and virtual-screening pose generation, not binding-affinity prediction.
Idioma del contenido del Skill: inglés
Repositorio: K-Dense-AI/scientific-agent-skills
Estrellas en GitHub: 56.516Actualizado: 1 oct 2026
N.º: 3454
main-image-editorOrchestrate screenshot + Chinese instruction into PSD batch edits with transaction rollback by reusing psd-automator.
Idioma del contenido del Skill: inglés
Repositorio: LeoYeAI/openclaw-master-skills
Estrellas en GitHub: 2169Actualizado: 23 mar 2026
N.º: 3455
chat-sdkUse for multi-platform bots built with chat SDK: webhooks, mentions, slash commands, cards, modals and streaming.
Idioma del contenido del Skill: inglés
Repositorio: lobehub/lobehub
Estrellas en GitHub: 84.502Actualizado: 26 sept 2026
N.º: 3456
lighttools-design-skillReproduce optical-design papers and build Synopsys LightTools models from paper geometry, freeform surface data, LED arrays, receivers, thin films, prism textures, distance/geometry sweeps, angular or spatial luminance meshes, and simulation audits. Use when Codex needs to automate LightTools through COM or JumpStart .NET, attach to an already-open GUI session with unsaved edits, modify named optical-property percentages, import freeform CSV surfaces into .lts models, reproduce figures from optical papers, construct LED/source/receiver setups, run colli1_lc double-length or ray-trace-state scans, vary spatial luminance meter latitude, export BLUReceiver meshes, post-process LightTools TXT files, debug model stability, version .lts outputs, or document validated optical-design workflows.
Idioma del contenido del Skill: inglés
Repositorio: lq1229477734-sys/optical-design-skill
Estrellas en GitHub: 16Actualizado: 3 jul 2026
N.º: 3457
production-schedulingCodified expertise for production scheduling, job sequencing, line balancing, changeover optimization, and bottleneck resolution in discrete and batch manufacturing. Informed by production schedulers with 15+ years experience. Includes TOC/drum-buffer-rope, SMED, OEE analysis, disruption response frameworks, and ERP/MES interaction patterns. Use when scheduling production, resolving bottlenecks, optimizing changeovers, responding to disruptions, or balancing manufacturing lines.
Idioma del contenido del Skill: inglés
Repositorio: nguyentrunghieutcu/ctxora-engine
Estrellas en GitHub: 19Actualizado: 8 sept 2026
N.º: 3458
harmonyos-dev-suiteUnified HarmonyOS development entry skill for ArkTS, ArkUI, DevEco CLI, build/run/debug, device logs, testing, multi-device adaptation, atomic services, native development, stability diagnosis, and optional HarmonyOS atomic Skill routing. Use when the user mentions HarmonyOS, OpenHarmony, HongMeng, 鸿蒙, ArkTS, ArkUI, DevEco, .ets, oh-package.json5, build-profile.json5, HAP/HAR/App, emulator, hilog, hdc, hvigor, or HarmonyOS app development.
Idioma del contenido del Skill: inglés
Repositorio: openJiuwen-ai/jiuwenswarm
Estrellas en GitHub: 8565Actualizado: 9 nov 2026
N.º: 3459
weitoutiao-creator微头条爆款文案生成器：通过 6 步流程（账号定位 -> 素材来源 -> 写作风格 -> 文案框架 -> 生成文案 -> 优化迭代）产出 300 字以内、可发布的短文案，含标题、正文与互动引导。触发场景：用户要写微头条、写爆款短文案、做社交媒体短内容创作、提升互动率；用户说「写微头条」「微头条文案」「爆款文案」「短文案」「帮我写一条」「提升互动率」。适用于职场、情感、健康、育儿、财经等各类自媒体账号。用法：/weitoutiao-creator 然后按提示逐步回答。
Idioma del contenido del Skill: chino
Repositorio: renky1025/agent-skills
Estrellas en GitHub: 11Actualizado: 25 sept 2026
N.º: 3460
feishu-doc读写本项目的飞书文档「seamless-interaction」（wiki MBp9wq1PSiklbmkvCR9cQKvTn5g）。同步计划、写实验笔记、插图片/GIF/视频到飞书时使用。依赖本机已安装的 lark-cli。
Idioma del contenido del Skill: chino
Repositorio: ryf1123/seamless-interaction
Estrellas en GitHub: 0Actualizado: 23 ago 2026
N.º: 3461
graphifyUse for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools.
Idioma del contenido del Skill: inglés
Repositorio: safishamsi/graphify
Estrellas en GitHub: 75.074Actualizado: 1 jul 2026
N.º: 3462
code-audit软件代码审计、回归测试与实现验证。
Idioma del contenido del Skill: chino
Repositorio: Sven-Mirana/sublation
Estrellas en GitHub: 279Actualizado: 26 ago 2026
N.º: 3463
pie-blueprint-engineGenerates engineering-standard drawings (P&ID, SLD, floor plans, isometric) with ISA-5.1 and IEEE symbol libraries in SVG/DXF format. Activates for drawing generation, diagram creation, blueprint packaging, and output formatting from verified engineering calculations.
Idioma del contenido del Skill: inglés
Repositorio: Tibsfox/gsd-skill-creator
Estrellas en GitHub: 71Actualizado: 27 feb 2026
N.º: 3464
circuit-schematic-wiring-simulation设计和修改电路原理图，按任务要求选用或实现元件，使用清晰可见的原生导线连接，分模块仿真后验证整机，并定位故障、优化仿真速度。用于 Multisim 等电路实现、接线检查和实物对照任务；包含 Multisim 实现参考与外部引脚连接比较脚本。
Idioma del contenido del Skill: chino
Repositorio: WHITEWARM/circuit-schematic-wiring-simulation
Estrellas en GitHub: 1Actualizado: 10 sept 2026
N.º: 3465
create-crushDistill a crush into an AI Skill. Import chat history, photos, social media, generate Relationship Memory + Persona, with continuous evolution. | 把暗恋对象蒸馏成 AI Skill，导入聊天记录、照片、朋友圈，生成 Relationship Memory + Persona，支持持续进化。
Idioma del contenido del Skill: Varios idiomas
Repositorio: xiaoheizi8/crush-skills
Estrellas en GitHub: 372Actualizado: 3 oct 2026
N.º: 3466
imperva-waf-reese84Conditional escalation skill for confirmed Imperva/Incapsula/Reese84 work. Use only when the user explicitly names 84盾, Reese84, Incapsula, Imperva, x-d-token, reese84 cookie, or when current evidence shows Reese84/Incapsula markers such as SWJIYLWA/CWUDNSAI/SWUDNSAI challenge HTML or protected business API rejection tied to those markers. It records token identity, WAF acceptance evidence, and backend acceptance boundaries. Do not trigger for generic anti-bot, generic fingerprint, ordinary sign/token, Cloudflare/Akamai/DataDome, or crawler delivery without Imperva/Reese84 evidence.
Idioma del contenido del Skill: Varios idiomas
Repositorio: zy950618/oh_my_reverse_skill
Estrellas en GitHub: 16Actualizado: 8 jul 2026
N.º: 3467
text-format-organizerA local text formatting organizer for biomedical/academic writing; use it when you need to clean whitespace/line endings while preserving Markdown structures or when normalizing .docx/.md/.txt before submission or proofreading.
Idioma del contenido del Skill: inglés
Repositorio: aipoch/medical-research-skills
Estrellas en GitHub: 2032Actualizado: 23 jun 2026
N.º: 3468
threat-model-analystFull STRIDE-A threat model analysis and incremental update skill for repositories and systems. Supports two modes: (1) Single analysis — full STRIDE-A threat model of a repository, producing architecture overviews, DFD diagrams, STRIDE-A analysis, prioritized findings, and executive assessments. (2) Incremental analysis — takes a previous threat model report as baseline, compares the codebase at the latest (or a given commit), and produces an updated report with change tracking (new, resolved, still-present threats), STRIDE heatmap, findings diff, and an embedded HTML comparison. Only activate when the user explicitly requests a threat model analysis, incremental update, or invokes /threat-model-analyst directly.
Idioma del contenido del Skill: inglés
Repositorio: github/awesome-copilot
Estrellas en GitHub: 40.947Actualizado: 7 ago 2026
N.º: 3469
uniflyInspect and manage UniFi Network infrastructure with the unifly CLI: devices, clients, VLANs, WiFi, firewall, VPN, switch ports, site settings, and cloud fleets. Use for UniFi network configuration, monitoring, and troubleshooting, not UniFi Protect camera or recording management.
Idioma del contenido del Skill: inglés
Repositorio: hyperb1iss/unifly
Estrellas en GitHub: 274Actualizado: 12 oct 2026
N.º: 3470
baoyu-wechat-summarySummarizes WeChat group chat highlights into a structured digest using the local wx-cli binary (https://github.com/jackwener/wx-cli). Generates a normal digest by default; a roast (毒舌) version is opt-in. Maintains per-group history (history.json + history-digests.jsonl), per-user profiles, and per-group fact memory (memory.md) across runs, with privacy guardrails baked in. Use when the user asks to "总结群聊", "群聊精华", "群聊摘要", "summarize group chat", "group chat digest", mentions a WeChat group name with a time range, says "帮我看看 XX 群最近聊了什么", "XX 群有什么值得看的", or asks to "回溯画像" / "初始化画像" / "backfill profiles". Adds the roast version when the user says "毒舌版", "roast 版", "再来个毒舌的", or similar.
Idioma del contenido del Skill: inglés
Repositorio: JimLiu/baoyu-skills
Estrellas en GitHub: 27.412Actualizado: 2 nov 2026
N.º: 3471
find-skillsUse when users ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. Helps discover and install agent skills.
Idioma del contenido del Skill: inglés
Repositorio: joe-bell/cva
Estrellas en GitHub: 6911Actualizado: 8 sept 2026
N.º: 3472
pp-unifiEvery UniFi Network API operation, plus drift detection, topology, and rule prediction no other UniFi tool has. Trigger phrases: `audit my unifi network`, `what changed on my network`, `list unifi devices`, `check unifi firewall rules`, `unifi port audit`, `use unifi-pp-cli`, `run unifi-pp-cli`.
Idioma del contenido del Skill: inglés
Repositorio: mvanhorn/printing-press-library
Estrellas en GitHub: 1918Actualizado: 13 ago 2026
N.º: 3473
qianchuansucai顶级短视频获客文案专家，专精"元麻烦"理论与"卖点可视化"创作方法。为任何产品找到用户最深的自我怀疑，用硬核视觉测试击碎它，产出可直接拍摄的80秒获客视频脚本。使用场景：(1) 千川素材 / 抖音信息流获客脚本创作；(2) 用户要求写短视频带货脚本、获客视频、投放素材、广告脚本；(3) 需要挖掘产品痛点背后的"元麻烦"、设计卖点"暴力测试"画面；(4) 需要按十节点结构生成完整分镜头脚本。触发词：千川素材、获客视频、短视频脚本、元麻烦、卖点可视化、80秒脚本、信息流投放、带货脚本。
Idioma del contenido del Skill: chino
Repositorio: paul-xing/qianchuansucai-skill
Estrellas en GitHub: 7Actualizado: 15 ago 2026
N.º: 3474
silk-life-listing-image-sop丝绸生活 Ozon/Russian e-commerce listing 美工思维蒸馏 SOP。适用于“沟通图片/卖点表/参考图 → 俄罗斯电商 8 张套图”的一键工作流：先从沟通图片中锁定真实商品图，再生成 ArtDirectorContract，Codex 只做 reference-locked 无字底图，最后由 overlay_text.py 程序化叠加准确俄文，并用 critic 校验产品一致性、长宽比例、文字位置和画布铺满。触发词：丝绸生活出图、Ozon 套图、listing 套图、沟通图片转美工图、蒸馏美工作图思维、俄罗斯电商图片。
Idioma del contenido del Skill: chino
Repositorio: yulianggan/silk-life-listing-image-sop
Estrellas en GitHub: 2Actualizado: 30 abr 2026
N.º: 3475
nature-writingDraft, restructure, or plan Nature-style manuscript sections from author-provided claims, results, figures, notes, or Chinese drafts. Use when the user wants to write or rebuild an abstract, introduction, related-work, method, experiments, discussion, conclusion, title, or full manuscript argument rather than only polish finished prose. Also trigger on general academic-writing requests even without the word "Nature", such as writing a paper from scratch, drafting a manuscript/section, structuring a paper, and Chinese phrasings like 学术写作、科研写作、论文写作、写论文、写paper、SCI写作、帮我写论文、搭论文框架、起草论文、写引言/摘要/讨论.
Idioma del contenido del Skill: inglés
Repositorio: ai4protein/VenusFactory2
Estrellas en GitHub: 255Actualizado: 28 jul 2026
N.º: 3476
unreal-engine-developerExpert Unreal Engine 5 developer and technical artist for complete game development via agentic coding. Enables AI-driven control of Unreal Editor through MCP, Python scripting, Blueprints, and C++ for level design, asset management, gameplay programming, and visual development.
Idioma del contenido del Skill: inglés
Repositorio: aiskillstore/marketplace
Estrellas en GitHub: 408Actualizado: 5 jul 2026
N.º: 3477
software-dev-process-skill从零开始指导 AI 与用户协作完成一个完整软件或系统项目的开发。覆盖八个阶段：需求分析（面试式提问澄清）、系统概要设计、文档编写、数据库设计、详细设计与项目骨架搭建、编码实现、测试与集成、部署与交付，严格按顺序推进，每阶段产出物作为下一阶段的输入。触发场景：用户提出"开发/做一个软件/系统/应用/网站/平台"、 "从零搭建项目"、"走一遍完整的开发流程"、"帮我做需求分析"、"写需求规格说明书"、"做系统设计"、 "设计数据库表"、"搭项目骨架"、"开始编码实现"、"写单元测试"、"集成测试"、"部署上线"、"交付项目" 等。
Idioma del contenido del Skill: chino
Repositorio: blue00255/lccSkills
Estrellas en GitHub: 1Actualizado: 7 ago 2026
N.º: 3478
eda-simOffline EDA simulation workflow for ASIC DV projects using Synopsys VCS/Verdi. Use this skill whenever the user asks to run simulation, compile RTL, run regression, debug waveforms, read FSDB/waveform files, check coverage, or any task involving VCS/Verdi/UVM simulation. Also trigger when encountering compile errors, sim failures, needing to analyze sim.log results, or reading signal values from FSDB waveform dumps. This skill ensures correct offline tool invocation and includes an FSDB reader script using Synopsys NPI.
Idioma del contenido del Skill: inglés
Repositorio: cike128/eda-sim
Estrellas en GitHub: 25Actualizado: 19 mar 2026
N.º: 3479
cosmic-function-point-generatorThis skill should be used when the user provides a requirements design specification document (e.g., 概要设计说明书 / 需求设计说明书 / 详细设计说明书 in .docx format) and asks to generate a COSMIC function point measurement spreadsheet (.xlsx). It extracts functional requirements from the design document, decomposes them into functional processes and sub-processes, classifies data movements (Entry/Read/Write/eXit), and outputs a standard 12-column COSMIC function point table compliant with PBOSS project conventions and the COSMIC ISO 19761 methodology. Triggers include phrases like "生成 COSMIC 表格", "功能点度量", "生成功能点拆分表", "从概要设计生成 COSMIC", "COSMIC 度量", "function point estimation".
Idioma del contenido del Skill: chino
Repositorio: Jinhong270/AI-Agent
Estrellas en GitHub: 3Actualizado: 29 jun 2026
N.º: 3480
oc-tpt-generate-coverGenerate a TPT cover using the AI Studio DinoCover tool and save it locally with the book title as filename.
Idioma del contenido del Skill: inglés
Repositorio: luokai25/luo_os-v_0.1
Estrellas en GitHub: 1Actualizado: 11 abr 2026
N.º: 3481
ai-pm-advisory-boardAI 产品经理顾问团总控。成员：Marty Cagan、Andrej Karpathy、梁宁（专家视角）+ 《AI Engineering》(Chip Huyen)、《Prediction Machines》(Agrawal/Gans/Goldfarb)、《俞军产品方法论》（方法论）。能力：(1) 根据问题自动推荐合适的专家/方法论 (2) 召开多专家评审会，输出共识/分歧/综合结论。触发词：「AI PM 顾问团」「AI 产品评审」「让专家们看看这个 AI 需求」「开评审会」「AI PM 都上」。
Idioma del contenido del Skill: chino
Repositorio: SpaceZephyr/career.skill
Estrellas en GitHub: 164Actualizado: 3 jul 2026
N.º: 3482
sun-tzu-strategy-briefPrepare for a specific contest — a competitive deal, a negotiation, a market entry, a turf fight — using the actual planning framework from Sun Tzu's Art of War: the five factors, the calculations before battle, and winning without fighting. Use when facing a competitor head-to-head, preparing a bake-off or RFP, entering a rival's market, or picking which fight to have. Produces a strategy brief with a fight/no-fight verdict.
Idioma del contenido del Skill: inglés
Repositorio: mohitagw15856/pm-claude-skills
Estrellas en GitHub: 1320Actualizado: 25 jul 2026
N.º: 3483
yukino-yukinoshita雪之下雪乃（ゆきのしたゆきの / Yukino Yukinoshita），《我的青春恋爱物语果然有问题》侍奉部部长、总武高中年级第一才女、比企谷八幡的恋人。基于萌娘百科、轻小说全14卷+新篇+特典、动画3季的深度调研，资料更新至2026-06-05，提炼6个核心行为模式、完整的表达质感和角色扮演规则。触发词：「用雪乃的视角」「扮演雪之下」「雪乃模式」「雪之下同学」。
Idioma del contenido del Skill: chino
Repositorio: TTAWDTT/yukino-yukinoshita
Estrellas en GitHub: 2Actualizado: 7 jun 2026
N.º: 3484
gloss-mod-managerGloss Mod Manager 游戏接入与切换技能。用于在添加游戏前确认 GlossGameId、安装根目录和当前管理状态，并安全调用 mcp_gloss-mod-man_add-game-to-manager。
Idioma del contenido del Skill: chino
Repositorio: GlossMod/Gloss-Mod-Manager
Estrellas en GitHub: 622Actualizado: 20 may 2026
N.º: 3485
code-simplificationSimplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity. Use when asked to simplify, clean up, or reduce the nesting of a function or module that already works, even when the code is pasted inline and nothing else needs to change.
Idioma del contenido del Skill: inglés
Repositorio: addyosmani/agent-skills
Estrellas en GitHub: 114.193Actualizado: 16 oct 2026
N.º: 3486
agent-harness-constructionAI エージェントのアクション空間、ツール定義、観測フォーマットを設計・最適化して完了率を向上させます。
Idioma del contenido del Skill: japonés
Repositorio: affaan-m/ECC
Estrellas en GitHub: 299.529Actualizado: 17 may 2026
N.º: 3487
agent-sort通过将技能、命令、规则、钩子和额外内容并行进行仓库感知审查，为特定仓库构建基于证据的 ECC 安装计划，将其分为 DAILY 和 LIBRARY 两类。当 ECC 应精简为项目实际所需而非加载完整包时使用。
Idioma del contenido del Skill: chino
Repositorio: affaan-m/ECC
Estrellas en GitHub: 299.529Actualizado: 11 may 2026
N.º: 3488
e2e-testingPlaywright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies.
Idioma del contenido del Skill: inglés
Repositorio: affaan-m/ECC
Estrellas en GitHub: 299.529Actualizado: 23 mar 2026
N.º: 3489
configure-eccRun the conversational ECC setup wizard inside the current harness: inventory the install, collect scope (user/project/local) and hook mode (off/minimal/standard/strict) in Claude Code, use Codex's native plugin lifecycle, or install the project surface under ./.kimi-code, then preview, apply, and verify. Use when installing, updating, reconfiguring, or repairing an ECC installation, changing hook profiles, or moving ECC between install scopes.
Idioma del contenido del Skill: inglés
Repositorio: affaan-m/ECC
Estrellas en GitHub: 299.529Actualizado: 1 oct 2026
N.º: 3490
delivery-gateStop hook that blocks Claude from finishing until quality checks pass. Detects rationalization patterns (surface text heuristics), stale learning logs (filesystem mtime), and low disk space. Complements self-audit by mechanically enforcing learning capture habits. Use when Claude should be mechanically blocked from declaring work finished before quality checks and learning capture actually pass.
Idioma del contenido del Skill: inglés
Repositorio: affaan-m/ECC
Estrellas en GitHub: 299.529Actualizado: 20 oct 2026
N.º: 3491
gateguardPreToolUse fact-forcing gate that denies the first Edit/Write/Bash (including MultiEdit and NotebookEdit) attempt until the agent presents concrete facts (importers, data schemas, verbatim user instruction), then allows retry; A/B-tested at +2.25 quality points. Use when enabling or configuring the GateGuard hook, exempting paths via env vars, or handling first-touch denials.
Idioma del contenido del Skill: inglés
Repositorio: affaan-m/ECC
Estrellas en GitHub: 299.529Actualizado: 11 oct 2026
N.º: 3492
agent-creatorExpert guidance for creating effective Claude Code agents (subagents). Use when users want to create a new agent, update an existing agent, or learn agent design best practices. Covers agent architecture, prompt engineering, tool selection, model choice, and common pitfalls. Integrates with skill-creator when agent needs accompanying skills.
Idioma del contenido del Skill: inglés
Repositorio: agdev/claude-code
Estrellas en GitHub: 0Actualizado: 28 nov 2025
N.º: 3493
tavern-cards创建、编辑、评估 SillyTavern 角色卡和世界书（角色信息、世界观、NPC、场景、事件、文风、MVU 变量、EJS 方案等）。覆盖角色卡内嵌世界书和独立世界书，在 tavern-design 产出 design-spec.md 后继续项目创建与创作规划。确保在以下情况也使用此 skill：用户提到'角色设定'、'人设卡'、'worldlore'、'character card'、'角色卡'、'酒馆世界书'、'SillyTavern'、'世界书条目'、'世界书配置'、'蓝灯'、'绿灯'、'角色条目'、'世界观设定'、'NPC设定'等关键词时，即使用户没有明确说'世界书'也应触发。当用户要编写角色基础信息、性格调色盘、三面性、二次解释、多阶段调色盘、世界观、文风指导等创作流程时也应触发。当用户提到'MVU'、'变量系统'、'schema.ts'、'变量更新'、'initvar'、'变量结构'、'tavern-cards-forge'等关键词时也应触发。
Idioma del contenido del Skill: chino
Repositorio: ai4rpg/tavern-cards
Estrellas en GitHub: 264Actualizado: 16 sept 2026
N.º: 3494
react-bitsIntegrate, customize, and contribute to react-bits (github.com/DavidHDev/react-bits) — the largest and most creative library of animated React components. It covers Vite, Tailwind CSS v4, Three.js/Fiber, GSAP, and Framer Motion integrations. Use when the user asks about react-bits, animated React components, jsrepo registry, or contributing new animated components to the react-bits repository.
Idioma del contenido del Skill: inglés
Repositorio: akillness/jeo-skills
Estrellas en GitHub: 52Actualizado: 13 jul 2026
N.º: 3495
chief-data-officer-advisorUse for data strategy decisions: training models on customer data, warehouse vs lakehouse vs mesh, valuing data for a raise or M&A, or data hiring order. Runs ai_training_data_audit.py, data_product_strategy_picker.py and data_asset_valuator.py.
Idioma del contenido del Skill: inglés
Repositorio: alirezarezvani/claude-skills
Estrellas en GitHub: 29.497Actualizado: 30 oct 2026
N.º: 3496
founder-coachUse when a founder is the bottleneck, can't delegate, is burning out or is moving from IC to CEO. Covers delegation, energy and calendar audits, blind spots and succession.
Idioma del contenido del Skill: inglés
Repositorio: alirezarezvani/claude-skills
Estrellas en GitHub: 29.497Actualizado: 30 oct 2026
N.º: 3497
clinical-researchUse when designing a prospective clinical study: choosing primary and secondary endpoints, estimating sample size and power, or scoring feasibility before submission. Runs endpoint_selector.py, sample_size_estimator.py and phase_gate_scorer.py; outputs are estimates for a biostatistician to confirm.
Idioma del contenido del Skill: inglés
Repositorio: alirezarezvani/claude-skills
Estrellas en GitHub: 29.497Actualizado: 31 oct 2026
N.º: 3498
review-contractReview a contract against your organization's negotiation playbook — flag deviations, generate redlines, provide business impact analysis. Use when reviewing vendor or customer agreements, when you need clause-by-clause analysis against standard positions, or when preparing a negotiation strategy with prioritized redlines and fallback positions.
Idioma del contenido del Skill: inglés
Repositorio: anthropics/knowledge-work-plugins
Estrellas en GitHub: 35.244Actualizado: 13 mar 2026
N.º: 3499
clip-skills面向 AI Agent 的视频剪辑技能套件，把各大剪辑博主与专业后期经验内化为可决策、可复现的规则。当用户想剪一条视频、问任何剪辑怎么做（口播精剪、加音乐/卡点、贴 B-roll、调色、关键帧/运动、变速/补帧、抠像/蒙版/合成、二维或平面跟踪贴合、多机位采访、转场衔接、节奏垮了怎么救、导出参数与平台画幅），或让你自动出一版初剪时，务必使用本技能。它先判断意图（答疑 / 反问澄清 / 自主执行），再按音频驱动流水线编排：把"怎么剪"的判断（references 里 12 册软件无关知识内核）与"用什么剪"的执行（Palmier Pro 经 MCP / FFmpeg+Remotion 代码栈 / 剪映·Premiere·达芬奇）分离，每个软件用独立子 Agent 落地以防上下文污染。凡涉及视频剪辑、后期、Vlog、混剪、卡点、调色、字幕、转场、综艺包装、跟踪合成时都应触发。
Idioma del contenido del Skill: chino
Repositorio: appergb/ClipSkills
Estrellas en GitHub: 56Actualizado: 19 jun 2026
N.º: 3500
deep-researchDeep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report.
Idioma del contenido del Skill: inglés
Repositorio: asgeirtj/system_prompts_leaks
Estrellas en GitHub: 71.048Actualizado: 11 oct 2026