Recently Added
Fresh skills just added to the collection. Be the first to try them out!
visio-style-diagram
by getfunWindz
Generate Visio-style software engineering diagrams via draw.io Desktop. Use when user asks for: Visio风格图 / 数据库ER图 / 实体关系图 / 类图 / 架构图 / draw.io图 / 软件工程图 / 数据库设计图 / 系统部署图 / 数据流图 / DFD / 程序流程图 / N-S盒图 / Nassi-Shneiderman / 盒图 / UML图 / UML用例图 / UML状态图 / UML时序图 / 用例图 / 状态图 / 时序图 / 活动图 / 泳道图 / 跨职能流程图 / 软件工程图规范. Requires draw.io Desktop installed at C:\Program Files\draw.io\draw.io.
css-specificity-cli
by kea0811
Use when the user wants to audit, visualize, or gate CSS selector specificity — "which selectors are too specific", "specificity heat map", "fail CI when specificity is too high". A Node 18+ CLI that reads a CSS file and prints each selector's (a,b,c) specificity, sorted hottest-first, with a --threshold budget gate. Also exposes computeSpecificity/parseSelectors as a library.
cms-vfm
by cmr5hp4pp7-hub
This skill should be used when the user wants to "generate consistent video content", "maintain character appearance across shots", "edit character design sheet", "create scene environment specs", "manage video production consistency", "update character wardrobe bible", "track visual coherence rules", "design character proportions", or "build video generation reference documents" using the CMS-VFM (Character Model Sheet of Video Foundation Model) specification system.
挖财收支图片导入技能
by jeiner87
skill 解析含收支记录的图片（截屏/拍屏）并自动导入挖财APP
si-coder
by rahmanef63
"Zero human involvement full-stack deployment. Umbrella skill that points to modular sc-* sub-skills (sc-all, sc-dokploy, sc-convex, sc-convex-cloud, sc-vercel, sc-git, sc-onboarding) plus the legacy monolithic deploy.js. Two deploy paths share one flow shape: self-hosted (Dokploy app + self-hosted Convex) and online (Vercel frontend + Convex Cloud). The user can invoke /sc-all for end-to-end (--target dokploy vercel), /sc-convex/-cloud, /sc-vercel, or /sc-dokploy for narrower domain ops, /sc-git for GitHub repo/Actions ops, or /sc-onboarding to set up credentials."
latex-forge
by zhouder
Convert Microsoft Word .docx files and PDF .pdf files into compilable LaTeX projects. Use when Codex needs to transform DOCX/PDF sources into a project containing main.tex, figures/, references.bib, and a conversion report while preserving headings, lists, tables, equations, footnotes, images, captions, and Chinese document support with ctexart or xeCJK. Also use to inspect PDFs for extractable text and stop with an OCR-required message for scanned/image-only PDFs.
datum
by gitrdunhq
Automates the full software delivery cycle — brief to merged PR to closeout. Triggers: "datum go", "datum yolo", "datum <phase>", "datum resume", "datum status", "datum init", "run the epic", "start the development cycle", "let's implement this spec". Also activates when docs/epics//TICKET.md, docs/epics//SPEC.md, or TASKS.md is present.
name-candidate-generator
by NexaScience
AI/テック系のサービス名・プロダクト名・ブランド名の候補を、命名技法(造語・音象徴・語根・接尾辞パターン等)を 使って多数生成し、読み(カナ)・由来・タイプ付きの構造化リストで返すスキル。 ユーザーが「名前を考えて/出して/生成して」「ネーミング」「サービス名/プロダクト名/ブランド名の候補を出して」「命名」「名前案」 「いい名前ない?」など “まだ候補を作る” 段階の依頼をしたら必ずこのスキルを使う。 これは“生成”専用。商標/ドメイン/SNSの空き調査はしない（「使えるか調べて」「空き確認」「商標チェック」は brand-name-availability スキルの役割）。 生成後は人間がショートリストを選び、その後 brand-name-availability で調査する流れ。
ppt-master
by fanzhengxing
AI-driven PPT generation — converts PDF/DOCX/Markdown/URL/text topic into native editable .pptx presentations. SVG→DrawingML pipeline (ppt-master-enhanced). Multi-role collaboration: Strategist (content planning) → Executor (SVG authoring) → Post-processing (native PPTX export). Works on Hermes, Claude Code, Codex, OpenClaw, and any skill-compatible runtime. Trigger: "create PPT", "make presentation", "生成PPT", "做PPT", "制作演示文稿", "做个PPT", "ppt-master". Do NOT use for: quick text→pptx without layout needs (use officecli-pptx instead), reading/analyzing existing .pptx content (use the powerpoint skill instead).
orange-line-illustration
by orange2ai
Generate New Yorker-style minimalist editorial illustrations — thin black ink lines on white, vast negative space, a single orange accent (#F97316) — for articles, principles, covers, and concept visuals. Use when the user asks for 配图, 插图, 封面图, editorial illustrations, concept/metaphor illustrations, article covers, 公众号配图, principle/maxim illustrations, or mentions "橙线风格" / "orange line style" / "纽约客风格插图". Works with any image generation tool that accepts text prompts.
data-analysis-ai-evaluator
by anitachenchen331
设计和运行数据分析类 AI 产品评测，适用于数据问答、查询生成、语义层工具、图表生成、看板生成、异动诊断、归因分析、自动报告、权限治理和完整产品链路评估。使用时先根据用户提供的产品名称或链接调研公开产品能力，再通过人在回路确认评测目标、实验组、数据场景、问题矩阵、评分体系，随后生成评测资产、隔离实验提示词、标准答案和评分报告，并在用户确认后沉淀通用经验。
浪浪虎
by Ninawang07
Use when the user wants to plan a travel route (self-driving, cycling, hiking, motorcycle) and visualize it as an interactive web map. Triggers on "路线规划", "自驾路线", "行程地图", "road trip", "骑行路线", "徒步路线", "出境自驾", "路线可视化". Supports domestic and international travel with multi-route comparison, key node filtering, map customization, and one-click web deployment.
ecommerce-store-designer
by russodope
Design and generate e-commerce store homepage / decoration module images for any online-store platform. Use this skill whenever a user wants to: - Design an online store homepage or decoration (店铺装修 / 首页装修 / 店铺首页) - Create store banner images, series showcases, category navigation, or brand story sections - Build a modular store-design tool in HTML that exports module images at a user-specified width - Design e-commerce product showcase / homepage pages for any platform - Create a customizable store template for different brands Trigger on "店铺装修", "店铺首页", "首页设计", "banner", "详情页", "电商装修", "store/shop decoration", or "store homepage" alongside design or image-generation requests. ⚠️ The skill FIRST asks the user for the target image size (platform / 出图宽度), then designs at a 1440px internal reference and exports at the user's width.
TikTok → YouTube Automation — Skill Reference
by zahraishandsome-svg
exists for the same channel+slot.
faqmd
by danielcurran
"Use when the user asks to convert a GameFAQs walkthrough to markdown, scrape a GameFAQs FAQ/guide, or create hyperlinked walkthrough files. Trigger keywords: gamefaqs, walkthrough, faqdown, faq, guide, scrape, convert, markdown, FAQ, print=1."
yingzao
by songshishuang
营造——把团队任何岗位"能用"的 Agent Skill 按统一标准量出差距、打磨到"能交付/能发布"。双档：查勘（10 分钟只读体检，出一页报告）/ 大修（七步全流程打磨，含实测验证门）。触发词包括："打磨 skill" "体检 skill" "查勘 <skill>" "大修 <skill>" "升级我的 skill" "skill 评分" "这个 skill 能发布吗" "发布前检查" "比样" "多候选打磨" "落架" "推倒重写" "用营造打磨" "营造工坊" "岁修营造" "skill 出师" "帮同事看看这个 skill"。（"营造"裸词不触发——日常语境如"营造氛围"高频，需与 skill/打磨语境共现）不要用于：从零创建新 skill（用 skill-creator）；打磨非 skill 文档（PRD/README 单独优化用对应工具）；目标不是 Agent Skill 形态的提示词碎片。
nature-paper-to-patent
by Yuan1z0825
Convert scientific papers, theses, technical reports, source code, figures, or research manuscripts into evidence-grounded Chinese invention patent drafts. Use when an AI agent must extract patentable technical contributions, map every claimed feature to source evidence, preserve core formulas as editable Office Math, generate claim-aligned flowcharts and methodology figures, compare a paper with an existing patent, audit support and consistency, or deliver separate Chinese DOCX files for claims, specification, abstract, and abstract figure.
skill-fog
by pabang0620
대화 중 반복 요청 패턴을 자동 감지하여 스킬/커맨드/에이전트 생성을 제안하는 스킬. 매 5번째 메시지마다 자동 실행되며, 동일 패턴이 3회 이상·2개 이상 세션에서 감지될 때 즉시 제안한다. 사용자가 /skill-fog를 명시적으로 호출하거나 세션 시작 시 pending 패턴이 있을 때도 활성화된다.
critical-thinking-for-humans
by Imbad0202
Trains the HUMAN user's critical thinking through four modes: drill (argument-analysis items with a single defensible answer, judge stance), scene (Socratic exploration of synthetic scenes or user-supplied material, no verdicts on interpretations), expedition (guided audit of impossible-tier problems from verified packs), and detective (a runtime-generated multi-layer case worked as an escape room, guide-and-judge stance). Use when the user wants to practice critical thinking, analyze arguments, hunt assumptions, examine bias, or train reasoning. Triggers: critical thinking practice, train my thinking, drill, scene, byom, spot manipulation tactics, scam literacy, 批判思考練習, 話術辨識, detective, 查案, 破案, 偵探.
make-widescreen-highlight
by JieJessica
Convert vertical or non-16:9 videos into 16:9 widescreen highlight clips with a blurred full-frame background and the original video centered on top. Use when the user asks to make a video widescreen, add a blurred background, keep the original clip centered, preserve audio, extract a 10-second highlight, create social-media landscape output, or process MP4/MOV video files from Downloads or another local folder.
create-product-teams-reliable-workflows-fixing-mobile
by Kyro-Ma
Help users with Validated demand: Product teams need reliable workflows for fixing mobile responsiveness, navigation layout, and cross-device UI issues. This requirement is supported by 7 separate online signals across 1 source families, so it represents broader demand rather than a single isolated request.. Use when a user asks for creative-and-content, mobile responsive, responsive design, navbar, layout, or needs a practical workflow, artifact, checklist, analysis, or implementation support for this requirement.
omnata-plugin-development
by omnata-labs
"Guide for building plugins/connectors for the Omnata Sync Engine on Snowflake. Use when: creating a new Omnata plugin, modifying an existing plugin procedure, debugging plugin behavior, deploying plugin changes. Triggers: omnata plugin, omnata connector, build plugin, create plugin, plugin development, omnata procedure, connection form, sync engine plugin."
bazi-ziwei
by Goldentrii
八字 + 紫微斗数 AI 排盘与综合分析。当用户提供生辰（阳历/农历日期、时辰、性别）询问八字、紫微、命理、命盘、流年大运相关问题时使用。基于 Yiqi 算法库 + enrichBazi 补全层精准排盘（杜绝 LLM 自行排盘出错），支持按需独立分析八字 / 独立分析紫微 / 两盘交叉印证。
envi-dashboard
by dookda
Expert context for the Envi Dashboard project — Next.js config, basePath prefix, database schema, .env variables, Docker services, IoT API parameter codes, and alert pipeline. Use when working in the envi_dashboard repo.