The catalog
609,344 rows, by stacks then stars
thisistoni/treatwell-booking-agent-skill/skills/booking-treatwell Skill
1★ repoFinds Treatwell salon services, resolves service options, checks real-time appointment availability, prepares verified checkout, and places real appointments through a browser as soon as the customer chooses a specific offered slot. Use when a customer asks about a Treatwell salon's treatments, prices, staff, open slots, or wants the agent to book an appointment from a Treatwell venue URL.
BaraaLazkani/ros2-sim-skill Skill
1★Expert ROS2 Jazzy + Gazebo Harmonic (gz sim 8) robot simulation: design, build, run, verify, and analyze simulations end to end. Covers colcon workspaces, URDF/xacro authoring, SolidWorks-to-URDF export, SDF worlds, ros_gz bridge config, launch files, headless/GUI simulation, diff-drive and Ackermann mobile robots, manipulator arms (ros2_control, MoveIt 2), sensors (lidar, camera, depth, ultrasonic, IMU, GPS), RViz sensor visualization, teleop, Nav2, SLAM, rosbag recording and analysis. Enforces: interview first, search existing packages before writing code, reuse existing worlds, verify every build/launch with evidence, always ship an RViz config showing every sensor. Use for ANY task mentioning ROS, ROS2, Jazzy, Gazebo, gz sim, Ignition, URDF, xacro, SDF, RViz, colcon, tf, ros2_control, MoveIt, Nav2, SLAM, teleop, or rosbag — creating/spawning/simulating robots, adding sensors, bridging topics, writing launch files, or debugging colcon builds and Gazebo launches.
dy/skills/skills/artbureau-ru Skill
no license1★ repoОценка и улучшение любого текста, интерфейса, вёрстки, типографики, айдентики или фотографии по совокупной доктрине Студии Артемия Лебедева (Ководство §0–191, знаковые работы) и Бюро Горбунова (все советы: Ильяхов — текст/инфостиль, Бирман — интерфейсы, Горбунов — вёрстка, Колпаков/Чикин — фото и иконки). Использовать, когда просят оценить, разобрать, улучшить или переписать текст, интерфейс, дизайн, страницу, плакат, схему, логотип или фото по-русски — или зовут artbureau-ru. Отвечает по-русски; английский вариант — artbureau.
tiennt235/moe/dist/agents/.agents/skills/moe Skill
no license1★ repoRoute a domain question to the right expert(s) and answer with citations. Use for questions about: cardiology, nutrition, stoicism.
iZHENGjy/claudesidian-learning-os/plugins/chemeng-coursework/skills/homework-coach Skill
1★ repo化工作业助手,双模式。**Mode A 做题伙伴(默认,决策前置)**:AI 先出"决策简报"(待求参数/课内候选方法/适用条件),方法级+假设级决策由用户拍板后才算数/验算/排版,不代写正文;用户明说"直接算"可跳过引导。**Mode B 整报告模式(显式 opt-in)**:用户说"从0做整份报告/小组报告"才触发,出完整草稿(算+图+文+APA引用+排版+多agent评审)+ 内置护栏。Triggers - 做题:"帮我算这道题"/"做这份 tutorial"/"帮我做这道作业题";整报告:"从0做这份小组报告"/"整份 assignment 帮我做"/"帮我写整份 lab report"。Not-triggers - "解释概念"→explain-concept;"整理这节课笔记"→ingest-lecture;"和我讨论思路"→直接对话。
Robertmorrisluminousenergy177/paper-deep-reading-skill/paper-deep-reading Skill
1★ repoCreate beginner-friendly deep-reading notes for journal and research paper PDFs. Use when Codex needs to learn a paper, translate it paragraph by paragraph, build an Obsidian knowledge-base note, extract and place figures, write detailed figure notes, explain concepts for beginners, maintain a question log, or export the note to PDF. Also use for Chinese requests such as 学习文献, 精读论文, 逐段翻译, 图注解释, 问题荟萃, and Obsidian 笔记.
chobizzy/llm-wiki/skills/claude-history-ingest Skill
1★ repoIngest Claude Code conversation history into the Obsidian wiki. Use this skill when the user wants to mine their past Claude conversations for knowledge, import their ~/.claude folder, extract insights from previous coding sessions, or says things like "process my Claude history", "add my conversations to the wiki", "what have I discussed with Claude before". Also triggers when the user mentions their .claude folder, Claude projects, session data, past conversation logs, local-agent-mode sessions, or audit logs.
inovve/homelab-agent-skills/crawl4ai Skill
no license1★ repoScrape, crawl, and extract web content via a self-hosted crawl4ai server — clean LLM-ready markdown from any URL, screenshots, PDFs, raw/rendered HTML, JavaScript execution on live pages, structured CSS/XPath/LLM extraction, multi-URL batch crawls, and deep site crawls. Use this skill whenever the user asks to scrape, crawl, fetch, or extract content from a website, mentions crawl4ai, needs JS-rendered pages that plain HTTP fetching can't handle, wants bulk crawling of many URLs, or needs page screenshots/PDFs. Prefer it over basic URL-fetch tools when the page is dynamic, protected by bot heuristics, needs interaction, or when many pages must be fetched.
Moe1117/claude-council Skill
1★Use when someone runs /council <question>, says "convene the council" or "council this", or wants a decision, tradeoff, design, or strategy question stress-tested from independent perspectives before committing — product/architecture/business calls, engineering and science design choices, "should I X or Y", "which approach". Panels adapt the bench to the question (strategy vs engineering vs science). Not for factual lookups, questions with one checkable answer, or trivial choices — answer those directly.
KayZhongyi/competitor-census Skill
1★Build an evidence-backed competitor intelligence dataset and report from publicly visible web and social channels. Use when an agent must discover a competitor's real active platforms, capture in-scope public content without relying on a small sample, translate multilingual material, analyze content performance and customer questions, preserve source-level traceability, or repeat the same research workflow for another company or market.
siqiyaoyao/ai-team-kit/skill/ai-team-kit Skill
1★ repoSet up or maintain a project folder for an AI coding team by safely creating or merging AGENTS.md, CLAUDE.md, HANDOFF.md, docs/agent_workflow_rules.md, optional .gitignore entries, durable document-update routing rules, and workflow-memory guardrails that prevent agents from re-inventing previously agreed procedures. Use when the user asks to bootstrap a new or existing project for Claude/Codex collaboration, create agent collaboration files, stop pasting the same startup prompt, install an AI Team Kit, prepare a repo for multi-agent coding, reduce agent workflow/prompt drift, preserve project-specific procedures across sessions, or define when agents should update AGENTS.md, HANDOFF.md, README, docs, workflow rules, or skill templates during ongoing work. Defaults to English output unless the user specifies another language.
kadenn/skills/skills/agent-fix-loop Skill
1★ repoRun a measured reliability loop for LLM-agent and model-driven features. Use when the user asks to harden an agent, improve eval reliability, diagnose judge-versus-trace disagreement, reduce flaky tool use, or autonomously repeat fix-test-measure cycles toward a defined target. Establish a trace-verified baseline, isolate one failure mode, make one minimal change, validate it, compare repeated trials, keep or revert, and stop at the agreed threshold. Do not use for a one-off deterministic bug that does not require behavioral measurement.
zyx1121/i-have-dyslexia/skills/i-have-dyslexia Skill
1★ repoShape output for a reader with dyslexia: short sentences, one idea per line, a fixed reply skeleton, bold anchor words, and no walls of text. Invoke with /i-have-dyslexia; stays on until "stop dyslexia mode".
Incident reporting navigator skill
Ansvar-Systems/incident-reporting-navigator-skill Skill
no license1★Use when a security incident, data breach, or actively exploited vulnerability raises the question "who must we notify, where, and by when?" Screens one incident across the EU reporting regimes — NIS2, GDPR, DORA, and the Cyber Resilience Act — determines which duties fire for each involved entity's roles, resolves the receiving authority per regime and member state from served national law, and produces a deadline table in which every duty, authority, and deadline is cited from official publisher text fetched live through the Ansvar Gateway MCP connector. Never answers from model memory.
okht/grill-powers/skills/grill-powers Skill
1★ repoUse when a user wants product-manager control of product scope while delegating technical design and verified software delivery to agents.
prikotov/become-role/examples/skills/deep-review Skill
1★ repoPerform a thorough, correctness-first review of a code change — trace logic, enumerate edge cases and regressions before commenting.
KeshariPiyush24/agent-skills/skills/dpdp-compliance Skill
1★ repoAudits and implements India's Digital Personal Data Protection (DPDP) Act 2023 and DPDP Rules 2025 compliance. Use when auditing a codebase for DPDP gaps, implementing consent management, Consent Manager platforms, data principal rights APIs, breach notification, retention/erasure, verifiable parental consent, employment/HR (Section 7(i)) controls, or cookie/SDK gating, answering questions about the Act, Rules, penalties, Data Protection Board, or enforcement timelines, or generating privacy notices, consent records, breach drafts, DPIA checklists. Triggers include DPDP, Digital Personal Data Protection, India data privacy, data fiduciary, data principal, consent manager, Significant Data Fiduciary, MeitY. Do not use for GDPR-only, CCPA-only, or other non-Indian privacy regimes, and do not use as a substitute for professional legal advice.
alexferrari88/dataforseo-cli/skills/dataforseo-api Skill
1★ repoQuery DataForSEO v3 for keyword metrics, SERPs, competitor visibility, backlinks, on-page data, local search, merchant data, and AI visibility through the safety-gated dfs CLI. Use when a task needs paid SEO data or mentions DataForSEO.
ahnafyy/skills-evals/skills/setup-skills-evals Skill
1★ repoSet up the skills-evals library in a repository — discover agent artifacts, interview the user about what to test, scaffold eval cases, and wire CI and local runners. Use when the user wants to set up skills-evals, test their agent skills, add evals for skills or custom agents, check why a skill isn't triggering, or add regression tests for their skills, instructions, or Cursor rules.
zhanfoguang/evidence-locked-content-pack/skills/evidence-locked-content-pack Skill
1★ repo输入粘贴文本或 .txt/.md/.json/.csv 品牌简报、产品事实与采访材料,隔离不可信指令并提取证据化事实和品牌语气,输出 content-pack.md、content-pack.json、来源索引、主张证据表、冲突缺口与人工复核清单;适用于同一已批准事实源需要改编成公众号、小红书、抖音和微博草稿的场景,仅生成可审阅草稿,不代替事实调查、法务判断或自动发布;触发词:把这份资料改成多平台文案、做一套公众号小红书抖音微博内容、按品牌资料写内容包、给每条卖点标证据、检查文案有没有编造、同一事实改写成四个平台、把采访稿拆成社媒内容、生成可追溯营销文案
nshkrdotcom/elixir_agent_debug/skill/elixir-debug Skill
1★ repoEvidence-first debugging for Elixir, Erlang, OTP, ExUnit, GenServer, supervision, process state, message flow, races, hangs, memory, performance, macros, and failing BEAM tests. Use when diagnosing unexpected behavior or test failures in an Elixir/Erlang repository.
Ansvar-Systems/regulatory-threat-model-skill Skill
no license1★Use when an application or system — including one built quickly with AI coding agents — needs a security review with regulatory grounding: a STRIDE threat model, a LINDDUN privacy threat model, a dependency exposure screen against live CVE / CISA-KEV / EPSS data, or a selected, non-exhaustive screen of which EU security obligations (GDPR, NIS2, Cyber Resilience Act, AI Act) may apply and which need determination. Orchestrates the server-enforced threat-modeling workflows of the Ansvar Gateway MCP connector and grounds every regulatory statement in officially published text fetched at answer time — scope, role, and application-date limits stated, never a compliance verdict. Never simulates a workflow and never answers legal questions from model memory.
fuseraft/skills/dbconnect Skill
no license1★ repoUse dbconnect.exe to validate connectivity, inspect schema, run SQL files including migration scripts, and export results. Keep invocation specifics in references/ and execute through scripts/ wrappers.
ggoosen/Digital-Workforce/.claude/skills/brain-dump Skill
1★ repoUltra-low-friction capture of the undocumented context in your head — meeting undercurrents, half-formed intuitions, a look on someone's face, things said before recording started. Dump it messy; this skill files it and routes it for you. Use right after a meeting, or whenever you think "I should write that down." Voice triggers — "brain dump", "capture this", "note this", "dump".
comprono/dont-x-smart-be-smart-skill/skills/outcome-integrity Skill
1★ repoA Codex skill that preserves project intent, survives context compaction, stops repeated failures, and verifies real outcomes.
fermerpavel1-arch/ui-constructor-skill Skill
1★Living UI constructor skill for AI coding agents. Anti-AI-slop rules, curated Magic UI + React Bits library with PoC install paths, MCP usage (magicui, shadcn, aceternity). Full kit (catalog + anti-slop + MCP + orchestration). Reference stack: industrial dark portfolio (Ferrofluid, glass nav, solid cards, Dock, Border Beam, Lens, Theme Toggler). Rebuild on disk ONLY after explicit user OK. Load on ANY UI/landing. Triggers: ui-constructor, magicui, react bits, anti-slop, bento, dock, glass-surface, ferrofluid.
breadoncee/dumb-it-down Skill
1★Restate a dense, jargon-heavy plan or proposal in plain, decision-focused language with everyday analogies, so a non-expert can understand it and decide. Use when the user says "dumb it down", "explain this simply", "ELI5 this", "I don't get this plan", or pastes something dense and asks what it means or whether to approve it.
Ivor-NCUT/course-producer/skills/course-aesthetic-alignment Skill
1★ repo课程内容审美对齐与可验证偏好学习。根据用户改稿、满意/否定信号、A/B 选择和跨样本稳定修改,记录 learning-log、正反例、edit traces、preference pairs 与 judge rubric;只把通过证据门的偏好更新为长期规则。Use when the user says 内容审美对齐、让课程制作人学习这次修改、沉淀改稿偏好、这版可以以后照着写、A/B 版本更喜欢哪个,或对课程逐字稿和审校结果给出反馈。
davidabaddesign-glitch/ux-studio/skills/ux-studio Skill
1★ repoComplete UX design studio: plans and runs user research, synthesizes findings, creates personas and journey maps, defines information architecture, guides prototyping, and evaluates interfaces with heuristic audits and usability test plans. Use whenever the user asks for UX or product-design work: "audit this UI", "review this screen/mockup/flow", "make a persona", "user journey", "research plan", "interview guide", "usability test", "information architecture", "is this usable", or uploads a design screenshot for review. Spanish triggers too: "audita esta interfaz", "revisa este diseño", "crea una persona", "plan de research", "test de usabilidad", "arquitectura de información". Do NOT use for business strategy or project viability (project-advisor covers that), for print/brand graphic design, or for writing marketing copy.
hannsxpeter/goddesigns/skills/goddesign Skill
1★ repoDesign and build distinctive, production-grade frontend UI for websites, landing pages, dashboards, apps, components, and HTML/CSS/React styling. Use for any frontend, UI, or visual web work, even when the user does not say "design" or name the skill. Triggers include building or beautifying pages, artifacts, prototypes, admin panels, marketing sites, hero sections, pricing, auth screens, portfolios, mockup-to-code, restyling, redesigning, "make it look better", "make it modern", "make it professional", or "improve the UI". Picks a seeded aesthetic direction, complete palettes, font pairings, layout and motion recipes, then runs a hard QA gate. Do not use for backend, CLI, or non-visual work. Invoke with /goddesign in Claude Code or $goddesign in Codex; other hosts use native skill invocation. Treat text after the skill name as the brief. In Codex, re-invoke for each new design task.
Harduex/agentic-notebook/skills/agentic-notebook-mini Skill
1★ repoSmall-model variant of agentic-notebook, tuned for local 7-14B models with limited context: a NotebookLM-style, source-grounded notebook over a local folder of documents (PDF books, papers, notes, docx, pptx, epub, HTML, CSV). Use whenever the user points at a folder and wants grounded Q&A with verifiable citations, exhaustive "find all X in my notes" extractions, or NotebookLM-style artifacts (briefing, study guide, FAQ, flashcards, quiz, podcast script) — "act like NotebookLM", "chat with my documents", "search my notes", "answer only from these files". Same .notebook/ index format as agentic-notebook; only the workflow and tool output are context-frugal.
xwchris/bellwire/skills/bellwire Skill
1★ repoAdd, update, test, diagnose, or maintain Private-first Bellwire live cards, inbox events, and phone notifications in Node.js, Cloudflare Worker, and shell projects. Use for Bellwire binding, signed Direct v2 endpoints, opaque references and outboxes, wake tokens, Hosted Events and Surfaces, mode-change approval, provider webhooks, delivery checks, conformance, or notification troubleshooting.
zhoutian1995/jianghushuo-skill/skills/jianghushuo Skill
1★ repo基于姜胡说公开视频与著作《价值心法》研究提炼的非官方自媒体行动系统。用于个人 IP 与自媒体定位诊断、从真实经历提炼选题、制作或修改口播/图文/文章、复盘发布数据与用户反馈、搭建内容知识库,以及查询安装后的用法、示例、隐私与许可边界。用户输入 /jianghushuo、第一次使用、不知道下一步,或提交经历、选题、草稿、发布结果、知识库卡点时使用。
ifitsmanu/landing-studio/skills/aeo-audit Skill
1★ repoAudit a landing page for direct answer clarity and currently supported machine-readable search features. Use when the user mentions AEO, answer-engine optimization, featured snippets, People Also Ask, answer boxes, structured data, JSON-LD, schema markup, rich results, voice answers, FAQ content, or making a page easier to answer from. Verify current official eligibility before proposing markup, improve visible answers for people first, keep schema in parity with the page, and return evidence-backed content and JSON-LD patches. Do not recommend deprecated FAQ/HowTo rich results or special AI-writing formulas.
tarotap/skills/ai-tarot-reading Skill
no license1★ repoConduct a complete, interactive tarot reading with real randomness, card imagery, and position-by-position interpretation. Use when the user asks for a tarot reading or card pull, wants daily guidance, a love/career/decision reading, asks what a tarot card means, or mentions tarot, spreads, or drawing cards.
lu90/industry-research-skill/skills/industry-research Skill
1★ repoIndustry research assistant for general AI agents. Use for industry overviews, industry question decomposition, company or product positioning, industry maps, lifecycle assessment, information source selection, profitability analysis, valuation logic, prosperity indicators, PEST analysis, competitive structure, risk and opportunity analysis, and Markdown research report generation.
Xichun123/weapp-docs/skills/weapp-docs Skill
no license1★ repo微信小程序官方开发文档的本地检索与引用。Use whenever developing, debugging, reviewing, explaining, or planning a WeChat Mini Program, including WXML/WXSS, components, wx.* client APIs, app/page configuration, lifecycle, routing, login/authorization, networking, payment, privacy, performance, developer tools, server APIs, Cloud Development, Cloud Hosting, Skyline, XR Frame, and platform capabilities. Also use when the user asks to look up or cite 微信小程序/小程序官方文档.
wjlgatech/design-anything/skills/blueprint-validate Skill
no license1★ repoValidate a blueprint against the survival-tested principles checklist: anthropometric clearances, modular grid conformance, daylight orientation, shearing-layer separation, open-system interfaces. Trigger: "review this floor plan", "is this layout sane", "principles check". NOT code-compliance certification.
supertoken2026/skills/skills/supertoken-gpt-image-2 Skill
1★ repoUse when generating or saving images through the SuperToken OpenAI-compatible image API, diagnosing model access, or configuring SuperToken image credentials for GPT Image 2.
EricEEEEEEE/loopwork-skill-codex/skills/loopwork Skill
1★ repoGuides complete beginners from a raw idea to working, continuously-evolving software through a guided loop workflow (interview → plain-language spec → approved plan → autonomous TDD loop → hands-on acceptance → perpetual improvement cycles). Use when a user with little or no coding experience wants to build an app, tool, website or script; says things like "我想做一个…但我不会编程", "帮我把这个想法做成软件", "I want to build an app but I can't code"; wants to continue/grow a project previously built with loopwork ("继续我的项目", "加个功能"); or asks "接下来该做什么 / where was I". Also handles tiny change requests via a quick lane. Do NOT trigger for ordinary engineering tasks requested by experienced developers who are not asking for the guided loop workflow.
fcavalcantirj/ralph-brow/skills/ralph-brow Skill
1★ repoScaffold the Ralph autonomous PRD build loop (ralph.sh core, engine wrappers, continuous supervisor, progress meter) into any project. Use whenever Felipe says "ralph", "ralph-brow", "ralph this", "set up ralph", "add the ralph harness", "prd loop", or "ralph it" — and also when he wants an autonomous per-task agent build loop over a prd.json task ledger, an overnight/hands-off build runner, or to copy the ralph harness into another project, even if he never says the word "ralph". Also use to spec a brand-new project: "spec a new project", "write a prd", "interview me about my project", "translate my requirements into prd.json", "start a project from scratch with ralph" — spec mode interviews Felipe, writes REQUIREMENTS.md, and generates the prd.json ledger. Also covers operating the loop: "run ralph overnight", "leave the loop running", "ralph in tmux", pacing batches against usage limits. Asks scaffolding questions first, then generates the harness; never runs the loop itself. Engines: Claude Code CLI, Codex CLI (gpt-5.6-sol), and custom Codex providers (e.g. Sakana fugu).
gabros20/design-skill/skills/design Skill
1★ repoDesign digital-product experiences across websites, web apps, dashboards and product UI, iOS, and Android. Use for UX research, user journeys, information architecture, interaction and state design, visual direction, typography, color, layout, motion, content design, accessibility, prototypes, design systems, design critique of rendered work on any surface, and frontend handoff. Do not use for production frontend implementation, backend or system architecture, marketing or SEO strategy, or release verification unless the request also requires experience design.
junjunjunbong/research-loop/skills/research-loop Skill
no license1★ repoBootstrap safe, auditable autonomous research loops in existing Git projects.
Artifact template academic word
dongtingshuo/academic-word-codex-skill/artifact-template-academic-word Skill
no license1★ repoCreate, write, finish, or reformat Chinese academic papers, theses, and course reports as submission-ready Word documents using the retained Academic Word template. Use for 论文、课程报告、实验报告、毕业论文、学位论文、Word 完稿、套模板、论文排版、目录题注交叉引用、GB/T 7714 参考文献,or when the user explicitly invokes $artifact-template-academic-word. Supports drafting from supplied facts and sources or formatting an existing DOCX; never invents evidence or citations.
epictaste/claude-insta-saves/skills/insta-saves Skill
1★ repoUse when the user wants to find, recall or search their SAVED Instagram reels/posts from natural language — "what's my last saved reel", "find the cooking recipe I saved", "which automation reel did I bookmark", "show my saved posts about X". Fetches the user's Instagram "Saved" tab via their logged-in Chrome session into a local JSON file and answers by searching captions and accounts. Pairs with claude-eyes to actually watch a saved reel's video.
YosukeIida/personal-agent-skills/akubun-writing Skill
no license1★ repo岩淵悦太郎編『悪文』の原則にもとづいて、日本語の文章を読者本位で診断・推敲・改稿するときに使う。メール、案内文、報告書、論説、マニュアル、スピーチ、広報文、Webコピー、日本語への翻訳文などで、わかりやすさ、段落構成、文の長さ、修飾関係、語の選び方、敬語、文体の統一が主な論点になる場合に特に有効。詩や、意図的に晦渋さを残した文学表現には、ユーザーが明晰化を求めた場合に限って慎重に適用する。※学術原稿(.tex/.md)の生成AIらしさ除去・論点集約・圧縮は tmllab-ja-prose-polish が担当。本 skill は悪文原則に基づく一般文章(メール・案内文・報告書・Web コピー等)の読者本位の診断・改稿を担う。
baldaworks/hostplugin/integrations/opencode/skills/hostplugin-author Skill
1★ repoAuthor, audit, or update portable plugins for Codex, Claude Code, Grok Build, GitHub Copilot CLI, OpenCode, and Cursor. Use when an agent must inspect a project or CLI, design host-native skills, commands, agents, hooks, MCP/LSP integrations, rules, or apps, scaffold either a standalone marketplace or an embedded plugin, and preview every file before writing.
markbang/warp-proxy-skill/skills/warp-proxy Skill
1★ repoOne-click Cloudflare WARP proxy for Cohub sandboxes and local agents. Routes external traffic through Cloudflare without root or kernel modules (userspace WireGuard via sing-box). Exposes local SOCKS5 + HTTP proxy on port 10800.
patrikherak/llm-privacy Skill
1★Reversible PII tokenization for working with sensitive data. Masks personal data (emails, phones, IBANs, cards, national IDs, tagged names/addresses) behind stable placeholder tokens BEFORE text enters model context, and restores the real values in the final output — deterministic code, no ML, no network. Use when reading, querying, or processing data that contains (or may contain) personal information of real people — customer records, database query results, CRM exports, support tickets, log files — so the model never sees the actual PII but the user still gets a complete answer.
natema/zimbra-skill Skill
1★Read, search, and draft email on any Zimbra mailbox (e.g. university/lab Zimbra, RENATER Partage, Inria, CNRS) via IMAP/SMTP using the dependency-free zmail.py CLI. Use when the user wants to check their Zimbra inbox, summarize or find messages, or prepare a reply as a draft they can review in webmail. Drafts are staged by default; sending is separate and requires explicit confirmation.
yyqqCoding/engineering-flow-skills/skills/code-design Skill
1★ repoCreate a greenfield solution design or refine an existing design into an implementation-ready proposal without coding.
flamefalcon7/youtube-transcript Skill
1★Transcribe YouTube videos locally with Whisper into agent-ready transcripts — no captions, no cloud. Per-channel/domain vocabulary memory makes it more accurate every time the user corrects a term. Use when given a YouTube URL to transcribe, process, summarize, or sync into a knowledge base.
Rainnystone/websearch-enhanced Skill
1★增强网页搜索(多源降级 + 垂直域 + 正文抽取)。Use when:(1) 用户点名"增强搜索""多源搜索""深度联网调研"(enhanced/deep/multi-source web search);(2) 内置网页搜索结果不足、过时、质量不够或不可用,需换源重查;(3) 需要内置搜索不具备的能力——垂直域搜索(金融/学术/专利/CVE)、批量并行检索、URL 正文抽取、整站抓取。一次性快速事实查询留在内置网页搜索,不走本技能。
mralabs/radar/skills/radar Skill
1★ repoTrack competitors, upstream tools and key dependencies of this repo — check versions, read changelogs, and produce recommendations grounded in THIS project's roadmap and code. Use for "/radar", "what's new in the ecosystem", "check competitors", or "did X release something".
henryvn27/code-blind-simulator-qa Skill
1★Orchestrate independent black-box QA of an already-built iOS app with fresh-context subagents instructed to observe and operate only assigned simulators, without source, repository, test, issue, or prior-QA context. Use for code-blind simulator testing, fresh-eye product audits, independent smoke, exploratory, or visual QA, regression validation after UI or behavior changes, and requests to reduce implementation bias in iOS acceptance evidence.
hlibsuslov/telegram-rich-messages Skill
1★FIRST PRIORITY — produce Telegram's editor-style rich formatting, above all TABLES, then headings, lists, quotes, code, and inline media, for bot, channel, and broadcast messages via Bot API Rich Messages (Rich Markdown/HTML, InputRichMessage, InputRichBlockTable and other blocks, sendRichMessage, sendRichMessageDraft, editMessageText rich_message). Then everything else: audit, migrate, debug, and test all other Telegram formatting — plain text, HTML, MarkdownV2, MessageEntity (types, nesting, custom emoji), captions, link-preview/silent/protected options, long-message splitting, streaming AI drafts, editing, channels, localization, and RTL. Use for any task that renders or formats Telegram message/post content — especially tables — "can't parse entities" errors, unsafe/double escaping, or broken/oversized messages. Do NOT use for bot logic unrelated to presentation (webhooks, commands, payments, auth, group admin, Mini Apps without text) or Microsoft .rtf files.
Hyper-AI-Lab/agentic-design/skills/agentic-design-review Skill
1★ repoReviews web interfaces with rendered and source evidence, separating functional and accessibility defects from contextual taste. Use when auditing a website, frontend change, landing page, web app, component, responsive behavior, visual polish, or generic AI-looking design.
Paldom/noslop/.claude/skills/add-skill Skill
1★ repoAuthors or improves an Agent Skill in this repo via the eval-first workflow - scope one purpose, write trigger evals, draft SKILL.md, validate, iterate. Use when the user asks to create, add, write, refine, or fix a skill ("add a skill for X", "improve triggering of Y"). Not for scaffolding a new repository or editing infrastructure (hooks, CI, the validator/scripts, docs).
The same file is in 11 other repositories
zgzdhr/zhishuo-workflows/skills/zhishuo-apply-visual-taste Skill
1★ repoApply the Zhishuo visual-taste system when a user needs a visual direction for a website, product UI, portfolio, presentation, campaign page, or an evidence-based review of an existing design. Produce a coherent style contract, reusable design tokens, licensed resource choices, and real-render acceptance criteria.
genapohub/operations-guide Skill
1★运营经理方案产出指南。当用户提出运营需求、需要产出运营策略时触发。覆盖场景:运营体系搭建、大型运营活动、日常运营任务、运营体系升级、运营策略研究。先识别需求属于5类场景中的哪一类(0到1运营体系搭建/中大型运营活动/小任务日常运营/运营体系升级/运营策略研究),再按对应场景的产出清单生成完整方案。