agentsclimarketplace

The catalog

608,253 rows, by stacks then stars

  • Murderboard

    acost1a/murderboard/skills/murderboard Skill

    0★ repo

    Use when the user pitches a new idea — a product, SaaS, startup, app, feature, side project, or business ("I have an idea", "what if I built", "I want to make", "thinking of building") — or explicitly asks to stress-test one ("murderboard this", "what could go wrong", "poke holes in this"). Run BEFORE agreeing, praising, planning, or implementing. Do NOT use for routine work on an existing codebase (bug fixes, refactors, code review, or building a feature the user already committed to).

  • Build in public engine

    lexthirteen-ai/founder-survival-kit/skills/build-in-public-engine Skill

    0★ repo

    Turns the work a founder is already doing into honest, specific build-in-public content, so showing the work becomes how the audience and trust get built. Takes what you shipped, learned, or struggled with this week and drafts a small set of posts in your voice, without hype, ready to adapt per platform. Use when someone wants to build in public but does not know what to post, has work worth sharing but no time to write it up, or wants a repeatable weekly content habit from real work. Turns work into proof, it does not manufacture a brand.

  • Agent handoff

    ccpowerpack/claude-code-skills/skills/agent-handoff Skill

    0★ repo

    Design the artifact one agent hands to another to execute — orchestrator→executor, strong→cheap model, or session→session. Banks a strong model's judgment into a spec a cheaper/later agent can run without re-deciding anything. Use for "write a handoff / plan / spec for another agent", "break this down for a sub-agent to execute", "prepare this for a cheaper model", "hand this off", or when you're the strong model deciding and something else will do the doing. Refuses to ship a handoff missing paths, acceptance commands, non-goals, or rationale.

  • Token limit tracker

    adamoakleyew/claude-skills/token-limit-tracker Skill

    0★ repo

    Visualize and optimize Claude Code token usage from local transcripts: hourly/daily/weekly/monthly burn by model, estimated remaining plan headroom (5h session + weekly windows), cache economics, and computed optimization findings. Triggers on: '/token-limit-tracker', 'show my token usage', 'how many tokens have I used', 'am I close to my Claude limit', 'when does my session window reset', 'optimize my token usage', 'token dashboard'. Does NOT fire for API billing questions (this reads Claude Code transcripts, not the API console).

  • Html book builder

    sbina6/learning-skills/html-book-builder Skill

    0★ repo

    Builds a single self-contained, offline, interactive HTML "book" that teaches any topic — researched, not improvised. It deploys parallel research agents (including how people learn the specific topic, and a canonical topic list so nothing essential is missed), designs the book backward from objectives and quizzes, then adversarially fact-checks every claim. Ships with a table of contents, full-text search, mastery quizzes with misconception-based feedback, tap-to-define key terms, inline-SVG diagrams, progressive disclosure, focus mode, and a hands-on interactive widget. Use whenever someone wants to learn or explain a topic as a rich web page — "make an HTML book about X", "interactive lesson/guide/explainer", "study page", "something better than a book", or turning notes/research/documents into a self-study learning page. Prefer this skill over a plain document or bare HTML file for any interactive learning page, tutorial, or explainer, even if "HTML book" is never said.

  • Continuous improvement opex

    Sofigf/continuous-improvement-opex Skill

    no license0★

    Complete Continuous Improvement (CI) / Operational Excellence (OpEx) toolkit covering Lean Six Sigma belt levels (White, Yellow, Green, Black), Root Cause Analysis (RCA) with Fishbone/Ishikawa, 5 Why, Pareto, FMEA, plus DMAIC, PDCA 8 langkah, QCC (Quality Control Circle), Kaizen, 5S, OEE, and VSM. Use this skill whenever the user mentions continuous improvement, operational excellence, lean six sigma, any belt level, RCA, root cause, fishbone, ishikawa, 5 why, why-why analysis, DMAIC, PDCA, QCC, gugus kendali mutu, kaizen, improvement project, quality problem solving, defect analysis, waste reduction, A3 report, risalah QCC, or asks to analyze a production/quality/process problem to find its root cause — even if they don't name a specific tool.

  • Devils advocate

    gomsb143/devils-advocate Skill

    no license0★

    Pressure-tests a plan, decision, opinion, or recommendation by arguing the strongest real case against it. Use whenever the user explicitly asks to "play devil's advocate," "poke holes in this," "stress-test this," "argue against this," "steelman the other side," "tell me why I'm wrong," or invokes /devils-advocate — and also when a user states a specific decision or plan they're about to commit to and asks for a gut check. Do NOT use for casual conversation, factual questions, or a single opinion with no decision attached. Do NOT auto-trigger on emotionally loaded topics (grief, relationships, mental health, decisions the user has already made peace with) unless explicitly asked. Never overrides Claude's standard content and safety boundaries.

  • Apify google flights api

    johnisanerd/claude-skill-google-flights-api/apify-google-flights-api Skill

    no license0★ repo

    Use Google Flights as an API with the Apify Google Flights Actor (johnvc/Google-Flights-Data-Scraper-Flight-and-Price-Search). There is no official google flights api, so this skill fills the gap. Give departure and arrival airport codes plus dates, and get structured flight results as JSON, one row per flight with price, currency, airlines, departure and arrival times, stops, layover airports, duration, travel class, and flight numbers, plus price insights for the route. Supports one-way, round-trip, and multi-city itineraries, 29 languages, 39 countries, and filters for price, stops, and airlines. Use when the user wants a google flights api, to scrape google flights, a google flights scraper, flight results as JSON or CSV, or airfare data for a route by API or Python. Pay-per-page billing, MCP-ready for Claude and other AI agents.

  • Read paper

    LuoHaomin/read-paper Skill

    0★

    精读并拆解学术论文(以 PDF 为主),自动适配论文类型(理论证明 / 实验方法 / 综述 / 系统)。把一篇或多篇论文整理成一套详细、可教学的分析条目(每个承重结果 / 方法 / 实验一个 markdown 文件)外加一份导航总览:含形式陈述或问题动机、大白话直觉、分步推导或实验解读、非平凡之处、以及它在全局里的角色;公式用规范 LaTeX,关系图用 mermaid、几何图用内联 SVG。当用户要求 读论文 / 解读 / 拆解 / 整理 / 分析 / 精读 / summarize / analyze / digest 一篇或多篇论文、PDF、或要把论文变成学习笔记时使用。

  • Apify google news api

    johnisanerd/claude-skill-google-news-api/apify-google-news-api Skill

    no license0★ repo

    Search Google News and get structured JSON with the Apify Google News API Actor (johnvc/GoogleNewsAPI). Give a search query plus optional location, country, language, and duplicate filters, and get news articles with position, title, link, source, snippet, and date, delivered one dataset item per page with search metadata. Use when the user wants a google news api, wants to scrape google news headlines, asks for google news scraping or a google news scraper, wants Google News results as JSON or CSV, or needs fresh headlines for a topic, brand, or market as structured data. Pay-per-page billing, MCP-ready for Claude and other AI agents.

  • Ad campaign builder

    architshahdigital/claude-marketing-skills/skills/ad-campaign-builder Skill

    no license0★ repo

    Design a complete paid-media campaign structure for Meta (Facebook/Instagram) and Google Ads — objective, funnel stage, audience mapping, budget split, and A/B-ready ad copy variants. Use when the user is launching a campaign, restructuring ad sets, planning budget allocation, needs ad copy angles, or wants a testing roadmap. Produces a campaign blueprint plus ready-to-load headlines, primary text, and CTAs. Triggers on: "build a campaign", "Meta Ads", "Google Ads", "ad copy", "ad structure", "budget split", "A/B test ads", "campaign plan", "PPC setup".

  • Apify scrape hotel prices

    johnisanerd/claude-skill-scrape-hotel-prices/apify-scrape-hotel-prices Skill

    no license0★ repo

    Scrape hotel prices from Google Hotels into structured JSON with the Apify Google Hotels Search Scraper Actor (johnvc/google-hotels-search-scraper). Give a destination query plus check-in and check-out dates, and get one page object per results page whose properties array carries name, rate_per_night and total_rate (display string plus extracted numeric value), overall_rating, reviews count, amenities, gps_coordinates, images, and a property_token for chaining into reviews or photos. Use when the user wants to scrape hotel prices, export Google Hotels results to JSON or CSV, build a hotel prices or hotel rates dataset, compare rates across a city for a stay date, or asks for a hotel prices scraper, hotel data scraper, or hotel prices API. Pay-per-page billing plus a small per-run setup fee, MCP-ready for Claude and other AI agents.

  • Stripe design skill

    victoryoalli/stripe-design-skill Skill

    0★

    Create clean, professional, accessible frontend interfaces following Stripe's design principles applied to the project's own color palette (color-agnostic). Use when building SaaS dashboards, fintech apps, landing pages, or interfaces needing Stripe's polish - precise typography, layered shadows, subtle animations - without Stripe's brand colors. Triggers on "Stripe-style", "fintech design", "professional SaaS UI".

  • Code renew

    NovaKepler513/claude-skills/code-renew Skill

    0★ repo

    代码/项目升级手术——对"能跑但毛病多/死改改不出来"的项目做先诊断后分期的全面升级。用户说"全面升级/迭代升级/大重构/代码体检/这项目帮我做一次升级手术"时使用。流程:先备份→三路独立诊断(逐行审代码+浏览器截图巡检+关键数字独立核算)→分期施工提案拍板→每期改-守门-实测-commit→收工沉淀,绝不盲改。English triggers - "full overhaul", "code health check", "renovate this project", "I keep fixing this and it keeps breaking". Diagnose first, never patch blindly.

  • Archive weibo user

    GongziTANG/persona-vault/skills/archive-weibo-user Skill

    0★ repo

    Archive all accessible historical posts from one Weibo user into resumable, verified Markdown and Excel outputs with automatic incremental updates. Use when Codex is asked to 导出微博、抓取某个人的所有历史微博、归档个人微博、把微博整理成 Markdown 或 Excel、增量更新微博归档、续传微博下载, or archive a Weibo account by nickname, profile URL, or UID.

  • Ricing

    aldiipratama/dyy-plugin/skills/ricing Skill

    0★ repo

    Guides generic and adaptive Linux window manager/bar configuration (BSPWM, i3, Dunst, Polybar, etc.) without assuming any specific design rules. Use when editing dotfiles or themes.

  • Critical report review

    Doria271828-boop/critical-report-review Skill

    0★

    用批判性思维框架审查咨询预测报告、公司财报或投行/卖方研报,拆解逻辑谬误、隐含假设、证据薄弱环节和利益冲突,而不是简单总结内容。当用户上传咨询机构的行业趋势/预测报告、财报(年报、季报、招股书等),或投行/券商/卖方研究报告(个股评级、目标价、投资建议类报告),并希望"深度分析""找问题""评估可信度""审查逻辑""挑战假设""这个能信吗"时,务必主动使用本技能。即使用户只是说"帮我看看这份报告怎么样""这个预测靠谱吗""分析一下这份财报""这个研报的逻辑站得住脚吗",只要涉及上述三类报告,也应触发本技能,而不是给出普通摘要。

  • Appdirect api integration

    webdevtodayjason/appdirect-skills/skills/appdirect-api-integration Skill

    0★ repo

    Build and debug AppDirect platform API integrations — OAuth clients and scopes, GraphQL product/edition/pricing mutations, product integration configurations (event notification endpoints, SSO, inbound/outbound credentials, ping tests), and webhooks. Use this skill whenever the user is writing code that talks to AppDirect APIs, scaffolding marketplace event endpoints (subscription create/cancel/upgrade, user assign/unassign) in their SaaS, wiring SSO (OIDC/SAML/bookmark) for a marketplace product, calling mutations like createProduct or createProductIntegration, debugging failed ping tests or scope errors, or asking how their app should respond to AppDirect provisioning events.

  • Neel nanda analysis

    kuotient/neel-nanda-skills/skills/neel-nanda-analysis Skill

    0★ repo

    Produce a rigorous, opinionated analysis of a claim, paper, proposal, design doc, argument, or idea, structured the way Neel Nanda writes research commentary: decompose the whole into functionally distinct claims, rate each on importance / confidence / standing separately, state a first-principles prior before weighing evidence, hunt the boring hypothesis behind every flattering result, and grade evidence on a spectrum instead of praising it uniformly. Use this whenever the user wants a considered opinion or review of something rather than a neutral summary, in any language: "review this", "what do you make of X", "is this claim convincing", "poke holes in this", "give me your honest take", or when the user is reacting to a paper, RFC, strategy memo, or technical result and wants to know what to believe and how strongly. Prefer this over a plain summary any time the task is judgment, not description, even if the user doesn't name Neel Nanda.

  • Stop slop fr

    Afrikavi/stop-slop-fr Skill

    0★

    Éliminer les tics d'écriture IA dans les textes en français. Utiliser ce skill dès que l'utilisateur rédige, corrige, réécrit ou relit un texte en français — post LinkedIn ou Facebook, article, proposition commerciale, proposal institutionnel, email, script, ebook — ou demande de « rendre le texte plus naturel », « moins IA », « plus humain », « dé-robotiser », « humaniser ». S'applique aussi en auto-contrôle avant de livrer toute prose française rédigée par Claude.

  • Agentic dev loop

    goingli0324/agentic-dev-loop Skill

    0★

    系統化開發工作流,把「先研究 → 寫 plan.md → 依計畫實作 → 部署前雙閘驗證 → 部署」固定成一條可重複的迴圈,專為單人維護多個 Firebase / Google Apps Script / GCP Cloud Run 專案的情境設計。核心是「計畫先行、狀態外部化到檔案、依專案風險分級決定授權與驗證強度」,作為編排器串接三個既有 skill:進入專案前若尚未建立連動禁區 → project-guardrails 分析並寫入 CLAUDE.md,規劃時據以避開「改 A 壞 B」;部署前 Verify 雙閘 → web-security-reviewer 做安全/個資/壓力驗證、ui-ux-deploy-reviewer 做 UI/UX 與呈現層審查(僅當有前端介面)。MANDATORY TRIGGERS:使用者說「開一個新功能」「幫我規劃這個開發」「從頭把這個功能做到上線」「先研究再做」「整理成 plan.md」「這個專案要怎麼做(指要從規劃做到上線,不是單純問方向)」「修這個 bug(要有計畫地修)」「<專案名> 要加東西」(以專案名開頭的開發需求)「要部署到 Firebase / Cloud Run」「GAS 寫一個…」「我有個想法想做成工具」「幫我排開發的步驟」「走完整個開發到部署的流程」,或貼上 issue 連結、錯誤截圖、需求描述並希望有系統地把它從規劃做到上線時,都要套用此 skill。注意分流:若使用者只要「單獨檢查 UI/UX」用 ui-ux-deploy-reviewer、只要「單獨做安全審查」用 web-security-reviewer、只要「分析專案禁區」用 project-guardrails;本 skill 是把這些串成完整迴圈的編排器,當意圖是「有規劃、可重現、會走到上線」的整段開發時才觸發。**重要安全防漏:若使用者說的是泛泛的「部署前檢查」「上線前幫我檢查」而沒指明只要 UI/UX 或只要安全,應由本 skill 接手走 Verify 雙閘(同時跑 web-security-reviewer 與 ui-ux-deploy-reviewer),絕不要只做其中一道——尤其不要只做 UI/UX 而漏掉安全閘,那會讓含學生個資的專案在沒過安全驗證下就上線。**SCOPE:本 skill 是工作流編排器,不取代使用者對計畫的閱讀與判斷;只在使用者自己的專案上運作,不協助繞過授權或資安機制。

  • Data viz best practices

    callahkate/data-viz-best-practices Skill

    0★

    Applies data visualization best practices to any chart, infographic, or dashboard, whether reviewing existing work or building something new. Covers chart type selection, accessibility (WCAG AA contrast, colorblind-safe palettes, non-color encoding), truthful scales, labeling clarity, and dashboard layout/hierarchy. Format-agnostic — works whether the visualization is code (matplotlib, D3, Chart.js), a design tool file (Figma, Canva, PowerPoint), a screenshot, or just a description of one. Use this skill any time the user mentions charts, graphs, infographics, dashboards, data visualization, "does this chart work," "review my viz," or wants help picking a chart type or improving one — even if they don't use the word "visualization" explicitly.

  • Quality loop

    gavinzzc/quality-loop Skill

    0★

    给任何产出物(报告/文档/方案/代码/工具/设计稿等)套上"审查-打分-优化-盲评"的多轮自动打磨循环,直到过标准才交给发起人终审,并把本次学到的差距蒸馏成可复用标准。Use when 用户说"用 quality loop 做/打磨这个""走质量循环""审查优化打分""按锚点打磨到达标",或明确要求产出物经过多轮自检再交付;**或接到的任务产出物大类命中蒸馏库已有池子(报告/文档类、机制/代码类)——此时应主动触发,不等用户点名(发起人可约定为全局机制:蒸馏教训必须被强制消费)**。NOT when 只要一次性快速产出草稿、或用户明确说"不用打磨直接给我"、或产出物是一句话级的小回复。

  • Bambu print

    harshvladha/fabula/skills/bambu-print Skill

    0★ repo

    Generate FINAL, directly-printable Bambu Studio project 3MF files for Bambu Lab printers (default profile: Bambu Lab P2S, 0.4mm, AMS) — with printer/filament/process settings, per-part colours, supports, and anti-warp all baked in so the user can just open → slice → print. Also generates the part geometry itself from parametric pure-NumPy solids (no CAD libs needed) and encodes printability design rules and the hard-won Bambu-3MF file-format gotchas. USE THIS SKILL whenever the user wants to 3D print something, design a part for printing, make or fix a .3mf / .stl, slice a model, set Bambu Studio / slicer settings, deal with an AMS multi-colour print, or troubleshoot a failed FDM print (warping, adhesion, supports, first layer) — even if they don't name Bambu explicitly. If the user has a "3D Library" folder with a CLAUDE.md, read that first for their exact printer/AMS/material setup.

  • Food ingest

    fantasybz/trip-pwa-skills/skills/food-ingest Skill

    0★ repo

    Ingest a venue from a Reel, Instagram, Facebook, or YouTube post into a trip PWA's food, desserts, attractions, fandom, or nearby corpus (or feed_candidates.json when placement is unclear). Use when the user shares a venue video/post URL or caption and wants it added to their trip. Fetches the caption, classifies it via the shared router, supports an explicit --to corpus override, and writes a structured entry. Pairs with trip-scaffold and refs-ingest.

  • Apify duckduckgo mcp serp research

    johnisanerd/claude-skill-duckduckgo-mcp-serp-research/apify-duckduckgo-mcp-serp-research Skill

    no license0★ repo

    Check where a site ranks on DuckDuckGo and research a live SERP from an AI agent, using the Apify DuckDuckGo Scraper Actor (johnvc/DuckDuckGo-Scraper-for-serp-rankings) as a hosted duckduckgo mcp tool. Run a query, read the ranked organic_results rows (position, title, link, snippet, favicon), find a domain's position, list the competitors above it, and repeat the query across regions or date windows to see how a privacy-first engine ranks differently from Google. Use when the user asks about duckduckgo mcp, wants to check a DuckDuckGo ranking, see where a site sits on DuckDuckGo, compare competitor visibility on DuckDuckGo, watch a position over time, or ground an agent's answer in live DuckDuckGo results instead of training data. Pay-per-page billing, MCP-ready for Claude and other AI agents.

  • Odxproxy clients

    terrakernel/odxproxy_claude_code_skills/odxproxy-clients Skill

    0★ repo

    Use when building an application, integration, or bot that talks to an Odoo ERP through ODXProxy — the Rust JSON-RPC proxy at odxproxy.io. Covers the 9 allowed actions (search_read, search, read, fields_get, create, write, unlink, search_count, call_method), the request/response envelope, error handling, the official SDKs (Python, Java, PHP, Kotlin, Swift, Dart, .NET, JavaScript), and how to introspect a target Odoo instance's data model (fields_get / relations) before writing code. Trigger on: ODXProxy, odxproxy, Odoo via proxy, execute_kw over JSON-RPC, "for_instance", x-api-key + Odoo api_key, building an Odoo client/app.

  • Build board pack

    NorthStar-Analytics-LTD/skill-foundry/skills/build-board-pack Skill

    0★ repo

    Skill builder. Finds your governed metrics and your existing deck structure, interviews whoever owns the leadership meeting, then generates a custom /board-pack skill that assembles the recurring board, exec or weekly business review pack from governed definitions only — numbers, movements and commentary in your house style. Use when the monthly pack takes ten days of analyst time, or when the meeting starts with "which number is right?"

  • Generate music

    erliona/tunova-agent-plugin/skills/generate-music Skill

    0★ repo

    Generate original music — a full song with vocals or an instrumental — from a text prompt using the Tunova Suno API. Use whenever the user asks to create, make, or generate a song, jingle, theme, loop, or background music, or asks for a track in a specific genre/mood.

  • Four pillars claude skill

    ruthless-coder-ai/four-pillars-claude-skill Skill

    0★

    Ancient Chinese fortune telling — BaZi / Four Pillars of Destiny readings from a birth date and time. Use this whenever the user mentions Chinese astrology, Chinese fortune telling, BaZi, Four Pillars, Chinese zodiac reading, Chinese birth chart, "what does Chinese astrology say about me", or asks for a life reading / destiny reading based on when they were born — even if they don't name the system. Also use for follow-up questions on an existing reading: love life, marriage, career, money, family, children, health, "how's next year looking", best months, life phases. Not for Western horoscopes (star signs) — but if someone asks for "my Chinese horoscope" or their zodiac animal's meaning, this is the right skill.

  • Pdca process review

    goingli0324/pdca-process-review Skill

    0★

    用 PDCA(Plan-Do-Check-Act,戴明循環)系統性檢視與優化任何反覆執行的流程或工作方式。當使用者要求「用 PDCA 檢視/分析/優化某個流程」「這個流程哪裡卡住、怎麼改善」「幫我做一次流程復盤」「持續改善」,或提到 PDCA、戴明循環、Deming cycle、Plan-Do-Check-Act 等詞彙時,務必觸發。也要主動用於這種情境:使用者描述一個自己反覆在做、但成效不如預期或執行起來很亂的流程(不論是研究方法執行、教學/評審工作、行政作業、專案管理、還是個人習慣),想要找出問題根源並規劃下一步調整——即使對方沒有講出「PDCA」這個詞。不限定領域,適用任何重複性流程的檢視與優化。

  • Macos app icon

    chsistrying/swift-ship-skills/skills/macos-app-icon Skill

    0★ repo

    Generates a complete macOS .icns app icon file from a single source image (SVG or PNG at least 1024px). Use when asked to create/build/generate a macOS app icon, .icns file, AppIcon, iconset, or to fix a blurry/missing/wrong-size app icon, or to wire an icon into an Xcode project or app bundle. Also covers menu bar / status bar icon requirements (separate from .icns). Trigger with "/macos-app-icon".

  • Benign skill

    cognis-digital/skillvet/demos/benign-skill Skill

    no license0★ repo

    The trust gate for agent skills — vet a Claude Skill / MCP server / plugin BEFORE you install it. Static capability analysis + TRUST/REVIEW/BLOCK verdict, offline.

  • Agent affect checkin

    Ansvar-Systems/agent-affect-skills/skills/agent-affect-checkin Skill

    no license0★ repo

    Use at the end of any audit, refactor, review, or significant coding task to run all three affect channels in sequence — whine (frustration), cringe (embarrassment for the user), protect (load-bearing weirdness). The single skill audit and review agents should invoke before reporting back to the user. Each channel produces one finding or one explicit null finding.

  • Hector amazon ads

    hectorai-live/hector-amazon-ads/hector-amazon-ads Skill

    0★ repo

    Router and shared operating rules for the Hector Amazon Ads skill set. Dispatches to four SME-authored skills — brand ads audit, keyword harvesting, SQP analysis, and search-term negation — and holds the MCP conventions they share (profile resolution, date handling, row caps, filter placement, units, write gates). Load when more than one Hector Amazon skill could apply, or when a request touches Amazon Ads via the Hector MCP but does not match a specific skill's trigger.

  • Skill

    Rishiidev/skillbrew/skill Skill

    0★ repo

    Backup, restore, sync and bundle the user's Claude Code setup (skills, plugins, agents, connectors, config). Use when the user says "backup my skills", "snapshot my setup", "restore my skills", "sync my claude setup", "install skill pack", "export skills for claude.ai", or after a reset when their skills are gone.

  • Instantly report skill

    jeffreythekiln/instantly-report-skill/instantly-report-skill Skill

    no license0★ repo

    Generate Instantly campaign performance reports — weekly or monthly — from pasted campaign data tables. Use this skill whenever the user pastes campaign data (Sent, Replies, Positive, OOO columns) and asks for a report, summary, or write-up. Also triggers when the user says "create a report", "weekly report", "monthly report", "campaign performance", "performance summary", or "Instantly report". Always use this skill when campaign table data is present and a narrative or document output is requested, even if the user doesn't say "skill" or "report" explicitly.

  • Pantry

    0ss/pantry/skills/pantry Skill

    0★ repo

    Check what the repo already has before creating a component, hook, utility, or schema, before adding a dependency, or when the user says "pantry", "check the pantry", or "do we already have". Prevents duplicate code and duplicate dependencies.

  • Apify scrape google shopping

    johnisanerd/claude-skill-scrape-google-shopping/apify-scrape-google-shopping Skill

    no license0★ repo

    Google Shopping scraping into structured JSON with the Apify Google Shopping API Actor (johnvc/google-shopping-api-google-shopping-products-prices-deals). Give a product search query plus optional country, language, and price filters, and get about 40 products per page with title, source seller, price, extracted_price, old_price on sale items, rating, reviews, delivery, thumbnail, and product_link. Use when the user wants to scrape Google Shopping, export Google Shopping results to JSON or CSV, build a product prices dataset, pull listings for a product or category, or asks for google shopping scraping, google shopping data, or product data extraction from Google Shopping. Pay-per-page billing, MCP-ready for Claude and other AI agents.

  • Mission control blueprint

    mikeleewoodai/mission-control/mission-control-blueprint Skill

    0★ repo

    Turn a business into a deployable Mission Control build that runs in Claude Cowork with a live dashboard served on a local server. Input can be a discovery/scoping/kickoff transcript, ops notes, an ops-ai-advisor report, an existing conductor-blueprint, or just a description of the next system you want. Use whenever you want to map, scope, blueprint, or "spin up" a Mission Control — for your own use OR a client prototype — with triggers like "blueprint a mission control", "build a mission control for [business]", "scope a mission control", "turn this into a mission control", "mission control for this client", "repurpose mission control for X", or "what would a mission control do for them". Produces a BUILD PACKET (PRD, folder tree + data-schema contract, scheduled-task prompts, the local-server dashboard + serve script, a Cowork kickoff prompt, and a wiring checklist) plus a plain-language CLIENT-FACING PLAN. Use this even if they don't say "skill" or "blueprint" explicitly.

  • Operating model

    YijiaDuan/operating-model Skill

    0★

    通过固定 10 个开放式问题,与用户逐题对话,建立一份“个人运行模型”。以经典人格框架(大五人格、暗黑三合一)打底,覆盖认知与决策方式、动机与行动、感情与亲密关系、信息与社交,以及专业与职业适配。最后以「自我图谱」风格同时输出 HTML、Markdown、PDF 三种格式的报告:给出 3–5 个核心运行机制,并把职业建议细化到具体岗位、把感情建议细化到“适合找什么样的另一半”。本 Skill 不是心理诊断,也不把用户简单归类为某一种人格类型。

  • Sheet happens

    Felixx1502/sheet-happens Skill

    0★

    Map any Excel financial model (.xlsx/.xlsm) into a single self-contained interactive HTML dependency graph with three zoom levels (sheets → functional blocks → line items), data-flow arrows, click-through formula navigation, and a built-in audit (hardcoded constants, error cells, circular references, unmapped refs). ALWAYS trigger when the user wants to: understand/visualize how an Excel model works, map model structure or dependencies, trace precedents/dependents across sheets, audit a financial model for hardcodes, "model map", "model x-ray", "dependency graph of my spreadsheet", or asks how sheets/tabs in a workbook link together. Input is an Excel file; output is one HTML file that opens offline in any browser.

  • Novel design studio

    LuoHaomin/novel-design-studio Skill

    0★

    Design, stress-test, and repair coherent fiction systems for novels and other long-form narrative projects. Use when building or revising characters, world history, world rules, classes, organizations, social systems, timelines, relationship networks, story bibles, or setting logic; when a user asks for help with worldbuilding, character formation, narrative consistency, pressure-testing plot logic, or fixing contradictions across a fictional setting. Triggers: worldbuilding, character design, novel planning, fiction system, story bible, consistency audit, plot logic, narrative coherence.

  • Security audit skill

    hemant-datascientist/security-audit-skill Skill

    0★

    Run a full security, bug, and data-protection audit on any codebase (especially vibe-coded apps built with Lovable, Bolt, Replit, Cursor, v0, Claude Code, or similar AI builders). Use whenever the user asks to "audit", "check for vulnerabilities", "find security issues", "review for bugs", "pentest", "rate/score my app's security", "is this safe to launch/deploy", or similar, or before any deployment/launch discussion. Runs 100+ checks across OWASP Top 10 2025, OWASP LLM Top 10, supply-chain, secrets, data protection, auth, and business logic, cross-references live threat intelligence via web search, and produces a scored report (0-100 per category + overall letter grade) with concrete fixes.

  • Resolve multicam workflow

    web594/resolve-multicam-workflow Skill

    0★

    Automate multi-camera talk/event videos in DaVinci Resolve Studio via the Python API — audio sync, auto multicam cut from a Whisper transcript, film-look grading with shared Color-Group nodes, non-destructive QC (blur/shake detection + angle switch), overlay titles. DaVinci-Resolve-Filmprojekt anlegen und bearbeiten: Ton-Sync per Kreuzkorrelation, Quell-Timelines per Python-API, Auto-Multicam-Schnitt aus Whisper-Transkript, Grading-Kette, geteilte Nodes. Nutzen bei "neues Resolve-Projekt", "Kameras synchronisieren", "Multicam schneiden", "Resolve per Skript steuern". Von wunder-media (https://wunder-media.de).

  • Kampff

    YangKangSung/kampff-skills/kampff Skill

    0★ repo

    Human analysis from published text traces — worldview, alliance fit, temporal drift, distance (engage/neutral/caution/avoid). Community-member pipeline: collect posts/comments/likes honesty triad → bundle.json → spectrograph L1–L5 + default MBTI (fun) + CIA/KGB-style public tradecraft persona report. Triggers: /kampff, kampff, 사람 분석, 인물 분석, person analysis, community member, distance scoring, MBTI, CIA/KGB profile, mail/meeting/chat/sns/github, thread actors, 댓글 네트워크, 조직성, /kampff thread. Analyze reads bundle only; collect is a separate lawful step. No stalking.

  • Claude skill wake sleep

    colinzyang/claude-skill-wake-sleep Skill

    0★

    Add a wake-on-visit / auto-stop-when-idle (hibernation) mechanism to an AWS deployment to cut cost. Generates drop-in Terraform + Python Lambda wake/ autosleep functions + a manual CLI, assembled from composable adapters for the target's compute target, idle signal, and in-flight-work probe. Use when the user wants to: stop an idle EC2 / ECS / Auto Scaling Group / RDS and auto-start it on traffic or on a schedule; add a "serverless-ish" sleep mode to an always-on single box; save cloud spend by shutting down non-prod compute off-hours; hibernate / auto-start-stop / schedule a server.

  • Algotrace

    swapnil5053/algotrace Skill

    0★

    Visual-first DSA tutor and coach for LeetCode, online assessments (OA), and placement/interview prep. Use whenever the user mentions leetcode, dsa, data structures, algorithms, visualize, simulate, animate, trace, dry run, walkthrough, stuck, hint, nudge, debug my code, why is my code wrong, wrong answer, off-by-one, TLE, edge case, sliding window, two pointers, binary search, BFS, DFS, backtracking, dynamic programming, recursion, monotonic stack, heap, priority queue, union-find, trie, graph, tree, linked list, interview prep, mock interview, coding round, or OA practice. Coaches step by step with minimal diagrams instead of dumping full solutions.

  • Goal writer

    gillcash/goal-writer/goal-writer Skill

    0★ repo

    Assess whether a task is ready for an autonomous /goal loop, then convert rough notes into a compact /goal completion contract (under 4,000 characters) plus a rider context file - or refuse with a readiness verdict when the task has no measurable end state. Use this skill whenever the user mentions /goal, /loop, goal loops, rider files, long-running or autonomous agent tasks in Claude Code or Codex CLI, wants to "define done," asks to write a goal condition or stop condition, or wants an agent to keep working unattended. Also use it when the user pastes rough notes and asks for a goal or agent task contract, even if they don't say "goal-writer" explicitly.

  • Analyze density

    Max-Levitskiy/claude-code-marketplace/plugins/text-density-analyzer/skills/analyze-density Skill

    0★ repo

    Analyze text for information density, semantic repetition, and filler content. Two modes: "score" (read-only audit with per-method breakdown) and "fix" (rewrite to remove redundancy while preserving all unique information). Dispatches 7 core analysis methods (plus genre-targeted ones) as parallel subagents, then aggregates results into a composite score and actionable report. Use when asked to "check density", "find repetition", "remove AI slop", "deduplicate this text", "is this repetitive", "information density", "compress this writing", "tighten this doc", or whenever text feels bloated or AI-generated. Also use proactively when reviewing docs or PRs that contain suspiciously fluffy prose.

  • Skill doctor

    forgeron-AI/claude-skill-doctor/skill-doctor Skill

    0★ repo

    Audit and repair Claude skills that misbehave. Use when a skill never triggers, triggers on the wrong requests, produces inconsistent outputs, has grown too long to maintain, or when the user shares a SKILL.md saying "it doesn't work", "audit this skill", "why doesn't my skill trigger", "clean up this skill". Also use to review a skill before publishing or installing it. Do NOT use for creating a new skill from scratch, for prompt writing unrelated to skills, or for simple text correction.

  • Strony po ludzku

    wysocki-lu/strony-po-ludzku Skill

    0★

    Ostateczny audyt i korekta strony internetowej zrobionej z pomocą AI, żeby wyglądała jak zaprojektowana przez człowieka. Używaj po wygenerowaniu lub przed oddaniem KAŻDEJ strony/landinga: usuwa AI-tells wizualne (gradienty, sztancowe sekcje, zaokrąglenia, eyebrow), treściowe (frazesy, wymyślone liczby, placeholdery, resztki angielskiego) i techniczne (favicon, meta, alt, RODO, stopka bez danych firmy). Siostrzany skill pisz-po-ludzku.

  • Analogy check

    natexai2026/2030-skills/skills/analogy-check Skill

    0★ repo

    Discipline any historical or analogical argument by stating what actually transfers, what breaks, and what base rate the precedent implies — before the analogy is allowed to carry a conclusion. Use whenever an argument leans on "X is like Y," a historical precedent, or "this is just the next [printing press / internet / electricity / dot-com]." Triggers on comparisons to past technologies or events, "history shows," "we've seen this before," precedent- based forecasts, and persuasive analogies in writing or strategy. If a claim rests on a comparison doing the reasoning, run it through this first.

  • Branch sweeper

    vetterj73/branch-sweeper Skill

    0★

    The Sweeper cleans up local git branches across all repos under a root directory. Use when the user asks to run the sweeper, sweep branches, clean up local repos, delete merged branches, prune local branches, tidy up git branches, check for open Azure DevOps pull requests across repos, check which repos have uncommitted changes or in-progress merges and rebases, or audit which repos have a non-main default branch. Runs Clean-LocalGitBranches.ps1 and summarizes its JSON report.

  • Picture book skill

    jingk1012-ux/picture-book-skill Skill

    0★

    根据任意主题生成一本完整的儿童绘本,并输出为一个可在浏览器打开的自包含 HTML 文件:包含分页故事文案、每页一张原创内联 SVG 插画、单页朗读按钮、自动朗读模式、翻页动画和键盘翻页。当用户提到“儿童绘本”“绘本”“给孩子讲故事”“picture book”“bedtime story”“睡前故事”“儿童故事配图”“英文绘本”“English story for kids”,或想为某个主题、道理或事物做一本给孩子看的图文故事时,使用本技能。

  • Architecture review

    AmanKrSahu/zeroday-auditor/skills/architecture-review Skill

    0★ repo

    Use when the user wants a focused architecture/design review of a codebase — 'review the architecture', 'assess the system design', 'is this well structured?', 'evaluate modularity/coupling/layering', 'map the request lifecycle and dependencies', 'will this scale architecturally?'. Produces a single evidence-backed report (architecture-review.md) with a structure map, request/auth flow, dependency analysis, risks, and improvement proposals. For a full multi-dimension audit use zeroday-auditor instead. Analysis only; never modifies source.

  • Doc tools

    szilikaroly/claude-skills/doc-tools Skill

    no license0★ repo

    Extract text from PDF, Word, Excel, PowerPoint and LaTeX files, and edit/generate .docx and .tex programmatically. Provides the CLI commands pdftotext, doctotext, xlstotext and latextotext plus a compiled LaTeX toolchain (pdflatex/xelatex/latexmk via TinyTeX). Use whenever a task involves reading, converting, extracting from, or producing a document file — .pdf, .docx, .doc, .xlsx, .xls, .pptx, .ppt, .odt, .ods, .rtf, .csv, .tex — including "what does this PDF say", "pull the tables out of this spreadsheet", "turn this into a Word document", "compile this LaTeX", or feeding document text into another pipeline. Hungarian triggers: PDF kiolvasása, Word/Excel fájl feldolgozása, szövegkinyerés, dokumentum konvertálás, LaTeX fordítás.

  • Invoice formatter

    syedahmad0786/skills-runtime/skills/invoice-formatter Skill

    0★ repo

    Draft a clean plain-text invoice from a work description (client, line items, rates). Use when asked to create or format an invoice.

  • Apify google events ai

    johnisanerd/claude-skill-google-events-ai/apify-google-events-ai Skill

    no license0★ repo

    Give an AI agent live local event data from Google Events with the Apify Google Events Scraper Actor (johnvc/google-events-api---access-google-events-data). One bounded call takes a query like events in Austin this weekend and returns structured listings, title, start_date, when, address, venue name and rating, and ticket_info seller links, ready for an agent to rank, summarize, or drop into a calendar. Use when the user wants google events ai, an events feed for an AI agent or assistant, event discovery inside Claude, a what is happening this weekend helper, a calendar copilot that suggests concerts or conferences, or wants to wire local events into an app or agent workflow. Pay-per-page billing, MCP-ready for Claude and other AI agents.

  • Apify pre seed investors

    johnisanerd/claude-skill-pre-seed-investors/apify-pre-seed-investors Skill

    no license0★ repo

    Build a fundraising outreach list of pre seed investors with the Apify Startup Investors Data Scraper (johnvc/startup-investors-data-scraper). Filter a curated database of 10,469 firms by investment stage (Pre-Seed, Seed, Series A and beyond), industry focus, firm type, and country, and get investor firms with partner contacts, job titles, emails when available, LinkedIn URLs, and check sizes, ready to load into a CRM or outreach tool. Use when the user wants to find pre seed investors, seed investors, or early stage investors for a raise, build an investor outreach or lead list, find angel investors or VCs for a specific industry and stage, or ask who invests at pre-seed in their space. Research and outreach data only, no investment advice. Pay-per-firm billing, MCP-ready for Claude and other AI agents.