The catalog
608,253 rows, by stacks then stars
HacQueen2025/Claude-Skills/content-pipeline Skill
0★ repoUniversal content creation and scripting skill. Use this skill whenever the user wants to create scripts, voiceovers, outlines, storyboards, or content plans for ANY format — YouTube long-form, YouTube Shorts, Instagram Reels, TikTok, LinkedIn video, podcasts, documentary, explainer animations, ads, webinars, online courses, audiobooks, or presentations. Works for ANY topic: education (math, science, history, economics, philosophy), entertainment, business, tech, storytelling, news, self-help, finance, culture. Each format gets a specific script template. Optimized for AI voiceover (ElevenLabs) and human narration both. Also triggers for: "write me a script", "plan a video about", "content strategy for", "outline for a talk".
tenki-labs/public-claude-skills/plugins/tenki-public-skills/skills/bokmaal-proof Skill
0★ repoUse when the user types /bokmaal-proof, /bokmål-proof, or asks to "proof this Norwegian text", "rydd opp i denne teksten", "fix this bokmål", "check the Norwegian", "remove anglicisms", or wants stylistic and register-level review of Norwegian bokmål technical or business writing. Does more than grammar: catches anglicisms, register drift, Språkrådet recommendations, and the typical translation-from-English smell.
christiankoerbs-ui/agent-docs-skill Skill
0★Generate and maintain AI-agent-optimized documentation in `.agents/docs/` so coding and design agents load only the slice of the repo they need. Use this skill whenever the user mentions "bootstrap documentation", "update documentation", "set up agent docs", "generate agent context", "make this repo agent-readable", "sync agent docs after changes", or any request to produce, refresh, or per-module-document a codebase for AI agents — even if they don't say "agents.md" explicitly. Inspired by retrieval-led passive-context findings (Vercel agents-md evals).
pagoda111king/claude-code-pack/template/.claude/skills/case-study-gen Skill
no license0★ repoAutomatically repurpose completed client projects (or any work with content value) into 5 content types: anonymized case study + WeChat moments + Xiaohongshu + WeChat blog + Twitter/LinkedIn. This is the core of the methodology source flywheel—every delivery fuels acquisition.
OiiOAI/Query-Amplifier Skill
0★搜索放大器 - 将单一搜索词扩展为关联词、替代说法、别称和圈层暗语。触发词: 扩展搜索, 相关词, 替代说法, 圈层用语, 查询扩展, 同义词搜索, 帮我扩展, 更多说法
wilson534/editorial-resume Skill
0★Generate a single-page A4 PDF resume in editorial bilingual (中/英) style — the kind that lands top-tier tech jobs. Trigger when the user asks to build, write, update, polish, or export their resume; or wants a "looks-like-Peng-Zhiwei's-resume" PDF. Reads the user's context (chat history, attached docs, GitHub repos, LinkedIn dump, prior drafts) and produces a printable PDF without asking 20 questions.
slysik/ibm-bob-the-builder/skill Skill
no license0★ repoBuild anything in the IBM watsonx / Cloud Pak for Data 'Data Fabric' stack from the CLI: provision watsonx.data lakehouse (Presto/Spark/Milvus, Iceberg catalogs, COS buckets), IBM Knowledge Catalog (catalogs, projects, data assets, glossaries, policies, masking, lineage), DataStage flows, Data Virtualization, Watson Query, Master Data Management / Match 360, watsonx.ai foundation-model deployments, watsonx.governance factsheets, COS buckets, IAM access groups, trusted profiles, service IDs, API keys. USE FOR: ibmcloud login, ibmcloud resource service-instance create, ibmcloud plugin install cloud-pak-for-data / cloud-object-storage / code-engine, cpdctl wx-data engine create, cpdctl wx-data bucket register, cpdctl asset data-asset create, cpdctl project create, cpdctl wx-ai deployment create, cpdctl datastage flow create, Presto/Iceberg/Spark/Milvus on watsonx.data, IKC catalog + glossary + governance rules, watsonx.ai prompt + RAG deploy, watsonx.governance factsheet, design IBM data fabric reference architecture, compare watsonx.data vs Snowflake. DO NOT USE FOR: Snowflake/Cortex (use snowflake-cortex), Azure Foundry, AWS Bedrock.
physics4noobs/physics-solver-skills/jee-advanced-physics-solver Skill
0★ repoSolve JEE Advanced physics problems — multi-concept, multi-correct, integer-type, matrix-match — from photos, screenshots, text, or WhatsApp forwards. The skill searches the internet for existing solutions (FIITJEE, Allen, Resonance, Brilliant, JEE Advanced official keys), independently derives symbolically, verifies with Python/SymPy, cross-checks against internet consensus, and iterates up to three times — essential for Advanced where one missed case in multi-correct zeroes the mark. Stages a WhatsApp-ready reply with full derivation for teacher approval. Trigger whenever the user shares a JEE Advanced physics problem OR mentions JEE Advanced, JEE Adv, IIT advanced, Paper 1, Paper 2, matrix match, multi-correct, integer type. Also trigger on problems with multi-concept coupling (mechanics + thermo, optics + EM), non-trivial calculus, tricky limits, or four options where multiple may be correct.
Mothilal-M/remotion-video/.agents/skills/remotion-best-practices Skill
no license0★ repoBest practices for Remotion - Video creation in React
Browse emails to find opportunites
khanhvo2172-dotcom/seo-skills/browse-emails-to-find-opportunites Skill
0★ repoRead personal emails from 3 platforms HARO, MentionMatch & Qwoted to find relevant opportunities for TrueProfit
fengyiqicoder/m365-meeting-prep Skill
0★Use when the user has a meeting coming up and wants to prepare. Triggers on "prep for my meeting", "what should I know about X before our call", "research these people", "I have a meeting with [Company/Person] tomorrow", "build my brief", "background check on the prospect", "what's our history with this customer". Also triggers when user mentions specific upcoming meetings, calendar reviews, or wants intelligence briefings before sales/customer/investor calls.
cjcsecurity/claude-tabletop/skills/tabletop-aar Skill
0★ repoDraft an After-Action Report (AAR) from a completed tabletop exercise. Reads the filled forms in a `tabletop-exercises/<slug>/` directory (or a JSON export from the interactive HTML runbook) and produces a structured AAR with executive summary, timeline reconstruction, what-went-well/didn't, gaps, prioritized action items, and recommendations. Use after running an exercise generated by `/tabletop`. Trigger phrases: "draft the AAR", "write up the tabletop", "after-action report", "post-exercise writeup".
p-vbordei/dsl/skills/dsl Skill
0★ repoBuild and maintain a Domain-Shared Lexicon — a glossary of domain terms that you and the AI agree on. Use when the user says "build a lexicon", "we keep using term X differently", "set up a glossary", "what does Y mean in this project", or whenever you notice the same word being used for two different concepts in conversation. Also activates at session start when a lexicon file is present.
tagius/slides-animejs Skill
0★Build a PowerPoint-style, 16:9 full-screen, browser-served slide presentation animated with anime.js v4. Orchestrates content brainstorming (scientific-brainstorming), academic structuring (scientific-slides), UI/UX design (ui-ux-pro-max), static authoring (slides-grab), animation patterns (anime.js-best-practices + Context7), PPTX intake (pptx), and sparse comic relief (meme-factory). Outputs a self-contained bundle the user runs with `python3 run.py`. Trigger when the user asks to make an animated web slideshow, browser-served presentation, or convert a pptx to an interactive HTML deck with animations.
zelixag/debug-probe Skill
0★Hypothesis-driven runtime debugging with precise instrumentation. Use when debugging bugs, anomalies, or unexpected behavior where static code analysis is insufficient. 6-phase loop: hypothesize → instrument → reproduce → converge → fix → clean up. Triggers on: debug, diagnose, broken, bug, not working, unexpected behavior, investigate, root cause, probe.
2389-research/compcat/skills Skill
0★ repoUse when the user invokes /compcat — almost certainly a typo of /compact. Outputs an ASCII COMPuter CAT (cat sitting at a terminal) with a fresh silly quip each time, then nudges the user to type /compact for real. Levity for the typo, with the actual answer spelled out.
missionbuilt/loadout/floodlight Skill
0★ repoFloodlight. A visibility-first security posture overview built from three inputs — where you can see an attacker and where you're blind, mapped to ATT&CK tactics. Triggers: "run floodlight", "build my security posture", "where am I blind", "visibility assessment".
WebCrawlerAPI/skills/webcrawlerapi Skill
no license0★ repoScrape a single page or crawl a full website using WebCrawlerAPI. Trigger for: fetching page content, getting markdown from a URL, scraping a page, crawling a website/domain, websearch, webfetch.
ztnkv/personal-operating-system/.claude/skills/grill-me Skill
0★ repoInteractive "grill" session — asks pointed questions one at a time to surface blind spots in the current picture of the user and enrich the context for memory. Invoke when the user says "grill me", "ask me questions", "/grill-me", "I want to enrich the memory", "what don't you know about me", "ask me hard questions", or otherwise asks to be interviewed.
reshinto/gemini-skill Skill
0★Gemini API access for Claude Code: text, multimodal, structured output, embeddings, plan review, search grounding, media generation, files, caching, and more.
riddhi-mazumdar/zeitgeist-decoder Skill
0★Decode cultural signals, semiotics, and search intent into defensible marketing strategy for in-house teams. Use this skill whenever the user mentions cultural trends, zeitgeist, semiotics, trend reports, cultural insight, audience analysis, keyword research with demographic or geographic angles, search intent, brand permission, cultural codes, or wants to turn a cultural observation into a brief, deck, or one-pager. Trigger even when the user describes the task in plain language ("help me figure out if my brand can talk about X", "what does this trend actually mean", "is this just hype or a real shift", "find me keywords for this audience in this city"); they are asking for cultural decoding even if they don't use the word. Also trigger when the user wants to sanity-check whether a creative idea is grounded in a real cultural shift versus a passing meme.
baronguyen001/ai-automation-skills/skills/algora-bounty-scout Skill
0★ repoScout public Algora org bounty boards at algora.io/<org>/bounties?status=open - parse amount and linked GitHub issue, dedupe, then filter already-assigned issues, saturated races, joke bounties, dead-lane orgs, and maintainer comments that say the bounty is inactive. Use for scout algora, find OSS bounties, or open source bounty hunting.
kumarswathi/storekit2-claude-skill Skill
0★Scaffolds a complete StoreKit 2 auto-renewable subscription implementation in a SwiftUI iOS app — including a subscription manager actor, transaction listener, customizable paywall view, and a local .storekit config for sandbox-free testing. Use this skill whenever the user wants to add subscriptions, in-app purchases, paid tiers, or premium features to an iOS app, even if they don't explicitly say "StoreKit." Also use when they mention paywalls, RevenueCat alternatives, App Store subscriptions, or "monetize my iOS app." Targets iOS 17+ and SwiftUI.
GGGODLIN/claude-skills/skills/ai-image-gen Skill
0★ repoSingle entry point for ANY request to create, generate, design, draw, make, render, produce, or edit a visual asset. This explicitly includes logos, icons, brand marks, and design briefs — they count as image-generation tasks under this skill, not as generic "design work". Also covers photos, illustrations, comic/anime art, diagrams, flowcharts, wireframes, mockups, posters, banners, textures, sprites, concept art, and edits of existing images. Triggers on vague image requests ("做一張圖", "need an image") AND on traditional-sounding design briefs ("設計一個 logo", "做個 icon"). Trigger phrases (any language): "產圖", "生成圖片", "畫一張", "做一張圖", "做張圖", "做個圖", "畫個", "設計 logo", "設計一個 logo", "做個 logo", "設計圖標", "做個 icon", "generate image", "make an image", "create picture", "render image", "design a logo", "make me a logo", "I need an icon", "AI art", "illustration", "brand mark". ALWAYS invoke this skill when the user request could plausibly resolve to a visual output, even if it looks like a traditional design brief.
zack-dev-cm/tutorial-to-skill-free-pack/skills/affiliate-ugc-test-planner Skill
0★ repoPlan compliant affiliate UGC test campaigns from a product or niche into disclosure-safe hooks, short-form video briefs, carousel briefs, platform routing, cost assumptions, test metrics, and kill criteria. Use when the user wants to test affiliate products with AI-generated UGC, Pinterest pins, TikTok/Reels/Shorts, Claude/Higgsfield-style workflows, or similar content-generation systems without making unsupported income, health, or testimonial claims.
brianamazzio/design-system-toolkit/skills/design-system-generator Skill
0★ repoGenerates a complete design system for a project. Use when asked to create, generate, or build a design system. Runs a structured brand interview, then produces two outputs: an HTML visual style guide and a markdown spec file at /docs/design-system.md. Also updates CLAUDE.md references automatically. Invoke with /design-system-generator.
semanticpixel/abc/plugins/abc/skills/plan Skill
0★ repoProduce a draft PLAN-*.md file within the first few tool calls — structured for downstream consumption by /abc:scaffold-sub-issues (Linear issue creation) and /abc:ship-epic (parallel multi-repo shipping). Front-loads writing over Q&A. TRIGGER when the user says "/plan", "draft a plan for X", "write a PLAN doc", or asks Claude to plan a feature/migration/refactor before implementation.
dreamor/llm-wiki-obsidian/skills/llm-wiki-obsidian Skill
0★ repo基于 Karpathy LLM Knowledge Base 模式的个人知识库管理技能。通过 Obsidian CLI 与本地 Obsidian Vault 交互。核心思想:LLM 不是在查询时从原始文档重新发现知识, 而是增量构建和维护一个持久的 Wiki——结构化的、互联的 Markdown 文件集合。 当添加新资料时,LLM 会读取、提取关键信息并整合到现有 Wiki 中。 **触发条件**:用户提到知识库、Wiki、整理知识、建立知识体系、Obsidian、摄入资料、 查询知识、维护个人知识库、或讨论 Karpathy/Wiki 模式。
daehounan/k-jp-business-navigators/skills/japanese-business Skill
0★ repoJapanese business culture and deal mechanics for foreign professionals. Use when the user asks about 稟議 (ringi) / 根回し (nemawashi) consensus process, 空気を読む (KY) signal reading, 名刺交換 business card protocol, 飲み会 / 接待 entertainment, 報連相 (hou-ren-sou) communication, LINE/Chatwork business etiquette, Japanese hierarchy (社長/部長/課長 etc.), keigo selection, お中元/お歳暮 gift timing, Golden Week/Obon calendar, 検討させていただきます / 前向きに検討 decoding, hanko 印鑑 contracts, or preparing for any meeting/call/email with a Japanese counterpart. Also triggers on phrases like 日本 取引先, 日本 商談, ビジネス日本語, 稟議, 根回し, 名刺, 飲み会, 商習慣.
simple11337/do-ui/skills/no-ai-slop Skill
0★ repoStrip AI slop from UI and Next.js code output. Use when generated or reviewed React, Next.js, or TypeScript code contains redundant comments that restate the code, leftover TODO and placeholder stubs, debug remnants like console.log and debugger, bloated JSDoc, decorative banner comments, or lazy type escapes like as any and ts-ignore. Trigger when the user asks to clean up generated code, remove AI comments, deslop, or tidy UI output, and run automatically as a review pass in the DO-UI pipeline.
MaskedControl/skills/skills/create-docx Skill
0★ repoUse when creating or generating a Word document (.docx) for a client, email, or report. Covers Windows setup, running docx-js scripts in a temp folder, cleanup, and formatting patterns (tables, bullets, callout boxes, screenshot placeholders). Triggers on requests like "create a Word doc", "generate a .docx", "make a report in Word", or "build a document for the client."
mickzijdel/vischeck/skills/setup-auth Skill
0★ repoSet up the dev auth bypass route so the screenshot tool can authenticate. Invoke when screenshot fails with an auth/login redirect, or when the user explicitly asks to set up dev auth.
labrodev/laravel-playbook/skills/labrodev-action Skill
0★ repoUse when creating, reviewing, or refactoring write-side domain classes in a Labrodev Laravel project: Actions (e.g. BookingCreate, BookingUpdate, BookingRemove), domain Services, or {Model}Rule classes — including guard ordering, DB::transaction wrapping, UUID assignment, and choosing between throwing ValidationException and a silent no-op. Staged multi-step workflows live in labrodev-pipeline.
dpyeye-commits/my-arsenal-marketplace/skills/building-inflearn-courses Skill
no license0★ repoBuilds 12-chapter Inflearn course packages (PROPOSAL, slides, hands-on code, 5-style citation appendix) with auto revenue estimation. Use when the user requests 인프런 강의 만들기, 온라인 강의 12장 기획, PROPOSAL 작성, or 강의 슬라이드 자동 양산.
arturayupov/awesome-claude-skills/skills/doc-harvester Skill
0★ repoMirror an external platform's documentation site into the current project as local markdown files, so the coding agent can cross-check the official docs offline while building. Use this whenever a documentation or wiki URL appears together with a request to study, learn, fetch, download, mirror, save, scrape, or "vendor" the docs — including phrasings like "изучи документацию", "скачай документацию по ссылке", "собери вики", "study these docs", "pull the API docs into the repo", "I'm integrating with X, get its docs". Use it even if the user just pastes a docs link and says "learn this" without naming a tool, and even if they only give a deep link to one page. Prefer this skill over ad-hoc WebFetch whenever the goal is to capture a whole documentation set rather than read a single page.
Shankulkarni/react-native-ai-plugin/plugins/rn-ai/skills/animations Skill
0★ repoUse when implementing animations or gestures -- GPU-only properties, Reanimated v3 worklets, useDerivedValue, GestureDetector press states, layout animations, React Compiler compatibility.
hideokamoto/wordpress-skills/skills/wordpress-handbook Skill
0★ repoSearch WordPress official handbooks for development guidelines, coding standards, and best practices. Use when users ask about WordPress plugin development, theme development, REST API usage, block editor (Gutenberg), coding standards, or advanced administration. Triggers on questions like "How do I create a custom post type?", "What are WordPress coding standards?", "How does the block editor work?", or any WordPress development concept questions.
naudini/naudini-skill Skill
0★MCP & OpenAI function-calling skill — find and book boat charters in the Mediterranean from any AI agent
slogsdon/skills-engineering-reference/skills/auth Skill
0★ repoSecure authentication and authorization patterns — password hashing, brute-force protection, session vs JWT, OAuth/SSO flows, RBAC. Use when the user says "add login", "set up auth", "is this auth secure", "implement OAuth", "session vs token", "should I use JWT here", or when shipping any feature that gates access. Do NOT use for guessing at credentials or bypassing auth — refuse those.
marcgarciaseo/tribu-seo-local/.agents/skills/tribu-seo-local Skill
no license0★ repoSkill de **auditoría y planificación SEO local** para consultores hispanohablantes (España, México y resto de LATAM). Audita el Perfil de Empresa de Google (GBP), la web, el NAP, las citaciones, las reseñas, el schema, el hreflang, el contenido local y los Core Web Vitals de un cliente o de una ficha Rank and Rent, y produce un plan accionable + entregables comerciales (informes, propuestas, contratos R&R). Al invocarla pregunta primero si el trabajo es para un cliente real (sesgo conservador) o para una ficha Rank and Rent propia (sesgo agresivo). Incluye tácticas white-hat, grey-hat y black-hat marcadas por nivel de riesgo (🟢🟡🔴). Las 🔴 black-hat se documentan ejecutables con aviso explícito del riesgo (penalización o suspensión posible) para que el consultor decida con información. Úsala cuando vayas a auditar un GBP, una web local o todo el cluster SEO local de un cliente hispanohablante, o cuando montes y operes fichas Rank and Rent propias.
lifenewjob/nebo-claude-skills-public/skills/nebo-coding-patterns Skill
0★ repoCODING-PATTERNS SuperSkill v2.0. Triggers: рефакторинг", "код ревью", "дебаг", "архитектура", "паттерн", "performance", "bulletproof. Use when: Starting a feature; Debugging a bug; Code review
dylanmoo/workos-plugin/skills/create-project Skill
0★ repoBootstraps a new project in a WorkOS-style workspace. Use whenever the user says 'create a project,' 'new project,' 'spin up a project,' 'add a project,' 'start a new client,' 'add an engagement,' or asks to start a new client engagement, recurring workflow, or area of work that should have its own context. Creates the subfolder with CLAUDE.md and MEMORY.md following the standard project structure, then registers the project in the appropriate routing map (root or domain) so future sessions auto-load it. The successor to /create-workstation in v1.x — same skill, simpler name.
PlevanTem/luban-skill/.claude/skills/agents Skill
0★ repoLists all luban-distilled expert agents currently installed in this project. Renders a structured roster grouped by domain family, showing slash command, display name, sub-specialty, stage, and vibes_risk for each. Activates when the user asks "which agents do I have", "list my experts", "show available agents", "what luban agents are loaded", "/agents", or similar discovery queries. Does not activate for general "list skills" queries (that's Claude Code's built-in `/` palette), only for luban-distilled expert personas.
kennykankush/skillpack/plugins/agents/skills/autoreview Skill
no license0★ repoAuto Review closeout. Codex review is the default when no engine is set and is the recommended reviewer.
Kirchlive/Claude-Full-Context-Agent/skills/fan-out-fork-agents Skill
0★ repoOperational patterns for orchestrating multiple parallel forks in Claude Code. Covers the parent-prepares → async-dispatch → parent-merges lifecycle, worktree hygiene (including the .claude/worktrees/ gitignore lesson), the practical 6-8 concurrency limit (vs. ~10 scheduler-cap), fork-registry tracking, mandatory reporting contracts, and the federation pattern (fork-then-named-subagent for unbiased two-layer parallelism). Apply this skill EVERY time you are about to dispatch 2+ forks in the same turn, EVERY time a fan-out returns and needs reconciliation, and BEFORE the first fan-out in a new project (to set up gitignore). Complements prefer-fork-agents which decides WHEN to fork; this skill governs HOW to coordinate fork fan-outs.
fergus/claude-kimi-delegate Skill
no license0★Use when the user wants to delegate a task to Kimi Code CLI. Triggered by phrases like 'Kimi, ...', 'Hand this to Kimi', or when the user explicitly asks to send work to Kimi. This skill manages the delegation bridge, task file creation, and result handling.
glass-uk/interview-prep Skill
0★This skill should be used when the user asks to "interview me", "start an interview", "mock interview", "practice interview questions", "do a mock interview", "prep for interviews", "ask me a behavioral question", "ask me a technical question", "test my system design", "give me a Kafka question", "quiz me on Spring Boot", "quiz me on MongoDB", "quiz me on Java", "give me a DSA question", "run an interview session", "practice for senior roles", "pressure mode interview", "real interview mode", "review my code", "evaluate my code", "tailor questions to this job", "questions based on this JD", or wants to rehearse for software engineering job interviews.
n3owise/brand-launchpad Skill
0★Generate a creative-director-level brand system and a polished standalone HTML brand board for startups, products, SaaS tools, portfolios, media brands, entertainment labels, agencies, creator businesses, fashion brands, and studios. Use when the user wants branding, visual identity, art direction, landing-page style, tone of voice, design language, or a presentation-ready concept board. The skill should create three clearly different directions, recommend one with conviction, and output browser-ready artifacts instead of chat-only text.
locallaunchsc-cloud/solana-dev-skills/anchor-scaffold Skill
0★ repoUse this skill when the user wants to bootstrap a new Solana Anchor program from scratch — install toolchain, scaffold project, write a first instruction, build, test, and deploy.
richardvt/claude-skills-journalism-tw/journalism-core-tw/skills/ai-writing-detox-tw Skill
no license0★ repo偵測並改寫中文 (繁體中文/台灣) AI 寫作 pattern (對應 upstream ai-writing-detox 的英文版)。涵蓋:濫用的中文形容詞與排比、「值得我們深思」「在這個...的時代」「不僅...更...」家族、設問句濫用、中國大陸用語滲透 (視頻/網絡/軟件/質量)、四字成語堆疊、新聞文體浮誇詞 (揭密/驚爆/震驚)、學者腔/演講腔、全形破折號濫用。寫新聞稿、評論、深度報導、訪談稿、社群貼文、政策報告之發稿前檢查時觸發。記者使用 AI 協助起草後的人工潤稿必備。
kemsig/repo-polish Skill
0★Polish, clean up, and professionalize any code repository — of any language, framework, or domain. Use when the user wants to make a repo presentable, publish-ready, or portfolio-grade: "polish this repo", "clean up my repository", "professionalize this project", "prepare this for GitHub / open-source / a recruiter", "write a proper README", "add CI/CD", "add a PR template", "set up a .gitignore", "remove secrets", "get rid of junk / large files / committed datasets / model weights / .idea / __pycache__". Handles secrets removal, git-history bloat, README/docs, .github templates, CI/CD, licensing, and hygiene — safely, never pushing or rewriting history without explicit consent.
aksheyw/claude-code-ship-gate/plugins/ship-gate/skills/ship-init Skill
0★ repoScaffold a .shipgate.json for this project by auto-detecting its test/lint/typecheck/build commands and deploy target.
sindev08/react-principles-skills/skills/reactprinciples-audit-recipe Skill
0★ repoAudit an existing React Principles cookbook recipe for accuracy against the actual codebase. Invoke when the user (as a cookbook maintainer) says "audit recipe X", "check recipe accuracy", or "verify recipe is up to date". Reads the recipe file, checks every import path and pattern claim against the real codebase, flags discrepancies, and reports findings with fix suggestions. This is an internal maintainer skill — not promoted to end users.
vincent-wen789/japan-parking-advisor/skill Skill
0★ repoJapan parking decision assistant — region-specific (Japanese sources, lot types, mechanical-lot traps, and discount rules), NOT a universal solution. Use when the user mentions driving to a place/venue in Japan and asks "where do I park", "which lot is cheapest/free", "is there free parking near X", "park for free if I spend ¥Y", or "where's convenient to park when I drive to <place>". Searches the live web for nearby candidates, filters by the user's car (height/width limits — the safety-critical "can my car physically enter" check), and returns a top pick + 2-3 parallel nearby alternatives, each with a Google Maps link. Data honesty is exception-triggered (only speaks up when something is off); an unknown height/width limit is always stated. Trigger even on a casual "where do I park when I drive to X (in Japan)".
jihonghe68/skill-workshop/plugins/skill-workshop/skills/skill-auditor Skill
0★ repoSkill 提示词质量审查工具。当用户想检查、评估或改进任何 SKILL.md 文件的提示词质量时, 立即使用本 skill。触发关键词包括:审查 skill、检查提示词、skill 质量、SKILL.md 评估、 提示词有没有问题、帮我看这个 skill、skill auditor、audit skill、优化 skill 提示词、 全库扫描、扫描所有 skill。 即使用户只是说「帮我看这个 skill 好不好」也必须触发本 skill。 本 skill 输出结构化质量报告,自动修复可修复问题,并生成「待人工确认」清单。
Build-Your-Sales/data_gouv_mcp_bys/skills/ciblage Skill
no license0★ repoRun the full BYS targeting methodology on the French market — Discovery (10 questions), CAB-P matrix, 10 ciblages (signal × persona × geo) backed by real French companies fetched via the data.gouv MCP and the API Recherche d'entreprises. Use after /data-gouv-bys:setup to produce the strategic brief and lead lists.
jordanl17/claude-skill-linear-editing/skill-src Skill
0★ repoRender Linear issues as an interactive inline editor for review and edit before saving. Works for fresh drafts AND substantive edits to existing issues (title and/or description). A freeform prompt field captures next-turn instructions. Use when the user wants to draft new Linear issues OR rewrite the title or description of an existing issue inline, including phrases like "draft a Linear issue", "queue up Linear tickets so I can edit", "look at SAPP-1234 and let's edit the description", or "rewrite the description of X". The widget IS the editing surface; do not draft the content as Markdown prose first. Do not trigger for read-only queries (list, search, assign, comment). Do not trigger for single-field swaps ("change the title to X"); apply those inline. Do not trigger for one-shot create-and-save with no review step.
zavora-ai/skill-itsm-service-management Skill
no license0★Orchestrate IT service management — handle support requests with KB-first resolution, triage incidents, manage ticket lifecycle, process change requests, and track SLA compliance. Use when handling IT support issues, triaging incidents, checking SLA status, creating change requests, searching the knowledge base, or reviewing open tickets.
AmineYagoub/p2d/skills/p2d Skill
0★ repoCode navigation, refactoring, and impact analysis for any codebase. Finds symbols, traces dependencies, maps blast radius, renames safely, and performs surgical edits using structural AST tools. Use when the user asks to find usages, find references, navigate code, refactor, review changes, rename across files, check impact, understand dependencies, or edit code without breaking anything. Covers code review, best practices, and code quality workflows. Works on projects of any size. Also handles: safe rename, deletion simulation, state ownership mapping, and recall-aware benchmarks. Triggers on: "find all usages", "where is this used", "refactor", "blast radius", "rename", "safe to change", "is this still used", "can I delete this module", "what breaks if I remove", "update all related files".
LiozShor/design-log-skill/design-log Skill
0★ repoThe /design-log Stop & Think planning protocol for non-trivial features, bug fixes, refactors, workflow changes, UI changes, automations, or architecture decisions. Asks clarifying questions, researches the domain via an MCP web research tool, explores the codebase in plan mode, creates or updates a persistent design log, and waits for approval before implementation. Based on Yoav Abrahami's Design-Log Methodology (https://github.com/yoavaa/design-log-methodology).