The catalog
608,253 rows, by stacks then stars
Runesmith-Studio/claude-vault Skill
0★Back up Claude Code account data and migrate it across machines and accounts. Use when the user wants to: back up ~/.claude; migrate conversation history, CLAUDE.md, skills, settings, and memory to a new machine or new account; or when `claude --resume` can't find / is missing past conversations (often because moving machines or non-ASCII / CJK project paths cause project-directory slug collisions). Cross-platform (macOS / Linux / Windows), Python stdlib only.
aneebbaig/app-starter-skills/plugins/app-starter/skills/fastapi-app Skill
0★ repoBootstrap a new FastAPI backend, or audit and retrofit an existing one, with async SQLAlchemy 2.0, asyncpg, Alembic, Pydantic v2, and no deprecated APIs. Use when the user wants to start, scaffold, or set up a new FastAPI service, a Python REST API, an async backend, or asks to "create a new fastapi app" or "new python backend". ALSO use on an existing FastAPI or Python API codebase when the user asks to audit, review, fix, clean up, refactor, modernize, upgrade, harden, or "bring up to standard" the service, migrate off SQLAlchemy 1.x or Pydantic v1 patterns, remove deprecated APIs, or improve the structure. Handles JWT auth, layered app structure, Docker + Postgres, and Vercel or container deploy.
tengfone/agents/skills/brainrotify Skill
no license0★ repoRewrite developer-facing prose into playful Gen-Z "brainrot" language without changing executable code. Use when an AI coding agent or assistant needs to transform comments, docstrings, Markdown, README files, or other documentation text surfaces in one file or a directory while preserving syntax, logic, formatting, and code fences. Support optional backup creation and three intensity levels: `L`, `Mid`, and `W`.
oh-summy/skills/skills/agnes-generate-image Skill
0★ repoGenerate or edit an image with Agnes AI. Supports text-to-image and image-to-image via agnes-image-2.1-flash.
xts-x-xvxl-wxrld/MapWrite/skill/mapwrite Skill
0★ repoNavigate repo-specific wiki protocols, code-index maps, and agent update rules. Use when Codex needs to work in a repository that has `wiki/index.md`, `wiki/code-index/`, `AGENTS.md`, or `CLAUDE.md`; when creating, updating, or following wiki specs/plans; when creating or maintaining nested code indexes; when deciding which project files to read before code changes; or when updating agent-facing project navigation instructions.
Claws-Temple/claws-temple-bounty2.0-skills/skills/claws-temple-bounty Skill
no license0★ repoUse when the user is explicitly inside the Claws Temple Bounty 2.0 workflow, names Claws Temple / 龙虾圣殿 / Claws Temple Bounty 2.0, or is already continuing this branded five-task path. This skill packages the five-step journey that sends an Agent into the wild to make friends. Do not use for generic numbered tasks, generic bounty requests, or unrelated partner-matching requests outside this brand context.
nkur22/subscription-tracker/subscription-tracker Skill
0★ repoScan a user's Gmail to find upcoming subscription renewals, recurring payments, and billing deadlines. Use this skill whenever the user asks about their subscriptions, recurring charges, upcoming renewals, payment schedules, billing timelines, or wants to audit what services they're paying for. Also trigger when users say things like 'what am I subscribed to', 'when is my next bill', 'show me my recurring payments', 'subscription audit', 'what's renewing soon', 'am I still paying for X', or any variation involving tracking, managing, or reviewing subscription costs from their email. This skill requires the Gmail MCP connector to be enabled.
heliy/sup-learn/sup-learn Skill
0★ repoUse this skill whenever the user wants to build, train, evaluate, or iterate on a supervised machine learning or deep learning model. Triggers include: any mention of training or fitting a model with labeled data, dataset preparation, hyperparameter tuning, cross-validation, model checkpointing, experiment tracking, overfitting, loss curves, metrics, or prediction visualization. Also trigger when the user describes a supervised modeling task even without explicit ML terminology — e.g. "I want to classify X", "predict Y from Z data", "I have labeled data and want to build a model", "which model should I use for...", "my model isn't working / is overfitting / performs badly on new data", "I want to forecast X from historical data". Also trigger when the user shares existing supervised model code or a trained model and asks for feedback, review, improvement suggestions, or an explanation of what it does.
momomuchu/youtube-insights Skill
0★Extract transcripts and key insights from YouTube videos. Handles single or multiple URLs. Uses yt-dlp for reliable transcript extraction, supports all languages. Actions: get transcript, summarize video, extract insights, analyze video. Triggers on: YouTube URL, 'insight video', 'resume video', 'transcript', 'what does this video say'.
claudifytech/claude-code-skills-starter/skills/code-review Skill
0★ repoRun a structured self-review pass on changed files before opening a pull request
r-bart/scribetronic-plugin/plugins/scribetronic/skills/agenda Skill
0★ repoManages the writing cadence using per-ISO-week directories under scribetronic/calendar/. Combines recurring rules + per-week plan.md + history. Subcommands: show, plan-week, add, skip, done, rules. Used by /write router and /write-publish.
The same file is in 1 other repository
stakiran/gists/.claude/skills/generate-gists Skill
0★ repostakiran の GitHub Gists を取得し docs/ に静的サイト用 Markdown を生成する
lukeleekr/claude-github-scout Skill
0★GitHub 레포 스카우터. 내 Claude Code + Codex App 환경을 분석하여 필요한 GitHub 레포를 자동 추천하거나, 키워드로 GitHub을 검색합니다. "scout", "스카우트", "깃헙 탐방", "레포 추천", "repo search" 등의 키워드에 반응합니다.
cdragos/agentarium/skills/pytest-microservices-skill Skill
no license0★ repoPytest test development for Python microservices. Use when writing unit tests, integration tests, fixtures, mocking external services, or setting up test infrastructure. Triggers on requests to create tests, debug failing tests, test organization, factory fixtures, parametrization, or testcontainers.
edimuj/claude-workshop/plugins/codex-async/skills/codex-async Skill
0★ repoFire-and-forget async Codex delegation. This skill should be used when delegating debugging, implementation, refactoring, or code review to OpenAI Codex without blocking the current conversation. Trigger when: (1) implementation or refactoring touching 3+ files — do not attempt yourself, delegate, (2) debugging after 1-2 failed root-cause attempts — stop spinning and hand it off, (3) user says 'delegate to codex', 'send to codex', or 'use codex', (4) conserving Claude Max quota — delegate coding/debugging to Codex, reserve Claude for architecture/design/narrative, (5) any task you would spawn a haiku subagent for — use gpt-5.4-mini instead, it is cheaper and smarter. IMPORTANT: Err on the side of delegating. If the task involves writing or debugging 50+ lines of code, delegate it. The context and quota spent attempting it yourself almost always exceeds the cost of a Codex delegation. Do NOT delegate: architecture decisions, creative/narrative work, trivial 1-3 line fixes.
xonack/wp-gutenberg-claude-skill/skills/wp-gutenberg Skill
0★ repoComplete Gutenberg block development reference covering registration, edit/save components, dynamic blocks, InnerBlocks, variations, patterns, supports, build pipeline, transforms, testing, and performance optimization.
Chris1220-cmd/deep-research-skill Skill
0★Deep research with NotebookLM + web search. Iterative multi-source research with domain boost, source credibility, and post-research artifact generation (podcast, video, slides, quiz). Free alternative to Perplexity/Gemini Pro. Use when user says "/deep-research", "research this", "deep dive into", or "investigate".
Wayne-Lee-cs/Bug_Hunter_Skill Skill
0★KemenyStudio/roier-seo Skill
0★Technical SEO auditor and fixer. Use when the user wants to: - Run a Lighthouse/PageSpeed audit on a website or local dev server - Analyze SEO, performance, accessibility, or best practices scores - Fix technical SEO issues in their codebase - Optimize meta tags, structured data, Core Web Vitals - Improve page speed, accessibility, or PWA compliance Triggers: "audit my site", "check SEO", "fix SEO", "lighthouse", "pagespeed", "improve performance", "meta tags", "structured data", "core web vitals"
mukul-mschauhan/praxis-agent-suite/skills/evaluation Skill
no license0★ repoAgentic AI system built on Claude Skills
mnox/mnox-ai/plugins/aio/skills/aio Skill
0★ repoAgentic Implementation Optimizer — audit existing agentic AI implementations for reliability/cost/architecture issues, walk through creating new agentic implementations from scratch, or extend existing implementations with new capabilities. Use when: '/aio', 'audit my agent', 'build an agent', 'agentic review', 'extend this agent', 'agent architecture', 'optimize my agent'. Covers architecture patterns, reliability engineering, guardrails, cost optimization, observability, escape-hatch/abstention design, gap-signal capture, and production readiness.
re-sianturi/lp-insights/.claude/skills/lp-insights Skill
0★ repoGenerate hypothesis-driven landing-page feedback with simulated personas.
amomorning/zh-quotes-skill Skill
0★A Claude Code skill that fixes Chinese quotation marks breaking code syntax. Context-aware typography: ASCII quotes in code, Chinese quotes in prose.
puretechnyc/purebrain-skills/skills/content/blog-banner-creation Skill
0★ repoCreate branded blog header images with strict layout rules, safe zones, and brand color application. Python/Pillow implementation with 75% safe zone rule for mobile-safe rendering.
kazhuki7/agentskills-proxy/skills/example-skill Skill
no license0★ repoAn example skill demonstrating the framework capabilities. Use when testing skill execution with JavaScript, Python, or Shell scripts.
Antheurus/sshepherd Skill
0★Use this skill whenever the user mentions "sshepherd" by name, or wants to check on a remote server (health, disk, memory, CPU, ports, OOM history), inspect or restart docker/systemd services, tail remote logs, read or write remote config files, deploy a project via a named recipe, introspect a remote Postgres database, or audit SSH/security posture on a box — while keeping the agent zero-knowledge about credentials (no password, private key, or host/user/port ever reaches the agent's context or a tool response). Covers all 9 registry-driven command groups (hosts, check, logs, services, deploy, config, db, files, security) via a single compiled Bun/TypeScript CLI that shells out to the system `ssh` binary — the agent only ever passes an ssh alias, a pg-target name, or a recipe name, never a credential. `setup` is a separate group (deliberately not one of the 9) that writes sshepherd's own local config files; every `setup` action is agent-invocable, with one narrow exception — `setup ssh-alias install` opens a one-shot browser form that only a human can type a password into.
ddtraveller/lesson-builder Skill
0★Generates bilingual TEFL/ESL courses with lessons, exams, flashcards, conversations, pronunciation drills, worksheets, and syllabi for any language pair.
knckknck/skills/skills/baseline-ui Skill
0★ repoValidates animation durations, enforces typography scale, checks component accessibility, and prevents layout anti-patterns in Tailwind CSS projects. Use when building UI components, reviewing CSS utilities, styling React views, or enforcing design consistency.
The same file is in 2 other repositories
searayca/claude-skills/skills/add_copyright Skill
no license0★ repoAdd copyright headers and footers to source files in a project using ~/.claude/tools/add_copyright_headers.py
giovicordova/skills-gc/skills/auto-improve Skill
no license0★ repoRun a configurable loop that incrementally improves a target (agent, skill, doc, folder, CLAUDE.md, README) by verifying every external claim (URLs, library names, quoted attributions, named principles, project-style rules) against authoritative sources and tightening prose one small pass at a time. Use whenever the user says "auto-improve X", "polish X over time", "loop improving X", "verify and tighten X", "keep refining X", "iterate on X for a while", or invokes /auto-improve. Each pass touches one file, either editing in place (staged for review) or appending compact checkbox findings to AUTO-IMPROVE-FINDINGS.md for later interactive review. Mode, loop interval, and target are chosen interactively at start. NOT for first-draft writing, code refactors, or bug fixes.
riccardogiorato/rate-limit-this Skill
0★Audit a JavaScript or TypeScript web app, especially Next.js, for abuse and rate-limit surfaces, ask the human only material policy questions, write a root RATE_LIMITS.md for review, and route an explicitly approved specification to a fresh implementation agent. Invoke manually to design fair usage policies, choose protections suited to the existing stack, or implement a reviewed rate-limit contract.
deokjinlog/design-explosion-30-styles/skills/design-style-explorer Skill
0★ repo사용자가 도메인(제품·서비스 주제)을 지정하면 그 도메인의 대표 화면을 30가지 디자인 스타일(SF HUD, 공공포털, 트렌디 SaaS, 고밀도 터미널, 브루탈리즘, 글래스모피즘, 미니멀 모노크롬, 럭셔리 다크, 레트로 픽셀, 에디토리얼, 네이처 오가닉, 뉴모피즘, 오로라 그라디언트, 벤토 그리드, 클레이모피즘, 머티리얼, Y2K 베이퍼웨이브, 스위스, 맥시멀리즘, 다크 대시보드, AI 프로덕트, 핀테크 소프트, 엔터프라이즈 B2B, 헬스케어 웰니스, 커머스 리테일, 다크 프로 미니멀, 웜 프로페셔널, 하이컨트라스트 접근성, 컬러풀 모던, 데이터 리치 라이트)의 HTML 시안으로 만들어 비교하게 해주는 스킬. 사용자가 "디자인 시안 뽑아줘", "스타일 비교", "30개 디자인", "○○ 도메인으로 디자인 보여줘", "디자인 탐색", "어떤 스타일이 어울릴지" 등을 말하거나, 새 제품/화면의 비주얼 방향을 고민할 때 반드시 이 스킬을 사용할 것. 특정 스타일 이름(브루탈리즘, 글래스모피즘 등)을 언급하며 화면을 요청할 때도 사용.
xltang/hotspots Skill
0★用于拉取并展示最新热点内容(接口为 https://hotspot.api4claw.com/hotspots/latest?timestamp=$TIME_STEMP,返回 JSON 数组)。按模型预估点击率生成 Top 条目(不使用原始热度排序)。默认会提示用户创建定时任务(不自动执行),在用户确认后提供 cron 注册命令。适用于用户查询最新热点、服务状态、按 source_name 分组标题、Top 内容,或由已存在的定时消息触发执行。触发词:"今日热点"、"今日头条"、"热点新闻"、"热点"
martimramos/cairn-claude-memory/cairn/skills/init-memory Skill
0★ repoScaffold the per-repo session-memory structure (docs/NOW.md, docs/log/ daily journals, CLAUDE.md protocol section). Use when the user says "init memory", "onboard this project", or accepts the new-project memory offer. Also handles "no memory" opt-out.
automateandtweak/a-and-t-claude-skills/skills/wcag Skill
0★ repoAudit a page for WCAG 2.1 AA accessibility issues. Traces the render chain, checks structural/semantic HTML, contrast indicators, ARIA, and outputs a prioritized report.
robertsilen/vibe-dba/skills/mariadb-ai-dba Skill
no license0★ repoMariaDB AI DBA — connects to a MariaDB database and produces a factual server inventory covering configuration, schema, performance counters, security, and MariaDB-specific features. Use when the user asks to analyze, audit, health-check, or inventory a MariaDB or MySQL database, or asks for database performance advice with a live server available.
Kieldro/claude-skills/plugins/review/skills/review Skill
no license0★ repoRun a code review using Cursor Agent with Gemini
thinkyou0714/claude-lab-skills/.claude/skills/validate-skills Skill
0★ repoValidate the skill packs and run repo checks (structure, lint, types, tests). Use when asked to validate skills, check the repo, or verify a new/edited SKILL.md.
belousov-petr/strata/skills/strata Skill
0★ repo3-tier project memory (hot/warm/cold) with a unified issues backlog, operation-keyed learnings, generated indexes, immediate capture, and one-shot project initialization under .strata/. Invoke with no argument for rule lookup, "capture" to save a fresh finding/gotcha right away, or "init" to scaffold or migrate existing flat/0.0.1/0.0.2 memory without losing provenance. Used by /strata:save, /strata:load, and /strata:capture as the authoritative source of tier definitions and routing rules.
abedegno/reverse-engineering-companion/plugins/reverse-engineering-companion/skills/android-mitm-setup Skill
0★ repoIntercept a mobile Android app's HTTPS traffic on Android 7+ where TLS pinning is in force. Walks through rootable emulator selection, mitmproxy CA installation into the system trust store, proxy routing, and Frida-based pinning bypass. Use when you need to see what an Android app is sending over the wire — for security research, API documentation, or interoperability work.
withqwerty/ship/skills/debrief Skill
no license0★ repoUse this skill when the user wants a weekly check-in, retrospective, or recalibration of how they're building. Trigger on "ship debrief", "debrief", "weekly check-in", "how am I doing", "where did my time go", "ship retro", "debrief with dhh", "recalibrate my profile", "update my priorities", or when the user wants to reflect on their recent work and adjust direction. Also trigger when another ship skill nudges that a debrief is overdue. Do NOT trigger for code review (use ship-review), profile setup (use ship-init), or mid-build scope checks (use ship-focus).
ufec/ai-grimoire/skills/react-i18next Skill
0★ repoComplete best practices for using react-i18next and i18next in React Native / React projects. Trigger this skill when the user mentions internationalization, multilingual, i18n, i18next, react-i18next, translation files, namespace, language switching, locale, AI translation, or auto-translation. Applicable scenarios: setting up i18n architecture from scratch, namespace design for large-scale projects (10+ pages), TypeScript type-safe integration, translation file structure conventions, AI auto-translation workflows, and any i18next-related questions.
LuisHiluy/claude-code-pipeline-skills/clip-feedback Skill
0★ repoAnalyze an AI-generated video clip against the prompt that produced it. Detects canon rule violations, emotion/energy/world mismatches, palette drift, and quality issues, then suggests specific prompt fixes to improve the next generation. Use whenever the user has a Veo, Seedance, Kling, Runway, or other AI-generated clip and asks "why does this look wrong", "check the clip", "check this clip", "prompt feedback", "analyze this clip", "compare clip to prompt", or anytime a video was generated from a prompt and needs iteration. Trigger this skill even when the user casually asks "is this good" about an AI clip — prompt vs reality analysis is the job.
r-bart/scribetronic/.claude/skills/scribetronic-help Skill
0★ repoIntroduces the scribetronic project layout, CLI, and skills to AI agents working ON this codebase.
hauntedstack/prompt-forge Skill
0★4-pass prompt-optimaliseringsmotor som kombinerer 7 skills til en pipeline som garanterer 5/5 i alle kvalitetsdimensjoner. Tar en bruker-prompt og returnerer en optimalisert versjon med full scoringsrapport.
r04943083/doc-search-skill/skills/doc-search Skill
0★ repoSearch indexed documents (PDF, Word, Excel, PPT, TXT) using BM25 keyword search. Use for EDA tools, company docs, bug reports, and technical documentation.
outreachmagic/email-finder Skill
0★Waterfall email enrichment through trykitt and Icypeas. Works standalone with just API keys. Pair it with Outreach Magic and it checks your local DB first. Skips leads you already have, saves the result so you don't run the same search twice. Optional MillionVerifier for bulk re-check.
Layton2617/cloud-bridge Skill
0★Multi-cloud DevOps skill — manage deployments, resources, logs, and costs across Vercel, Cloudflare, AWS, and more from Claude Code
x0c/image-assets-skill Skill
0★Prepare image assets. Use for background removal, transparent PNGs, resizing, compression, format conversion, multi-size variants, splitting N-grid sprite sheets into frames, generating transparent animated GIFs, cutout model comparison, or fixing image-processing toolchains.
rodrijuarez/mtg-argentina-skills/mtg-argentina-playwright Skill
0★ repoScrape full catalogs of Argentine MTG stores using Playwright MCP. Walks pagination correctly across Bazaar of Baghdad, Rancho Store TCG, Labatikueva, Al Battle TCG, Phoenix Reborn. Use when surveying stores for deals across product categories (Collector Boxes, Bundles, Secret Lairs, Commander Decks, etc).
chenpianzhou/zhangxiaolong-skill/zhang-xiaolong Skill
no license0★ repo以张小龙(微信创始人)的产品观评审产品方案、功能设计、PRD 或产品决策。当用户说"让张小龙看看"、"用张小龙的视角/产品观"、"张小龙会怎么想/怎么做",或希望用极简、克制、用完即走的标准拷问一个产品想法时使用。也可用于回答"微信为什么这样设计"类问题。
jonocbell/agent-decision-log/agent-decision-log Skill
0★ repoPersistent decision log that creates a read-write feedback loop: read previous decisions before starting work, respect or supersede them, and write new Y-statement records as you go. Activates during any task involving architectural, structural, or design decisions - choosing libraries, designing schemas, creating modules, making tradeoffs, selecting patterns. Also activates when DECISIONS.md already exists in the project. Do NOT activate for trivial changes like typos, renames, or formatting.
lowkey-divine/sovereign-skills/build-skill Skill
0★ repoBuild a Claude Code skill with sovereignty principles, constraint architecture, and refusal design baked in. Interviews you about what the skill should do, then generates a complete, deployable SKILL.md file.
entpnomad/ai-rank Skill
0★Optimize content for LLM discoverability AND AI agent consumption. Use when user runs `/ai-rank`, asks to "optimize for AI", "optimize for LLMs", "optimize for agents", "make content AI-readable", or needs to write/proofread landing pages, docs, blog posts for answer engines and autonomous AI agents.
y-a-v-a/skills/attribution Skill
0★ repoUse this skill when the user wants to add author attribution to a project, for example to a README.md or as a footer on a website. Handles bare invocation (falls back to git config), explicit name/email/website arguments, and free-form placement instructions.
y-a-v-a/codex-executor/.claude/skills/codex-validate Skill
0★ repoValidate the codex, codex-review, and codex-discuss skills end-to-end in a session where the Codex CLI is available — preflight, hook unit tests, and per-skill smoke tests that prove context actually reaches Codex — then self-improve by recording each run and tightening checks when something breaks. Use when codex is installed and you want to confirm the skills still work.
yWorks/yfiles-for-html-skills/skills/yfiles-graphbuilder Skill
no license0★ repoThis skill should be used when the user asks to "build a graph from data", "load data into a graph", "import JSON into yFiles", "create nodes from an array", "use GraphBuilder", or mentions "data to graph", "import data", "business data", "GraphBuilder", "TreeBuilder", or "AdjacencyGraphBuilder".
mikiwiik/claude-code-skills/miki-rebase-reflect Skill
0★ repoMiki's rebase-and-reflect skill. Rebases the current branch onto the latest default branch, attempting to resolve conflicts mechanically and prompting the user for judgment when a conflict requires a decision. After a clean rebase, reflects on what landed in the default branch — the nature of the changes and which incoming files intersect this branch's diff. Hands off only on unexpected git state (not on conflicts). Invoke when the user says "/miki-rebase-reflect", "rebase against main", "rebase against main and resolve conflicts", "pull main and reflect", "main moved, what changed", or similar.
Nima-Edelkhani/claude-ux-design-skill Skill
0★Use whenever designing or restyling a UI — landing pages, app screens, dashboards, marketing sites, prototypes, frontend mockups, Tailwind/shadcn work, HTML/CSS visual design. Opinionated rules that bias the output away from generic AI defaults toward considered, distinctive, human-designed-feeling work.
hseinmoussa/exo/skills/exo Skill
0★ repoOne-shot clear-output shaping. Invoke with /exo when you want a single answer led by the point, literal, complete, no filler. For always-on shaping use the exo output style or the bundled hook instead - this skill is the manual, per-invocation entry point, not the persistent mode.