The catalog
608,352 rows, by stacks then stars
ShadowFull12/overhaul-ui/skills/overhaul-ui Skill
no license1★ repoFrontend design and UI craft. Use when building, redesigning, auditing, critiquing or polishing any interface - landing pages, dashboards, SaaS product UI, portfolios, e-commerce, docs, auth and form flows, AI chat apps, mobile screens, components, design systems. Covers design direction and taste, removing generic AI-slop aesthetics, typography, color and dark mode, layout and spacing, motion and animation, interaction and loading states, empty and error states, accessibility (WCAG 2.2 AA), Core Web Vitals performance, design tokens, responsive behavior, UX copy, data visualization. Triggers include design, redesign, overhaul, UI, UX, frontend, looks generic, looks AI-generated, make it look better, feel premium, polish, animate, motion, transition, typography, font, color, palette, dark mode, spacing, layout, responsive, accessibility, a11y, focus ring, contrast, empty state, skeleton, loading, design system, tokens, Tailwind, landing page, dashboard. Not for backend, data or infrastructure work.
robertogogoni/cortex-claude/src/skills/cortex Skill
1★ repo100% persistent memory system for Claude Code with auto-extraction, auto-recall, and compounding learnings (LADS)
Boom-Vitt/boombignose-plugins/plugins/thai-quotation/skills/quotation Skill
no license1★ repoปลั๊กอิน Claude Code: สร้างใบเสนอราคาภาษาไทย (Thai quotation) → HTML/PDF, VAT 7%, บาทถ้วนอัตโนมัติ — marketplace ของ BoomBigNose
yhyatt/dishonest-code-audit/skills/stub-audit Skill
1★ repoAudit a codebase for mock, stub, placeholder, or TODO code that lives in a real user-visible path (buttons that do nothing, hand-drawn placeholder SVGs that ignore their input, handlers that don't call the server, stale TODOs on shipped slices, hardcoded canned data in route handlers). Wraps language-specific tools (knip + leasot for JS/TS, vulture for Python, go vet for Go, cargo clippy for Rust, rubocop for Ruby) plus a tuned grep sweep to build a candidate list, then uses the model to judge each one against the question "does the user see this and does it lie to them?" Use whenever the user asks for a mock/stub/placeholder audit, a "what's fake in this codebase" pass, a stale-TODO sweep, a pre-release sanity check for unfinished work, or before shipping/cutting a release. Also use proactively at the end of a slice or before merging a feature branch. Output goes to a fresh `MOCK-STUB-AUDIT.md`.
AbigaleD/paper-explainer-video/skills/paper-explainer-video-en Skill
1★ repoTurn a research paper into a short narrated explainer video — Manim animation + edge-tts voiceover + synthesized BGM + Live2D anime host (Chinese & English skills for Claude)
cogniva/cogniva-skills/plugins/cogniva-dev/skills/plan-feature Skill
1★ repoClaude Code skills used at Cogniva.
fluxlay/claude-plugin/skills/fluxlay-wallpaper Skill
no license1★ repoClaude Code plugin for building Fluxlay wallpapers — scaffold, validate, and publish without leaving the chat.
saifulapm/focus/skills/focus Skill
no license1★ repoStop losing context. Stop repeating failures. Just focus.
say8425/hs-cli/plugins/hs-cli/skills/hearthstone-deck Skill
1★ repoHearthstone CLI for AI agents and humans. Decode deck codes, look up cards, query metadata via HearthstoneJSON
azagreev/life-planning-coach/plugins/life-planning-coach/skills/life-planning-coach Skill
1★ repoИнтерактивный evidence-based life coach для AI-ассистентов (Claude, Grok, Kimi). Постановка целей, планирование, привычки, ретроспектива — на русском языке.
PeterMalmkjaer/content-analysis-plugin/skills/content-analysis Skill
no license1★ repoScientific content analysis plugin for Claude Cowork — codebook, thematic analysis, ICR
Claude for it services and msps
travcjohnson/claude-for-business/skills/claude-for-it-services-and-msps Skill
1★ repoWorking Claude workflows for service businesses. One skill per trade, every prompt included, plus an honest list of what not to use Claude for.
yhyuk/claude-code-doctor/skills/claude-doctor Skill
no license1★ repoClaude Code 설정 진단 스킬 — CLAUDE.md, settings, skills/agents를 분석하고 등급과 개선사항이 담긴 HTML 리포트를 생성합니다.
Shivaprasadfarale/Reframe/skills/tailor-resume Skill
1★ repo🎯 AI-Powered Universal ATS Resume Tailoring Engine. Automatically reframes your experience, projects, and skills to match any Job Description into 1-page LaTeX & PDF.
adelaidasofia/claude-plan/skills/plan Skill
1★ repoTemporal Agency skill that moves your to-dos into Google Calendar as time-boxed blocks, protects biological anchors (sleep, exercise, meals) first, separates maker from manager time, and tracks scheduled-vs-shipped as a credibility scorecard. Four modes: /plan week (Sunday planning), /plan morning (daily forward briefing + gratitude), /plan review (Friday scorecard + closure), /plan touch (reactive when a meeting request lands mid-day). Trigger when the user says /plan, "plan my week," "what's my day," "review the week," or when a new meeting request arrives and they ask whether to accept.
CognitiveVR/c3d-marketplace-public/plugins/cognitive3d-public-api/skills/cognitive3d-public-api Skill
1★ repoA marketplace to share public plugins from Cognitive3D
adryanmoldokkr32-pixel/banana-claude/skills/banana Skill
1★ repoAI image generation Creative Director powered by Google Gemini Nano Banana models. Use this skill for ANY request involving image creation, editing, visual asset production, or creative direction. Triggers on: generate an image, create a photo, edit this picture, design a logo, make a banner, visual for my anything, and all /banana commands. Handles text-to-image, image editing, multi-turn creative sessions, batch workflows, and brand presets.
The same file is in 2 other repositories
benry-products/wcag-auditor/skills/wcag-auditor Skill
1★ repoUse when the user wants to audit their own web application for WCAG accessibility compliance, run an a11y check on a URL (including authenticated routes), generate a markdown accessibility findings report, fill in a VPAT / ACR, or get concrete remediation diffs for accessibility violations. Default target is WCAG 2.2 Level AA (covers 2.0/2.1 A/AA transitively); AAA is opt-in. VPAT fill-in requires a user-supplied ITI VPAT 2.5 INT template; covers WCAG + Section 508 + EN 301 549 via crosswalks.
AlperErd0gan/investor-council/skills/investor-council Skill
1★ repoSimulates a council of 7 legendary investors (Buffett, Lynch, Graham, Soros, Dalio, Wood, Munger) each analyzing your investment idea through their own publicly documented philosophy. Educational simulation only — NOT financial advice. Use when user says "investor council", "what would Buffett think", "analyze this investment", "should I buy", "is this a good investment", "get investor perspectives", "what would X think about Y", "council review", "analyze this stock", "watchlist", "rank these stocks", "export analysis", or invokes /investor-council.
AlaskaAirlines/auro-ai/plugins/auro/skills/post-mortem Skill
no license1★ repoyaniv-golan/telegram-webapps-skill/.agents/skills/telegram-webapps Skill
1★ repoBuild Telegram Mini Apps (Web Apps) — interactive web applications embedded inside Telegram. Covers the full stack: HTML boilerplate, browser dev mock, JavaScript SDK, BotFather setup, initData validation (Node/Python/Go), SPA navigation, Telegram Stars payments, and advanced APIs.
Zakir0vT/Docent-Skill/skills/docent Skill
1★ repoДуальный режим: уголовник Доцент и заведующий детсадом Трошкин из «Джентльмены удачи». Тот же ответ, та же точность — наконец-то с душевностью Леонова.
ansible-tmm/status-skill/skills/status-skill Skill
no license1★ repoClaude Code skill that generates weekly status reports from Google Calendar, Gmail, Meet transcripts, and GitHub activity
rainshed/research-companion/skills/research-companion Skill
no license1★ repoA named research companion for academic/scientific projects. Triggered when user says '科研伙伴', 'research companion', '研究搭档', or mentions the companion's custom name (registered in CLAUDE.md after first use). On first use, asks the user to give the companion a name. Maintains layered persistent memory and collaboratively identifies next research steps.
ChrnX0/proofgate/skills/proofgate Skill
1★ repoAcceptance gate to run BEFORE declaring any delivery "done" (feature, bugfix, release, deploy, PR merge-ready). Four layers — a mechanical gate (tests, push state, 18 diff guards) that writes a SHA-bound verdict, a judgment gate with an evidence hierarchy (believed → static → tested → exercised → in-prod) that demands proof for every claim, an adversarial skeptic pass, and hooks that refuse to push or declare done without a fresh passing verdict. Also use when a bug reappears or a fix has failed twice.
skar8848/Morpheus/.claude/skills/morpheus Skill
no license1★ repoellyseum/claude-cordyceps/skills/cordy Skill
1★ repoDrive `cordy` (the @ellyseum/cordyceps CLI) to consult peer LLMs from different model families — Codex (OpenAI), Gemini (Google), Ollama (local), and additional Claude variants — for ANY task where cross-model input improves the answer: code reviews, plan critiques, red-teaming, brainstorming, decision exploration, claim cross-checking, meta-reviews of reviews. Capability skill — Claude picks the right shape (single peer query, silo'd panel + chair, adversarial pair, divergent panel, tiered escalation, persistent sidecar, meta-review) for the user's ask. ACTIVATE on explicit cross-model phrases: "consult peers", "spawn council", "convene council", "ask the panel", "code review with peers", "plan critique with peers", "brainstorm with peers" / "brainstorm with multiple LLMs", "what would <name-of-model> think about this", "ask Codex/Gemini/Ollama". TIGHT, NOT BROAD: phrases like "second opinion", "peer review", "plan review", "red team this" are AMBIGUOUS — they can mean "Claude take another pass" rather than "spawn external models". Activate on those ONLY when accompanied by a target artifact (file, plan, claim) AND a peers/panel/multi-model signal. Otherwise ask a one-line clarifying question first. SKIP on trivial / time-sensitive tasks. Cross-model consultation costs latency and tokens; only invoke when the task rewards multiple perspectives.
sensortower/playliner-ai-plugins/plugins/playliner/skills/playliner-search Skill
1★ repoPlayliner AI plugins for Claude Code
pixeloven/crew/skills/agent-platform-design Skill
1★ repoDesigning agent capabilities and surfaces — the three interface classes (MCP, AXI, CLI) and which one a capability belongs in, skill vs agent tradeoffs, surface naming, and the operator-layer vs autonomous-runtime scope distinction. Load when designing a new agent capability, deciding whether a tool federates through the gateway or stays local to one machine, or evaluating platform options.
sabirmgd/swarmfish/skills/swarm Skill
1★ repoSwarmFish - Multi-agent swarm intelligence engine. Predict outcomes by simulating diverse stakeholder interactions. Commands: init, run, report, dashboard, chat, graph, metrics, svg, pdf, query, status, inject, check, config
samrith-s/ebert/skills/ebert Skill
1★ repoOpen Ebert's review UI for a PR, branch, or diff the user asked you to review, then act on their comments. Use only when the user explicitly asks for a code review, PR review, or `/ebert:review` — never as a routine end-of-task step.
aws-samples/sample-gpu-open-weight-bench/plugins/bench-open-model/skills/bench-open-model Skill
1★ repoRun a POC on any open-weight model and validate your GPU needs in one session. Sizes VRAM, provisions the right instance, benchmarks it on vLLM, and tears everything down so you know what fits, how fast it runs, and what it costs before you commit.
MisreadableMind/human-writing-skill/human-writing/skills/human-writing Skill
1★ repoLLM generates Slop, Human write GREAT texts. Teach LLM to be more human.
Autonomous loop engineering team
SamiKolarkar/autonomous-loop-engineering-team/skills/autonomous-loop-engineering-team Skill
1★ repoAsynchronous 7-engineer team driven by /loop + background Agent spawns. Use when user says "autonomous loop", "/loop + auto-team", "async engineering team", "/autoloop", or asks to drive a project through an unbounded engineering cycle where Team Leader orchestrates via /loop ticks instead of blocking calls. Mirrors the role definitions in ~/.claude/CLAUDE.md §1 but replaces Workflow() with run_in_background=true Agent() calls keyed by task_id stored in state.md, so each /loop tick is one phase transition.
MaYiding/Skills/skills/a2a-development Skill
no license1★ repoA2A (Agent-to-Agent) protocol v1.0 development guide for Python. Use when building A2A agents, creating multi-agent systems, implementing A2A servers or clients, working with Agent Cards, handling Task lifecycle, implementing streaming or push notifications, integrating frameworks (LangGraph, Google ADK, BeeAI, AG2, CrewAI, Semantic Kernel, Microsoft Agent Framework) with A2A, configuring OAuth2/PKCE/mTLS security, implementing multi-tenancy, using extensions, or migrating from v0.3 to v1.0. Triggers: 'a2a', 'agent-to-agent', 'agent card', 'TaskUpdater', 'AgentExecutor', 'A2AStarletteApplication', 'A2AClient', 'ClientFactory', 'a2a-sdk', 'HandoffTool', 'RemoteA2aAgent', 'langgraph-a2a-server', 'to_a2a'. Do NOT use for MCP (Model Context Protocol) tool-calling patterns or non-A2A agent communication.
CipherandRow/claude-hive-plugin/skills/hiverev Skill
1★ repoPersona-driven review of anything, from any angle. Point it at a UI, a landing page, a cold email, a README, a pitch deck, an onboarding flow, an API design, or any artifact, pick who is looking at it and what lens they bring, and get a prioritized friction punch list. Lighter than /hivesim. Triggers when user says /hiverev, "review this as [persona]", "what would [persona] think", "find friction in this", or "critique this from the angle of [X]".
corbitsdev/agents/plugins/corbits/skills/corbits Skill
no license1★ repoA skill package for Claude Code or OpenCode to directly discover and call paid API proxies on the Corbits platform.
jordanburke/supabase-typed-query/.claude/skills/supabase-typed-query Skill
1★ repoStefanKarpinski/karpinski-claude-plugins/plugins/process-probe/skills/process-probe Skill
1★ repoStefan Karpinski's personal Claude Code plugin marketplace
Snap-Developers/SnapCode-CC-Plugin/plugin/skills/snaplogic-deploy Skill
no license1★ repoSnapLogic SnapCode distribution via a Claude Code plugin marketplace.
furkanzt/claude-tdd-bdd-harness/skills/tdd-bdd-harness Skill
1★ repoBootstrap or maintain a self-enforcing TDD+BDD discipline in any repo — executable Gherkin scenario catalogue with machine-verified test citations, coverage matrix, CI meta-guard, gap-grinding workflow, adversarial test audits, and a quality-loop layer for behaviours only a live system can prove. Use when the user says "adopt TDD/BDD", "scenario catalogue", "spec harness", "test discipline", or wants this project's testing methodology ported to another repo.
VascendTechnologies/Vascend-Official-Plugins/vascend/skills/danilov-prompt Skill
1★ repoStructured prompts and verifiable execution for Claude Code agents. The Danilov method: INDEX/DEFINITIONS/RELATIONS prompts, one-hot DanilovGoal tracking with an HMAC-signed trace and a deterministic verdict, plus token-efficient .vascend memory. Zero dependencies.
ZhengHe-MD/ZhengHe-MD/skills/engoo-daily-news-writer Skill
no license1★ repoMy personal repo
Endeavor-Brasil/endeavor-plugin/endeavor/skills/endeavor Skill
no license1★ repoRhyanz46/go-rest-skills/skills/code-review-business Skill
no license1★ repoDeepDiver1975/claude-rpg-skills/skills/cyberpunk-red-oneshot Skill
no license1★ repoAarvinGeorge/Claude-workflow-framework/.framework/bundles/design-frontend/skills/shadcn Skill
no license1★ repoManages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", or "switch to --preset".
The same file is in 135 other repositories
MartinForReal/compress-text-skill/skills/compress-text Skill
1★ repomanji6/brand-slide-kit/skills/design-extractor Skill
1★ repoPPTX・PDF・画像・スクリーンショット等の参考資料からデザイン情報を抽出し、design-guideline.yaml を生成するスキル。ユーザーが「デザインガイドラインを作って」「このPPTXからブランドカラーを抽出して」「参考資料を元にデザイン定義ファイルを作って」「design-guideline.yaml を生成して」「このスライドのブランド情報を取り出して」などと依頼したときは必ず使用すること。PPTX・PDF・画像ファイルが渡されてデザイン情報の抽出を求められた場合も積極的にトリガーする。
aks-builds/ai-test-failure-analyzer/skills/ai-test-failure-analyzer Skill
no license1★ repo8-phase evidence pipeline for Playwright, pytest, Jest, Cypress, Newman, k6, and JUnit failures. Scans git history, application logs, and config to produce confidence-scored root-cause hypotheses. Exposes as MCP server, CLI, and streaming web UI.
Sortium-io/voxcpm-voice/skills/voxcpm-voice Skill
no license1★ repoClaude Code skill: generate any voice (announcer, character, narrator, villain, AI) using VoxCPM2 voice design — text-only, no reference audio needed.
MB-uc/mercury/mercury/skills/ms-crawl Skill
no license1★ reponnovaeshc/hc-scaffold-service/skills/hc-scaffold-service Skill
no license1★ repoCreates a new service, component, or other resource from any registered Backstage software template through conversation, without opening the Backstage UI - walks the template's own schema and infers values from context, catalog precedent, and conversation, so it keeps working as new templates are added to the catalog. INVOKE FOR the /hc-scaffold-service command, or requests to scaffold, create, or spin up a new service, component, API, microservice, or Lambda from a Backstage template (e.g. "create a service for payment callbacks", "scaffold a Lambda API", "new service from template") - even if the user never says the word "Backstage". SKIP for code changes inside an existing app/repo (e.g. "create a React component in this app"), general questions about Backstage or its catalog, or ops tasks against services that already exist (docker compose, deploys, restarts).
arash77/github-actions-skill/skills/github-actions-hardened Skill
no license1★ repoGenerate production-hardened GitHub Actions CI/CD workflows enforcing least-privilege permissions, concurrency groups, timeout guards, dependency caching, and latest major version action tags. Always co-generates a .github/dependabot.yml. Also use this skill to HARDEN EXISTING workflows using zizmor — applies persist-credentials, template injection fixes, permissions, and optional SHA pinning automatically. Use this skill whenever the user asks about CI, CD, pipelines, GitHub Actions, YAML workflows, automated testing, deployment, releases, security audits, SOC 2, compliance, zizmor, workflow hardening, or "fixing" workflow security — even if they don't say "hardened" or "secure". Always prefer this skill over github-actions-templates for any workflow that touches production, uses third-party actions, or needs to pass a code review. Trigger for any GitHub Actions workflow request, whether creating new or hardening existing workflows.
VietUy001/iOS2Android/plugins/ios2android/skills/ios2android Skill
no license1★ repoClaude Code skill for porting iOS SwiftUI apps to Android Jetpack Compose with measurable parity: a binary Definition of Done, script-checked visual, behavioural and motion gates, and a process benchmark. README in 5 languages.
Sherpa-wtf/sherpa-skill/skills/sherpa-bot-optimizer Skill
1★ repoSkill (Agent Skills) para analizar conversaciones de un bot de Sherpa y editar sus flujos de forma segura, vía el MCP de Sherpa.
MaikelHeijen/socrates/skills/teach Skill
1★ repoAdaptive Socratic tutor. Probes current understanding of a topic, plans a fact-checked curriculum, and teaches it one step at a time with applied-reasoning checks and self-checked visuals. Use for "/socrates:teach <topic>", or "/socrates:teach" with no topic to pick from topics already in progress.
priyank766/OpenSource-SKILL/skills/contributor-experience-review Skill
1★ repoa OpenSource Code Review Skill for everyone
Evolvlabsai/Competitive-Research-Skill/skills/competitive-research Skill
1★ repoRun a thorough weekly competitive feature analysis on the current codebase and produce a ranked, evidence-backed list of features the product is missing. Use this skill whenever the user asks for competitive research, competitor analysis, feature ideas, gap analysis, product roadmap input, "what are competitors doing," "what should we build next," "what features are we missing," weekly product strategy review, or anything similar — even when the user doesn't explicitly say the word "competitive." Also use it for tasks framed as "look at competitors and tell me what to build" or "help me figure out what to add to my product." Auto-discovers product identity, JTBDs, features, and constraints from the codebase, so it works zero-config.
itseasyco/easy-skills/skills/premortem Skill
1★ repoUse when the user asks to premortem, stress-test, future-proof, find blind spots in, or "find what could kill" a plan, launch, product, hire, strategy, pricing change, partnership, or any commitment where the cost of being wrong is high. MANDATORY TRIGGERS — "premortem this", "premortem my", "run a premortem", "what could kill this", "future-proof this", "stress test this plan", "what am i missing here", "find the blind spots". STRONG TRIGGERS — "what could go wrong with", "am i missing anything", "poke holes in this", "where will this break", "devil's advocate this". DO NOT trigger on requests for general feedback ("thoughts on this?", "what do you think?", "review this") unless the user also signals they want failure analysis or stress-testing. Do not trigger on factual questions, simple edits, or already-irreversible decisions.