agentic-awesome-skills

Agentic Awesome Skills — AI Skills & AAS Core

Find reusable instructions for your project, inspect their complete files, and keep an exact skill set you can review and reuse.

Agentic Awesome Skills is a library of 2,926+ installable SKILL.md playbooks for Claude Code, Codex, Cursor, Gemini CLI and other AI coding agents. AAS Core helps Codex or Claude search the complete local catalog, record the skills the agent chooses, and preview a plan you can inspect before changing a target. Core does not rank or recommend skills.

Start here: Explore the skill catalog · Codex setup · Claude Code setup · Install skills directly

Current release: V20.6.0. AAS Core supports local catalog inspection, agent-owned selection, stack validation, and plan preview. Apply and recovery remain experimental. Read the AAS Core preview guide for setup and exact trust boundaries.

This README tracks main. Features listed under Unreleased require a later release; the versioned guide describes the published package.

This is an independent community project, not affiliated with or endorsed by Google. Google, Antigravity, Gemini, and related names describe compatibility and install targets. The GitHub repository is canonical; the hosted catalog and browser-local Workbench are companion discovery and review surfaces.

Table of Contents

• Watch the Introduction
• Support the Project
• AAS Core: Agent-First Preview
• Installation
• Choose Your Tool
• Recommended Specialized Plugins
• Bundles & Workflows
• Browse 2,926+ Skills
• Troubleshooting
• Stable Skills Manifest v1
• Contributing
• Community
• Credits & Sources
• Top Contributors
• Repo Contributors
• Star History
• License

Watch the Introduction

A 40-second introduction to Agentic Awesome Skills and AAS Core, with music and on-screen explanations.

https://github.com/user-attachments/assets/0129747c-3e92-4a18-805f-58fe2e59909b

You can also watch the video on the AAS website.

Support the Project

Help keep the catalog open, maintained, and available to the builders who use it.

Support AAS	What it helps fund
♥ Sponsor AAS	Ongoing maintenance, reviews, and release work
Buy Me a Coffee	Small, direct contributions from the community

Every contribution helps us keep the skills curated, the tooling tested, and the catalog useful for the next project.

Security tooling support: Snyk.

AI compute & model credits: Atlas Cloud (supporting media generation workflows via atlas-cloud-media).

This project is tested with BrowserStack.

For a complete setup through your first skill selection and installation preview, follow Codex setup or Claude Code setup.

AAS Core: Agent-First Preview

Codex or Claude inspects your project and chooses exact skills. Every current catalog skill is individually searchable, readable, and available for agent selection. The read-only compose_stack tool validates the chosen IDs and structure in memory; a client or the aas CLI can persist aas-stack.json and optional selection evidence. aas stack validate checks the manifest, while aas stack plan writes an immutable preview for your review. Manifests have a technical maximum of 128 skills; Core does not rank or recommend candidates or install skills in this supported preview path.

[!IMPORTANT] Structural and identity validity does not certify semantic fit, compatibility, setup correctness, operational safety, or safety to apply. Apply and recovery require experimental opt-in and remain outside the supported preview.

The Workbench reviews stack and plan artifacts in browser memory without accessing your filesystem. See the Core guide for tool contracts, capability coverage, and limits.

Installation

From selection to use

Start with AAS Core in Codex or Claude. Configure the local MCP using the Codex or Claude guide. With the MCP available, ask the agent to inspect your project, compare relevant skills, and save the exact selection. Then validate its manifest and review the resulting plan before any installation. The first configuration command previews a change and returns an approval digest:

npm exec --yes --ignore-scripts [email protected] -- aas mcp configure \
  --host codex \
  --scope user \
  --config /absolute/path/to/codex/config.toml \
  --cache-root /absolute/path/to/aas-cache

Use --host claude and its configuration path for Claude. The Core setup guide explains approval, reconnection, validation, and planning. To hand the reviewed IDs to the direct installer, use aas stack install-preview as described in the manifest handoff; that command only prepares a --dry-run preview and does not apply a Core plan.

Install selected skills directly

If you already know the IDs, preview a focused install into your host's skill directory:

npm exec --yes --ignore-scripts [email protected] -- \
  agentic-awesome-skills --release 20.6.0 --path .agents/skills \
  --skills brainstorming,systematic-debugging --dry-run

Review the preview, then repeat without --dry-run when ready. The direct installer does not consume or apply a Core plan. Antigravity's watched skill directory can overload its context, so its default target requires a selected set, a filter, or an explicit --all override. See the installation guide and security guidance for other targets, auditing, and failure modes.

Choose Your Tool

Use the path for your agent. Core setup is available for Codex and Claude; the other rows show direct install targets or plugin options.

Tool	Install	First Use
Claude Code	AAS Core local MCP preview, direct install, or Claude plugin marketplace	Ask Claude to choose and compose an AAS stack
Cursor	npx agentic-awesome-skills --cursor	@brainstorming help me plan a feature
Gemini CLI	npx agentic-awesome-skills --gemini	Use brainstorming to plan a feature
Codex CLI	AAS Core local MCP preview or npx agentic-awesome-skills --codex	Ask Codex to choose and compose an AAS stack
Autohand Code	npx agentic-awesome-skills --path ~/.autohand/skills or --path .autohand/skills	Use brainstorming to plan a feature
Mercury CLI	npx agentic-awesome-skills --path ~/.mercury/skills or --path .mercury/skills	Use brainstorming to plan a feature
Antigravity IDE	npx agentic-awesome-skills --antigravity --skills <ids> --dry-run	Ask an MCP-enabled agent to choose exact IDs first
Antigravity CLI (agy)	npx agentic-awesome-skills --agy	/brainstorming help me plan a feature
Kiro CLI	npx agentic-awesome-skills --kiro	Use brainstorming to plan a feature
Kiro IDE	npx agentic-awesome-skills --path ~/.kiro/skills	Use @brainstorming to plan a feature
GitHub Copilot	gh skill install sickn33/agentic-awesome-skills skills/brainstorming/SKILL.md --agent github-copilot --scope user --pin v14.2.0 (preview)	Ask Copilot to use brainstorming to plan a feature
OpenCode	npx agentic-awesome-skills --path .agents/skills --category development,backend --risk safe,none	opencode run @brainstorming help me plan a feature
AdaL CLI	npx agentic-awesome-skills --path .adal/skills	Use brainstorming to plan a feature
Custom path	npx agentic-awesome-skills --path ./my-skills	Depends on your tool

See the host guides, including Claude Code, Cursor, Codex, and Gemini CLI, for complete setup.

Recommended Specialized Plugins

Choose a focused plugin for the domain you are working in. These packages are available for Claude Code and Codex; compatible bundles also have a standard Agent Plugins manifest. See the plugin guide for installation and host support.

Plugin	Skills	Best for
AAS Web App Builder	10	Frontend and full-stack developers shipping modern web apps.
AAS Product Design Studio	10	Product UI, brand, portfolio, accessibility, and richer visual work.
AAS Security Engineer	10	Authorized security testing, audit, and hardening.
AAS Secure App Builder	9	Developers who want security embedded while building features.
AAS Documents & Presentations	9	Office files, document conversion, decks, and slide workflows.
AAS Data Analytics	10	Product analytics, SQL, dashboards, and experiments.
AAS Agent & MCP Builder	10	Agentic apps, MCP tools, RAG systems, and evaluation loops.
AAS QA & Test Automation	10	Test suites, browser automation, and QA stabilization.
AAS DevOps & Cloud	10	Infrastructure, deployments, and operational workflows.
AAS Accessibility & Inclusive UX	8	WCAG audits, automated scans, screen-reader checks, and accessible QA.
AAS API Platform Builder	10	API design, OpenAPI contracts, auth, security, load tests, and observability.
AAS SaaS Launch & Revenue	10	SaaS MVPs, pricing, payments, analytics, lifecycle, referrals, and SEO.
AAS AI Product & Evaluation Ops	10	AI product metrics, evals, tracing, experiments, and model-quality loops.

Browse the plugin roadmap, live plugin catalog, or generated plugins/ tree for the full set.

Bundles & Workflows

Bundles suggest related skills; workflows describe the order to use them. They are guidance for selecting and running skills, not additional packages to install.

• Bundles group skills by role or goal, such as Web Wizard, Security Engineer, and OSS Maintainer.
• Workflows give ordered playbooks for planning, shipping, testing, and auditing; workflow metadata is available for integrations.
• If too many installed skills overload Antigravity, follow the selective activation guide. For other hosts, preview a smaller exact install or use the installer's --risk, --category, and --tags filters.

Browse 2,926+ Skills

Explore the complete library in the hosted catalog or CATALOG.md. The canonical playbooks live in skills/; skills_index.json provides machine-readable discovery. Use Getting Started and Usage for first steps, or the Workbench to inspect a saved Core stack and plan in your browser.

For narrower comparisons, see Claude Code skills, Cursor skills, and the library comparison.

Troubleshooting

• Core setup and trust boundaries
• Installation and everyday use
• Windows context and truncation recovery
• Linux/macOS overload and selective activation
• Plugin compatibility and installation
• Security and antivirus alerts

Stable Skills Manifest v1

Host integrations that load individual SKILL.md files can use skills_index.json, the v1 schema, and the compatibility mirror. This direct-host discovery manifest is separate from aas-stack.json and the AAS Core catalog. Read the discovery contract before integrating.

Contributing

• Add new skills under skills/<skill-name>/SKILL.md and follow CONTRIBUTING.md.
• Start from the skill template and run npm run validate before a PR.
• Keep source PRs free of generated registry artifacts. Skill content and risky guidance require manual logic and safety review alongside automated checks.

Community

• Discussions for questions, ideas, and examples.
• Issues for reproducible bugs and actionable improvements.
• Follow @AASkills_ on X for project updates and examples, or @sickn33 for releases.
• CODE_OF_CONDUCT.md for community expectations; SECURITY.md for security reports.

Credits & Sources

We stand on the shoulders of giants.

👉 View the Full Attribution Ledger

Source credits stay here for attribution and auditability. Repository contributor credit lives separately in Repo Contributors.

Key source families include:

• Official AI platform and tool repositories
• Security, web, infrastructure, data, design, and automation communities
• Independent skill authors and open-source maintainers

Official Sources

• superdesigndev/treg: Source for seven Treg client workflow skills: treg, jev-memory, lead-signals, make-ugc, rea-growth, recruit and web-access. Apache 2.0 with additional terms (LicenseRef-Treg), including hosted-service restrictions; complete custom notices retained in each bundle. AAS adaptations require explicit budgets, data-transfer and memory consent, and authorized business-contact/media use.

• fclairamb/solidping-plugin: MIT official source for the solidping skill - uptime checks across 40+ types, results, incidents, diagnosis and status pages through the hosted SolidPing MCP server, with every write confirmed by the person first. SolidPing itself is AGPL-3.0.

• Outreachgenie/outreachgenie-linkedin-mcp: MIT source for outreachgenie-list-audit, a read-only saved-list and template audit with local Python reports. Connected use requires an OutreachGenie workspace and compatible MCP host.

• Aident-AI/aident-skill: MIT official source for the aident-loadout skill - search actions across apps the user connected in Aident Loadout, read live schemas, check connections and cost before running, and require approval for side effects, through the hosted Aident MCP server.

• SergiuPogor/curlshot-mcp: MIT official source for the curlshot skill - web page screenshots, PDFs and scrolling videos, plus HTML/Markdown rendering, through the hosted CurlShot API or MCP server. The hosted service has separate terms.

• AltoRank/altorank: AGPL-3.0 official source for the altorank skill - SEO/AI-search readiness audits, Search Console reads, keyword research and draft creation into a person-reviewed queue through the hosted AltoRank MCP server.

• getchordlabs/chord: MIT official source for the chord-onchain-trading skill - DEX market data, best-route swap quotes and unsigned swap transactions on eight EVM chains through the Chord API; the skill never signs or sends. The hosted API and server have separate licensing.

• Krexa-xyz/skills: MIT-0 official source for the krexa skill - turn a trading idea, post or video into fixed rules, backtest and paper-trade them, and request a user-approved live trading agent through Krexa's hosted MCP server.

• tuantqse90/moltnode-mcp: MIT official source for the moltnode-chain-reader skill - keyless JSON-RPC reads on 31 blockchains through MoltNode by Chord, plus Chord swap quotes with an unsigned transaction and simulation. The hosted gateway and server have separate licensing.

• arcmira/mcp: Apache-2.0 plugin source for arcmira-find-quotes, YouTube and podcast quote research with timestamped sources. The hosted service and server have separate licensing.

• Pazificateur69/tokenleak: Official tokenleak source for the tokenleak skill - token-lean working rules that cut the context a coding agent re-sends on every call (big reads, noisy logs, re-reads, serial calls), with a published A/B benchmark (MIT).

• beatra-ai/ai-headshot-generator-skill: Official Beatra source for the ai-headshot-studio skill - paid, hosted work installed from a digest-pinned 0.1.7 archive byte-identical to commit a8818c3 with self-update disabled before first use (MIT-0).

• uxkin/agent: Official UXKIN source for the free uxkin-research skill — research real iOS app screens, user journeys and website design systems before designing UI (MIT).

• loootai/looot-skills: Official looot skills - search, price and run 2,500+ data API endpoints (work emails, company search, SERP, web pages) from one prepaid balance.

• CosmoBlk/email-marketing-bible: Official Email Marketing Bible source for the email-marketing-bible skill - data-backed email marketing for agents: automation flows, deliverability triage, copy de-slopping, AI email design, compliance and 19 industry playbooks, with ESP control via MCP behind explicit send-approval gates (MIT).

• lognorm/lognorm-mcp: MIT official source for the lognorm skill — work a site's SEO and AI-visibility (GEO) backlog through the hosted LogNorm MCP server: audits, fixes, content and AI-answer tracking.

• NygenAnalytics/scarf: Official Scarf source for the scarf-single-cell skill - out-of-core single-cell RNA-seq analysis with Scarf's Zarr DataStore on local disk or object storage, immutable provenance-tracked artifacts, audited QC, clustering, markers and comparisons (BSD-3-Clause).

• anup-a/agent-artifacts: Official byagent source for the byagent skill - publish agent-written Markdown or HTML as a shareable link with the byagent CLI, read readers' line comments back, edit, republish to the same link and resolve; pages are public unless --private and comment text is treated as untrusted data (MIT).

• prateeks367/voicemoat-skills: Official VoiceMoat source for eight Twitter/X and LinkedIn skills (write-in-my-voice, turn-this-into-a-thread, same-idea-both-platforms, repurpose-into-a-post, define-my-content-pillars, why-did-this-post-flop, get-seen-in-replies, draft-my-comments). They draft in your own voice, write threads, cross-post, repurpose long content, pick content pillars, diagnose a post that underperformed, and write replies and comments worth reading; each works from pasted text alone, and an optional paid VoiceMoat connector adds voice scoring and preview-gated publishing (MIT).

• cloudishai/skills: Official Cloudish source for the cloudish skill - deploy a Dockerfile, source folder, or existing image as a running container at a live URL, built server-side, with confirmation before the first deploy and before spending credits; uploads the build context and spends prepaid credits (MIT).

• voygr-tech/placecall: Official PlaceCall source for the placecall skill - place real outbound phone calls to US businesses through the PlaceCall REST API (reservations, inquiries, quotes), follow the call and return the structured outcome and transcript; paid API, real calls ring real phones (MIT).

• gongdear/cline-pilot: Official source for the cline-pilot skill - proxy-drive Cline CLI coding tasks serially, monitor long runs against git/test evidence instead of self-report, relay decision points, and learn per-project-tag preferences in git-ignored private state (MIT).

• bosmdavid-gif/dropthehassle-skill: Official DropTheHassle source for the dropthehassle-publish skill - check that a folder is a finished static build, publish it to a free HTTPS link, hand the human the claim link and verify it is live; the agent never pays (MIT).

• busabase/skills: MIT source for the busabase skill — authorized MCP workspace operations, permission-aware ChangeRequests, and canonical-versus-pending readback.

• jcaiagent7143-ui/linkdigest-mcp: Official LinkDigest source for the linkdigest-social-link-reader skill - read one public Xiaohongshu, Douyin, TikTok, YouTube, X or WeChat article link into text (transcript, image text, key points with checked quotes, coverage receipt) through the paid hosted LinkDigest API or MCP server with the user's own key (MIT).

• metalbear-co/skills: Official mirrord skills source for the mirrord skill - run a local process inside a live Kubernetes pod's network, env and traffic, with confirmation before traffic-stealing or cluster-modifying steps (MIT).

• beatra-ai/viral-video-remake-skill: Official Beatra source for the viral-video-teardown-remake skill - paid, hosted work installed from a digest-pinned 0.3.1 archive byte-identical to commit 46f7875 with self-update disabled before first use (MIT-0).

• beatra-ai/photo-to-anime-skill: Official Beatra source for the ai-photo-restyler skill - paid, hosted work installed from a digest-pinned 0.1.4 archive byte-identical to commit 87bc4c4 with self-update disabled before first use (MIT-0).

• beatra-ai/ai-voice-cloning-skill: Official Beatra source for the voice-cloning-studio skill - paid, hosted work installed from a digest-pinned 0.2.1 archive byte-identical to commit 64923d9 with self-update disabled before first use (MIT-0).

• beatra-ai/multilingual-voiceover-skill: Official Beatra source for the ai-multilingual-dubbing skill - paid, hosted work installed from a digest-pinned 0.1.9 archive byte-identical to commit 030ec84 with self-update disabled before first use (MIT-0).

• beatra-ai/ai-voiceover-generator-skill: Official Beatra source for the voiceover-narration-studio skill - paid, hosted work installed from a digest-pinned 0.1.9 archive byte-identical to commit 0c44adf with self-update disabled before first use (MIT-0).

• beatra-ai/ai-podcast-voiceover-skill: Official Beatra source for the ai-podcast-voiceover skill - paid, hosted work installed from a digest-pinned 0.1.7 archive byte-identical to commit ddca11e with self-update disabled before first use (MIT-0).

• beatra-ai/ai-image-generator-skill: Official Beatra source for the ai-image-generation-studio skill - paid, hosted work installed from a digest-pinned 0.1.4 archive byte-identical to commit 13c7b9b with self-update disabled before first use (MIT-0).

• beatra-ai/ecommerce-product-images-skill: Official Beatra source for the ecommerce-listing-image-set skill - paid, hosted work installed from a digest-pinned 0.2.0 archive byte-identical to commit ef9056d with self-update disabled before first use (MIT-0).

• beatra-ai/ai-poster-maker-skill: Official Beatra source for the poster-design-studio skill - paid, hosted work installed from a digest-pinned 0.1.3 archive byte-identical to commit 7a6337f with self-update disabled before first use (MIT-0).

• beatra-ai/ai-music-generator-skill: Official Beatra source for the music-generation-studio skill - paid, hosted work installed from a digest-pinned 0.1.8 archive byte-identical to commit fee8fbf with self-update disabled before first use (MIT-0).

• beatra-ai/ai-media-generator-skill: Official Beatra source for the beatra skill - paid, hosted work installed from a digest-pinned 2.8.8 archive byte-identical to commit 69afbfe with self-update disabled before first use (MIT-0).

• beatra-ai/ai-product-photography-skill: Official Beatra source for the product-photo-studio skill - paid, hosted work installed from a digest-pinned 0.2.0 archive byte-identical to commit 1490364 with self-update disabled before first use (MIT-0).

• beatra-ai/ai-logo-maker-skill: Official Beatra source for the ai-logo-maker skill - paid, hosted work installed from a digest-pinned 0.1.7 archive byte-identical to commit 89bf762 with self-update disabled before first use (MIT-0).

• beatra-ai/lyrics-to-song-skill: Official Beatra source for the suno-lyrics-to-song skill - paid, hosted work installed from a digest-pinned 0.2.0 archive byte-identical to commit 2facaac with self-update disabled before first use (MIT-0).

• vanshyadav1408/Omentir: Official Omentir source for the omentir-linkedin-outreach skill - LinkedIn prospecting and outreach through the hosted Omentir MCP server (OAuth): find and score leads, draft messages, and check campaigns, research and drafts only by default, never signs into LinkedIn (MIT).

• Spicy-API/nsfw-ai-skill: Official SpicyAPI source for the nsfw-ai-spicyapi skill — adult (18+) image, image-to-video and image-edit generation through the SpicyAPI API with quote-before-spend and adults-only / consent rules (MIT).

• Atlas Cloud: Official source for the atlas-cloud-media skill — asynchronous image and video generation through the Atlas Cloud API.

• sandbaseai/cli: Official source for the sandbase-mcp skill - discover, inspect, and invoke 2,000+ AI models and APIs through a local MCP bridge with explicit schema and cost checks (Apache-2.0).

• vostride/agent-qa: Official Agent QA skills for authoring natural-language web and mobile tests, evidence-backed run triage, and scoped debug/fix workflows (FSL-1.1-ALv2, Apache-2.0 after two years).

• uizze/uizze: Official UIZZE source for the free anti-ui-slop skill—product-specific UI references, design contracts, required states, and a hard finish gate grounded in 800,000+ real web and iOS screens (MIT).

• anthropics/skills: Official Anthropic skills repository - Document manipulation (DOCX, PDF, PPTX, XLSX), Brand Guidelines, Internal Communications.

• anthropics/claude-cookbooks: Official notebooks and recipes for building with Claude.

• Orkas-AI/Orkas-VideoStudio: Official source for the video-router skill - choose and lock generation, deterministic composition, supplied-footage editing, or an automatic cross-modal production plan (MIT).

• remotion-dev/skills: Official Remotion skills - Video creation in React with 28 modular rules.

• vercel-labs/agent-skills: Vercel Labs official skills - React Best Practices, Web Design Guidelines.

• openai/skills: OpenAI Codex skills catalog - Agent skills, Skill Creator, Concise Planning.

• bekservice/Famulor-Skill: Official Famulor skill for tenant-safe operation of its hosted MCP server across assistants, communication history, campaigns, knowledge, automations, telephony, and workspace administration (MIT).

• supabase/agent-skills: Supabase official skills - Postgres Best Practices.

• microsoft/skills: Official Microsoft skills - Azure cloud services, Bot Framework, Cognitive Services, and enterprise development patterns across .NET, Python, TypeScript, Go, Rust, and Java.

• Simon-He95/markstream-vue: Official Markstream skill for installing streaming Markdown renderers across Vue, React, Svelte, Angular, Nuxt, Next.js, and Vue 2 applications (MIT).

• nowork-studio/NotFair: Official source for the seo-drift skill - dated SEO baselines and regression detection across rankings, indexation, metadata, directives, schema, and on-page elements (MIT).

• MiniMax-AI/cli: Official MiniMax CLI - text, image, video, speech, music, vision, and web-search workflows for MiniMax models and APIs.

• google-gemini/gemini-skills: Official Gemini skills - Gemini API, SDK and model interactions.

• apify/agent-skills: Official Apify skills - Web scraping, data extraction and automation.

• BuyWhere/buywhere-mcp: Official BuyWhere MCP server — search and compare products from Singapore, SEA, and US markets via Model Context Protocol.

• expo/skills: Official Expo skills - Expo project workflows and Expo Application Services guidance.

• huggingface/skills: Official Hugging Face skills - Models, Spaces, datasets, inference, and broader Hugging Face ecosystem workflows.

• longbridge/skills: Official Longbridge Securities skills - real-time quotes, charts, fundamentals, portfolio analysis, options, and market workflows for HK, US, A-share, and SG markets.

• makeev/alphai-claude-skills: Official AlphAI skills - stock briefs, market pulse, SEC Form 4 insider scans, two-ticker read-across, and news alerts through the hosted AlphAI MCP server (relevance-scored financial news, filing-verified earnings reads) (MIT).

• HasData/hasdata-cli: Official HasData CLI and API guidance for search, scraping, ecommerce, travel, jobs, local business, and structured web data workflows.

• runapi-ai/cli-skill: Official RunAPI CLI skill - generate AI images, videos, and music/audio from agent workflows, plus run other model API jobs.

• neondatabase/agent-skills: Official Neon skills - Serverless Postgres workflows and Neon platform guidance.

• prisma/skills: Official Prisma skills - Prisma Postgres setup, Prisma ORM, Prisma Compute deploys, and Client/CLI workflows.

• Skyvern-AI/skyvern: Official Skyvern browser automation skill — AI-powered browser control using Vision LLMs and computer vision for navigating sites, filling forms, and extracting structured data.

• scopeblind/scopeblind-gateway: Official Scopeblind MCP governance toolkit - Cedar policy authoring, shadow-to-enforce rollout, and signed-receipt verification guidance for agent tool calls.

• Forward-Future/loop-library: Official Loop Library skill - find, adapt, and design bounded AI-agent feedback loops with verification, stop rules, guardrails, and handoffs (MIT).

• agent-frontier/wgm: Official wgm protocol skill - governed build loops with triage, alignment, planning, deterministic backpressure, holdout-scenario judging, and handoff audits (MIT).

• Instant-Expert/skills: Official Instant Expert source for the ask-human-expert skill - ask real executives, operators and domain experts a question for a written or voice answer or a short call, with a free test mode and the user's approval before every paid order (MIT-0).

• browser-act/skills: Official BrowserAct skills - authenticated browser automation, JavaScript-rendered extraction, screenshots, parallel session isolation, verification handling, and human handoff (MIT).

• masakaai/jet-browser: Official Jet Browser skill and Apache-2.0 source - isolated WPE WebKit sessions with ordered JSONL, native input, semantic DOM inspection, screenshots, and reproducible offline runtime checks.

• browserbase/skills: Official Browserbase competitor-analysis skill - Browserbase Search API competitor discovery, research lanes, matrices, screenshots, and HTML reports (MIT).

• dair-ai/dair-academy-plugins: Official DAIR Academy plugin skills imported as standalone skills - image generation, adaptive learning, lesson artifacts, LLM council deliberation, survey papers, wiki building, and YouTube study notes (MIT).

• weaviate/agent-skills: Official Weaviate skills - vector database operations, semantic and hybrid search, data imports, RAG cookbooks, agentic RAG, multimodal PDF search, and async client patterns (BSD-3-Clause).

• pilot-protocol/pilotprotocol: Official Pilot Protocol overlay network - agent addressing, encrypted P2P messaging, NAT traversal, and an installable agent app store (AGPL-3.0).

• Xquik-dev/x-twitter-scraper: Official Xquik skill for X data workflows - tweet search, user lookup, follower export, media downloads, MCP, webhooks, OpenAPI, and SDK setup (MIT).

• Modellix/modellix-plugin: Official Modellix skill - authenticated, paid AI image and video generation through the Modellix CLI (MIT).

• replynodes/replynodes-agent-skills: Official ReplyNodes source for the url-to-markdown skill - fetch a public webpage as clean Markdown for reading, summarizing, quoting, or citing while preserving the source URL (MIT).

• beatra-ai/talking-avatar-video-skill: Official Beatra source for the talking-avatar-video skill - paid, hosted work installed from a digest-pinned 0.2.1 archive byte-identical to commit 251c968 with self-update disabled before first use (MIT-0).

• beatra-ai/beatra-skills: Official Beatra source for the beatra-ai-video-studio skill - paid, hosted AI video generation, editing, and extension, installed from a digest-pinned 1.2.5 archive byte-identical to commit 95d662f with self-update disabled before first use (MIT-0).

• cohesivity-org/cohesivity-skill: Official Cohesivity skill - agent provisioned backend infrastructure covering Postgres, hosting, auth, realtime, storage, cron, email, and AI model APIs over one HTTP API (MIT).

• ASI2030/Fact-Check-X: Source for the fact-check-x-complete workflow - claim-level AI answer comparison, citation-fidelity review, and public primary-source verification without bundled browser automation (Apache-2.0).

• happy520ai/unified-ai-system: Official source for the unified-ai-gateway skill - governed Codex MCP tools for provider-free prompt enhancement, credential-free gateway health, readiness, fake-provider chat, knowledge, workflow, and workforce evidence (Apache-2.0).

• testdriverai/testdriverai: Official TestDriver source for the testdriver-e2e-testing skill - author, run, and debug end-to-end tests that drive browsers and native apps in a real desktop sandbox with AI vision and natural-language element descriptions (Apache-2.0).

• HEOJUNFO/ai-film-crew: Official source for the film-crew skill - run a video idea past seven film-crew roles and get a shot list with one model-ready prompt per shot, plus prompt fixes and reroll diagnosis for Wan, LTX, Kling, Veo, Seedance, Hailuo, and Runway (MIT).

• hermes-labs-ai/lintlang: Official source for the lintlang-audit skill - deterministic, zero-LLM static auditing of agent instructions, tool definitions, and embedded Python prompts, reporting finding codes and locations without editing files or calling a model (Apache-2.0).

• target1m/traderspy-mcp: Official TraderSpy source for six crypto market research skills (traderspy-*) - market briefings, technical analysis, screening and backtests, AI signals, top-trader positioning, and position checks through the hosted, read-only TraderSpy MCP server (MIT).

• MohammadHijjawi97/since-cutoff: Official source for the since-cutoff skill - lists which APIs of a project's pinned Python dependencies changed after the model's training cutoff, from a static diff of the two releases with no model calls, shows where the code uses them, and writes short AGENTS.md or CLAUDE.md notes (MIT).

• qrxcodes/qrx-mcp: Official QRX skill - turn a text prompt and a link into an artistic, branded QR code through the hosted QRX MCP server, checked to scan before it is returned (MIT).

• opencanviz/opencanviz-skills-repo: Official openCanviz source for the opencanviz-json skill - write an openCanviz video project as JSON with a standard-library Python builder and validator (text entrances, 22 scene transitions, motion presets, LaTeX math, plots, tables, rings, 22 example projects), then import it at opencanviz.com/create, where a free account builds and plays it as a narrated, animated explainer and the MP4 download needs a plan or a one-time export purchase (MIT).

• a4a-network/a4a: Source for a4a.

• beatra-ai/ai-audiobook-generator-skill: Source for ai-audiobook-narration.

• beatra-ai/ai-image-realism-skill: Source for ai-image-realism.

• beatra-ai/ai-storyboard-generator-skill: Source for ai-storyboard-generator.

• beatra-ai/wechat-article-cover-skill: Source for wechat-cover-maker.

• beatra-ai/xiaohongshu-copywriter-skill: Source for zhongcao-note-copywriter.

• beatra-ai/xiaohongshu-cover-maker-skill: Source for zhongcao-cover-maker.

• ces107/agent-forge: Source for launch-check.

• commentkeyword/agent-toolkit: Source for comment-to-dm-cta.

• cooper-email/cooper-email: Source for cooper-email.

• coupler-io/skills: Source for coupler-marketing-analytics.

• datawebot/datawebot-mcp: Source for datawebot.

• doomsday-network/doom-pay: Source for doom-pay.

• doomsday-network/doomsday: Source for doomsday-escrow.

• f-o-x11/deed-page-skill: Source for deed-page.

• f-o-x11/perq-skill: Source for perq.

• faberlang/faber: Source for faber-language.

• kasovy/neverapply-mcp: Source for neverapply.

• lliu56/minicut-skills: Source for minicut-film-studio.

• mesmerlord/lurkapi-claude-plugin: Source for lurkapi-ad-research.

• mobbin/skills: Source for mobbin.

• pangolin-spg/openclaw-skills: Source for pangolinfo-amazon-data-research.

• pixeltable/pixeltable-skill: Source for pixeltable.

• quinnod345/ponder: Source for ponder.

• robinfaraj/postel-mcp: Source for postel-writing.

• sendblue-api/sendblue-cli: Source for sendblue/sendblue-cli.

• sfxmint/sfxmint-mcp: Source for sfxmint.

• soundza/soundza-mcp: Source for soundza.

• target1m/footval-mcp: Source for footval-follow-matches-and-tables, footval-scout-and-rank-players, footval-stats-and-transfer-news, footval-value-and-compare-players.

• uiverify/uiverify: Source for uiverify-triage-visual-changes.

• wassim-azi/agy-powerline: Source for agy-powerline.

• webly-ai/webly-plugin: Source for webly.

Community Contributors

• timini/agentic-verification: MIT source for the agentic-verify and agentic-test-audit skills - check a Python change by running every mutant of the changed lines and writing tests until they catch them, and audit a pytest suite for gaps, flaky and slow tests, and removal candidates checked on held-out mutants.

• UmarSiddiqui/obsess: MIT source for the obsess skill - a bounded perfectionist loop for one target that keeps the best evidence-backed attempt and stops on an attempt or time budget.

• openhook-dev/openhook-inbox: MIT source for the openhook skill: disposable callback inboxes, event inspection and cursor-based waiting for authorized integration tests.

• huyanxius/logo-to-stickers: MIT source for logo-to-stickers — brand marks become consistent paper-sticker characters with small visual stories, reference roles and fifteen real examples.

• moooai/takeout-coupon: MIT source for the takeout-coupon skill - Meituan, Ele.me/Taobao Shangou and JD Waimai hidden coupon feeds with verbatim taokouling codes and QR/H5 claim pages.

• moooai/trip-coupon: MIT source for the trip-coupon skill - Didi ride-hailing and hotel coupon feeds with verbatim codes and claim pages.

• moooai/movie-coupon: MIT source for the movie-coupon skill - movie-ticket discount feeds for Chinese cinema platforms with verbatim codes and claim links.

• moooai/parcel-coupon: MIT source for the parcel-coupon skill - courier and parcel-delivery coupon feeds with verbatim codes and claim pages.

• moooai/obtain-coupons-all-in-one: MIT source for the obtain-coupons-all-in-one skill - one aggregated coupon feed across the four categories above.

• yumaheymans/carejobs-mcp: MIT source for the healthcare-job-search skill - US healthcare job and posted-pay lookup for nursing, CNA, allied health, therapy, imaging, pharmacy and physician roles through CareJobs.Now's free read-only MCP server or public CC BY 4.0 JSON endpoints.

• AshenJyy/antigravity-browser-bridge: Source for the Browser Bridge guide for authorized Edge/Chrome automation using a separately installed local extension and daemon (Apache-2.0).

• Reak-Z/mcd-secret-menu-lab: MIT community recipe-planning workflow for McDonald's China using an authorized MCP connection and explicit account-action boundaries.

• Kadajett/cockney: MIT source for the cockney skill - terse Cockney-voiced replies and the smallest correct change (reuse, stdlib before dependencies, no speculative abstraction), switching to plain English for security and destructive-action warnings.

• estevecastells/awesome-copilot: MIT source for the invokely-statistics skill - find official statistical figures, series, comparisons and place rankings through the Invokely MCP server, and report each value with its period, unit and source citation. The originating contribution is open and unmerged upstream.

• morluto/rea: MIT source for the reverse-engineer-anything skill - evidence-led native, managed, JavaScript/Electron, packaged, and browser investigations with explicit provider limits.

• stas4000/what-could-break: MIT source for the what-could-break skill - find what a change breaks outside its own diff and prove the one fact that makes it safe by running real code. Includes material adapted from pstack by Lauren Tan (MIT).

• stas4000/tastegate: MIT source for the tastegate skill - pick a design direction, build on a craft floor, then render the page in headless Chromium at phone and desktop width and fail on overlap, sideways scroll, low contrast and AI-slop defaults. Direction rules derive from taste-skill (MIT) and the craft floor from impeccable (Apache-2.0).

• stefanautomateed/shipvela-codex: MIT source for shipvela-publish — owner-confirmed website publishing and exact deployment tracking through an already connected Shipvela account. The hosted service is proprietary and plan-limited.

• mdagnolops/1human-reels: MIT source for the agent-reels skill - find credited animation and video references on 1human and consult a private library shared by a human and their creative agent; registration, saves, likes, comments and publication are state-changing and require prior owner authorization.

• alexyc9381/shark-skill and alexyc9381/court-skill: MIT sources for the shark and court skills by Alex Chen (@nocodealex). Each is a panel of Claude sub-agents (investors, or a jury) that stress-tests an idea.

• ASCIT31/darkmoon-mcp-server: GPL-3.0 source for the darkmoon-pentest skill — authorized autonomous pentest runs, status polling and findings triage on a self-hosted Darkmoon Pro instance through its MCP server.

• alapha888/session-handoff-kit: MIT source for the session-handoff skill — structured handoff artifact for the next session, for use when context approaches capacity, before /clear or /compact, when switching tasks, or when ending a coding session.

• FlowLLM-AI/AxonX: Apache-2.0 source for axonx — quantitative research plugin development, task execution, and artifact/lineage inspection through CLI and MCP.

• supercorp-ai/supercov: MIT source for the supercov skill — line, branch and MC/DC coverage of a project's existing tests, used to write focused tests for the untested code.

• alapha888/agent-skills-en: MIT source for deep-research-framework, five-axis-code-review, git-commit-message, meeting-notes, and tech-writing-proofread — concise English workflows for research reports, code review, commit messages, meeting minutes, and technical proofreading.

• Natchannnn/repository-engineering-skills: MIT source for repo-foundation and repo-native-refactor — repository-native implementation, contract-aware migrations, evidence-based review, and bounded cleanup.

• tomelias10/mcp-drift-check: MIT source for the mcp-dependency-drift-audit skill — zero-execution review of mutable npm/npx package references in MCP configuration, with a manual static fallback and CI/SARIF guidance.

• wwewtech/chatexport-need-miner: Source for the chatexport-need-miner skill — community guidance and examples under MIT.

• socai-io/jev-social: Source for the jev-social skill — read-only Jev/socai social research routing (MIT).

• work0r-ai/agent-kit: Source for the workorai skill — agent kit workflows (MIT).

• awss1i/assay: MIT source for the assay skill. Deterministic local QA that opens a web page you built in a real browser, drives every control, and reports where the page contradicts itself, with no tests to write, no API key, and no network.

• shitianfang/jev-use: Source for the jev-use skill - routing an agent loop's no-text judgment steps to the Jev judgment model via the jev_judge / jev_gate MCP tools, batched per state, with a typed escalation contract that hands writing and low-confidence steps back to the LLM (MIT).

• wwewtech/anti-slop-design: Source for the anti-slop-design skill - anti-AI-slop UI/UX engineering with token archetypes and a seven-axis quality gate (MIT).

• wwewtech/dali-short-address-commissioner: Source for the dali-short-address-commissioner skill — community guidance and examples under MIT.

• romankurnovskii/etemaro: Source of the meteora-dlmm-pool-screening skill - read-only screening and ranking of Meteora DLMM pools from public APIs (MIT).

• wwewtech/eol-resistor-calculator: Source for the eol-resistor-calculator skill — community guidance and examples under MIT.

• tubeagentkit/youtube-transcript-skills: Source for the youtube-transcript-skills skill - YouTube transcript fetching, video/channel search, channel browsing, and playlist extraction via the getyoutubetranscript.com API, free tier with no card required (MIT).

• wwewtech/esl-price-sync: Source for the esl-price-sync skill — community guidance and examples under MIT.

• Pranav-Nexus/antigravity-skill-porter: MIT source for skill-porter, adapted for conservative local bundle previews and complete support-file copying.

• 70v-Yoyo/md2video-audio-skill: Apache-2.0 community source for md2video-audio, converting Markdown into narrated MP4 video with synchronized slides and narration.

• wwewtech/marlin-bed-leveling: Source for the marlin-bed-leveling skill — community guidance and examples under MIT.

• onkarbadve/agy-auto: MIT community source for agy-auto, providing guarded Antigravity CLI permission automation with scoped approvals.

• wwewtech/oneroster-csv-validator: Source for the oneroster-csv-validator skill — community guidance and examples under MIT.

• twoicewoo/awesome-copilot: Pinned MIT source for the break-ai-fix-loops skill - bounded AI repair loops with stable failure fingerprints, real-path proof, negative controls, and rollback verification (MIT).

• chenli-yy/entropy-box-public: Source for the entropy-box skill - grounded embodied-AI research and workflow assembly through Consult, Search, Lookup, Evidence, and the Panorama Graph, with public-service privacy and physical-system safety boundaries (CC BY 4.0).

• Junaid-PK/laravel-development-workflow: Source for the laravel-development-workflow skill - root-cause Laravel bug fixes and repository-native feature work with regression coverage and risk-based verification (MIT).

• Sketchjar/stipple-agent-skills: Source for seven Stipple-backed docu