AAS Core — Agentic Awesome Skills
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 2,474+ installable SKILL.md playbooks. 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.
Current release: V18.7.0. 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 2,474+ 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. Press play to watch it here on GitHub.
AAS-onboarding-Flashing-Lights.mp4
If GitHub's player stalls, watch the video on the AAS website.
Support the Project
We’re looking for sponsors to support Agentic Awesome Skills. If you or your company would like to support the project, become a sponsor.
You can also support AAS on Buy Me a Coffee.
Security tooling support: Snyk.
AI compute & model credits: Atlas Cloud (supporting media generation workflows via atlas-cloud-media).
This project is tested with BrowserStack.
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-cacheUse --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 18.7.0 --path .agents/skills \
--skills brainstorming,systematic-debugging --dry-runReview 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 |
| 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, andOSS 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--tagsfilters.
Browse 2,474+ 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.mdand followCONTRIBUTING.md. - Start from the skill template and run
npm run validatebefore 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.mdfor community expectations;SECURITY.mdfor 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
Official Sources
- Atlas Cloud: Official source for the
atlas-cloud-mediaskill — asynchronous image and video generation through the Atlas Cloud API. - sandbaseai/cli: Official source for the
sandbase-mcpskill - 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-slopskill—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-routerskill - 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-driftskill - 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.
- 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.
- 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).
- browser-act/skills: Official BrowserAct skills - authenticated browser automation, JavaScript-rendered extraction, screenshots, parallel session isolation, verification handling, and human handoff (MIT).
- browserbase/skills: Official Browserbase
competitor-analysisskill - 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).
- beatra-ai/beatra-skills: Official Beatra source for the
beatra-ai-video-studioskill - paid, hosted AI video generation, editing, and extension, installed from a digest-pinned 1.2.5 archive byte-identical to commit95d662fwith 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-completeworkflow - 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-gatewayskill - 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-testingskill - 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-crewskill - 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-auditskill - 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).
Community Contributors & Source Repositories
Community Contributors
-
tomelias10/mcp-drift-check: MIT source for the
mcp-dependency-drift-auditskill — 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-minerskill — community guidance and examples under MIT. -
socai-io/jev-social: Source for the
jev-socialskill — read-only Jev/socai social research routing (MIT). -
work0r-ai/agent-kit: Source for the
workoraiskill — agent kit workflows (MIT). -
shitianfang/jev-use: Source for the
jev-useskill - routing an agent loop's no-text judgment steps to the Jev judgment model via thejev_judge/jev_gateMCP 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-designskill - 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-commissionerskill — community guidance and examples under MIT. -
romankurnovskii/etemaro: Source of the
meteora-dlmm-pool-screeningskill - read-only screening and ranking of Meteora DLMM pools from public APIs (MIT). -
wwewtech/eol-resistor-calculator: Source for the
eol-resistor-calculatorskill — community guidance and examples under MIT. -
tubeagentkit/youtube-transcript-skills: Source for the
youtube-transcript-skillsskill - 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-syncskill — 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-levelingskill — 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-validatorskill — community guidance and examples under MIT. -
twoicewoo/awesome-copilot: Pinned MIT source for the
break-ai-fix-loopsskill - 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-boxskill - 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-workflowskill - 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 document trust skills covering document forensics, identity-pack gaps, grounded extraction, citation checks, AI-text triage, adverse-media review, and AU/NZ tender matching, with explicit hosted-data and human-review boundaries (Apache-2.0).
-
263311487-ux/falsify: Source for the
falsifyskill - a scientific reasoning protocol for explicit hypotheses, adversarial checks, evidence grading, and calibrated conclusions (MIT). -
Ghost011118/project-state-governor: Source for the
project-state-governorskill - evidence-backed canonical project state across sessions, branches, reviews, and research cycles (Apache-2.0). -
sandbaseai/sandbase-skills: Source for the
multi-source-searchskill - cross-validated research with explicit source diversity, confidence, conflicts, gaps, and an offline-checkable evidence ledger (Apache-2.0). -
sandbaseai/awesome-workbuddy: Source for the
skill-security-auditskill - read-only-by-default review of Agent Skills, MCP servers, connectors, and extensions across permissions, provenance, credentials, data flow, and irreversible actions (CC0-1.0). -
alexprivalov/boost-asio-skill: Source for the
boost-asio-proskill - version-aware async C++ networking with Boost.Asio and standalone Asio across coroutine, callback, and classicio_servicestyles (MIT). -
xiehuan123/dsh-deepread: Source for the
dsh-deepreadskill - evidence-first analysis of articles, books, PDFs, and document sets with claim tracing, knowledge maps, and Feynman checks (MIT). -
riffkit/skill: Official upstream source for the
riffkitskill - short-form video riffing and UGC ad generation in nine natively generated languages (MIT). -
5dive-ai/skills: Source for the
compile-knowledgeskill - durable, atomic, interlinked knowledge stores with explicit hygiene, provenance, expiry, and secret-handling boundaries (MIT). -
JanYork/using-lwc: Source for the
using-lwcskill - durable, source-grounded project memory with independently verified document and code graphs (Apache-2.0). -
saudademjj/luopan: Source for the
travel-plannerskill - Chinese-first travel itinerary planning with mandatory budget confirmation, source-traceable facts, workload-aware daily pacing, and rule self-checks (MIT). -
OJPalenzuela/agents-generator: Source for the
agents-generatorskill - project-specificAGENTS.mdand companion rule generation with package-manager detection, monorepo handling, dry-run/update modes, backups, and validated commands (MIT). -
agentbody/skills: Source for the
people-dataskill - LinkedIn and YouTube professional-profile and public business-contact research via the Agent Body MCP server (MIT). -
sudosubin/gh-attach: Source for the
gh-attachskill - GitHub CLI uploads and downloads ofuser-attachments(screenshots, PDFs, zips, videos), producing repo-scoped URLs for PRs, issues, and READMEs, with GitHub Enterprise Server support (MIT). -
Continuum-AI-Corp/OrcaReplay: Source for the
orca-replayskill - reading, replaying, and forking recorded coding-agent runs, so a question about what a past run did is answered from its trace rather than from memory (Apache-2.0). -
Continuum-AI-Corp/OrcaPromptVault: Source for the
system-prompt-lookupskill - a dated archive of shipped AI products' system prompts and tool schemas, each labelled captured or vendor-reported, so a claim about what an agent was instructed to do is answered from the artifact rather than from memory (AGPL-3.0). -
amElnagdy/review-skills: Source for the
debate-reviewandbabysit-prskills - two-model debate review of PRs/MRs with inline comments and automated babysitting of review rounds for GitHub, GitLab and Azure DevOps (MIT, docs-only — runtime not bundled). -
yylo-dev/yylo-skills: Source for 7 YYLO skills (
ledger-tasks-yylo,plan-ledger-tasks-yylo,ralph-loop-yylo,understand-project-yylo,wiki-yylo,workflow-yylo,artifact-yylo) - repo-resident Kanban/task ledger, PDR planning, validated single-task execution loop, and wiki/workflow/artifact records with fail-closed Ledger boundaries (MIT, docs-only —scripts/kanban.shruntime not bundled). -
addyosmani/agent-skills: Source for
constraint-driven-development,interview-me,using-agent-skills— only names not already in the catalog (22/25 overlap with existing entries) (MIT). -
ayghri/i-have-adhd: Source for the
i-have-adhdskill — ADHD-friendly output shaping (MIT). -
career-ops-hq/career-ops: Source for the
career-opsskill — multi-CLI job-search command center (MIT, docs-only — Node runtime not bundled). -
zubair-trabzada/geo-seo-claude: Source for 14 GEO/SEO skills (
geo-audit,geo-citability,geo-technical, …) — site audits and client reporting (MIT, docs-only;geo-updateself-installer excluded). -
BagelHole/DevOps-Security-Agent-Skills (compliance batch): Source for 19 governance/framework/continuity/auditing skills (MIT, docs-only).
-
BagelHole/DevOps-Security-Agent-Skills (security batch): Source for 35 secrets, scanning, network, operations, and AI-security skills (MIT, docs-only).
-
BagelHole/DevOps-Security-Agent-Skills (infrastructure batch): Source for 70 server, storage, database, networking, cloud, and local-AI infrastructure skills (MIT, docs-only).
-
elementalsouls/Claude-BugHunter: Source for 83 bug-bounty/red-team skills (79 offensive with
AUTHORIZED USE ONLY+ confirmation gates, 4 process skills) — recon, exploitation, and validation workflows across web, API, cloud, identity, and mobile attack surfaces (MIT, docs-only — helper scripts, commands, engine, and research assets not bundled). -
BagelHole/DevOps-Security-Agent-Skills (devops batch): Source for 39 CI/CD, orchestration, observability, release, and AI-ops skills (MIT, docs-only).
-
amElnagdy/delegate-skills: Source for 18 delegation skills (
delegate-setup+ 17 implementer relays for Claude/Codex/Cursor/OpenCode and 13 more) — multi-agent delegation and fleet orchestration with Node built-ins only, relay never commits (MIT, docs-only — runtime not bundled). -
zhaoxuya520/reverse-skill: Source for 43 security skills covering reverse engineering, binary analysis, offensive assessment orchestration, and threat-intelligence workflows, adapted with English metadata and upstream safety gates (MIT).
-
abhinaykrupa/cowork-to-code-bridge: Source for the
cowork-to-code-bridgeskill - consent-bound execution on the user's own machine with pinned provenance, narrow scopes, and explicit local-agent limitations (MIT). -
maleksaadi0109/hyprfedora: Source for the
fedora-hyprland-installerskill - GPU-aware Fedora Hyprland installation, configuration, verification, repair, and removal workflows (MIT). -
merc1305/findMate: Source for the
find-complementary-foundersskill - private-first own-owner assessment, approved expiring profiles, and evidence-backed human founder matching (MIT). -
provencher/codex-skills: Source for the
orchestrateskill - focused Codex multi-agent delegation with non-overlapping ownership, coordinator integration, and user-held approval gates (MIT). -
Phelan164/codex-howto: Source for the
maintain-codex-wikiskill - review-first engineering knowledge with provenance, explicit capture and promotion, and deterministic structural checks (MIT). -
kotobuki09/instructree: Source for the
instructreeskill - local instruction-scope mapping, metadata and link validation, recursive Copilot import audits, and SARIF reports (MIT). -
0xsarwagya/ontoly: Source for the
ontoly-software-graphskill - deterministic TypeScript software graphs, MCP-backed architecture review, request tracing, impact analysis, and dependency analysis (MIT). -
amElnagdy/guard-skills — Code Quality & Testing Guard Skills (by amElnagdy)
-
cloudflare/security-audit-skill — Cloudflare Web Security Audit Skill (by Cloudflare)
-
gooseworks-ai/goose-skills: Source for the
competitor-ad-intelligenceandad-campaign-analyzerskills - evidence-labeled public ad research plus uncertainty-aware campaign diagnostics and bounded budget tests (MIT). -
supernovae-st/nika-agents: Official upstream source for the
nikaskill and its deterministic, budget-aware AI workflow runner (MIT skill content; AGPL-3.0 engine). -
atdy/maoxuan-product-agent: Source for the
product-decision-agentskill - Chinese-first product judgment across prioritization, growth, operations, data, delivery, and cross-functional collaboration, with 36 tested scenarios (MIT). -
hafiz-actyte/idea-autopsy: Source for the
idea-autopsyskill - business-idea validation that hunts the one sentence that kills an idea before you build: kill-list check, five hard filters, free-AI one-prompt test, and live ad-market verification (MIT). -
cruisekkk/trading-ledger: Source for the
trading-ledgerskill - decision-quality trade journaling that captures entry thesis, plan, and emotion into the user's own Notion database (MIT). -
cruisekkk/time-ledger: Source for the
time-ledgerskill - natural-language time tracking parsed into the user's own Notion database with ask-instead-of-guessing reconciliation (MIT). -
mattpocock/skills: Source for 17 Matt Pocock workflow skills - codebase design, TDD, bug diagnosis, triage, PRDs, issues, prototyping, handoff, teaching, and skill-writing guidance (MIT).
-
emilkowalski/skills: Source for Emil Kowalski design engineering skills - UI polish, motion review, animation standards, component craft, and high-taste frontend guidance (MIT).
-
chaunsin/agent-skills: Source for the
pre-release-reviewanddrizzle-migration-conflictskills - deploy-readiness audits and Drizzle Kit migration-conflict workflows (Apache-2.0). -
addyosmani/agent-skills: Source for the
browser-testing-with-devtoolsskill - Chrome DevTools MCP browser verification, profiling, network inspection, and frontend debugging guidance (MIT). -
stareezy-1/frontend-architecture-skill: Source for the
frontend-lighthouseskill - portable Lighthouse CI Core Web Vitals gates, performance budgets, and GitHub Actions reporting (MIT). -
bin1874/before-you-build-skill: Source for the
before-you-buildskill - pre-coding product risk review across demand, alternatives, switching costs, channels, and validation steps (MIT). -
sparklingneuronics/sparkling-skills: Source for the
dispatchskill - multi-CLI delegation from Claude Code to Codex, Antigravity, and Gemini agents (MIT). -
takeaseatventure/sql-sentinel: Source for the
sql-sentinelskill - SQL warehouse cost and performance anti-pattern audits across BigQuery, Snowflake, Redshift, and Postgres (MIT). -
takeaseatventure/devops-skills: Source for the
cron-doctorskill - cron expression diagnosis, validation, trap detection, and zero-dependency schedule analysis tooling (MIT). -
drogers0/gh-image: Source for the
gh-imageskill - GitHub CLI image uploads that return canonicaluser-attachmentsembed URLs for PRs, issues, comments, and README screenshots (MIT). -
Genefold/arrowspace-skills: Source for the
arrowspaceskill - spectral vector search using graph Laplacian eigenstructure for structurally aware retrieval (Apache-2.0). -
yaojingang/yao-meta-skill: Source for the
yao-meta-skillskill - governed skill creation, refactoring, evaluation, packaging, review, and distribution workflows (MIT). -
connerkward/ckw-design-skill: Source for the
ckw-designskill - frontend design direction, design-system guidance, visual philosophy, spatial checks, usability review, and production UI polish workflows (MIT). -
connerkward/deterministic-design-skill: Source for the
deterministic-designskill - rendered UI layout and usability audits using deterministic measurement plus vision-judged review loops (MIT). -
connerkward/lookdev-auto-skill: Source for the
lookdev-autoskill - automated visual tuning loops where a vision or video model rates rendered variants and suggests improvements (MIT). -
connerkward/lookdev-studio-skill: Source for the
lookdevskill - human-in-the-loop visual and prose tuning through rendered variants, sliders, swatches, inline edits, and selection-driven refinement (MIT). -
connerkward/macos-screen-recorder-system-audio: Source for the
macos-screen-recorderskill - macOS ScreenCaptureKit recording with system audio, CLI workflows, permission handling, and export guidance (MIT). -
connerkward/mcp-apple-notes: Source for the
apple-notes-searchskill - semantic and keyword search, related-note discovery, bridge finding, entity threads, and cited synthesis across local Apple Notes via MCP (MIT). -
connerkward/screenstudio-alternative-skill: Source for the
screenstudio-altskill - open-source screen recording polish with auto-zoom, idle speed-up, cursor treatment, captions, and vertical export workflows (MIT). -
connerkward/web-media-getter-skill: Source for the
web-media-getterskill - unified search across free image, video, and GIF APIs with license-aware media selection guidance (MIT). -
xi-kari/crossframe-skill: Source for the CrossFrame Skill Suite - Chinese-canonical structural diagnosis, essay drafting, review, and companion workflows across relationships, organizations, institutions, public issues, and research notes (MIT).
-
qinghui316/ecl-harness-engineer: Source for the
ecl-harness-engineerskill - ECL Agent Harness infrastructure for AI coding workflows, repository guidance, change tracking, lint checks, CI gates, and handoff docs (MIT). -
baskduf/FableCodex: Source for the
codex-fable5skill - Codex-native Fable-inspired workflow discipline for evidence-first implementation, goal tracking, review findings, verification gates, and prompt adaptation (AGPL-3.0-or-later). -
Suraj1235/open-dynamic-workflows: Source for the
open-dynamic-workflowsskill - open-source dynamic multi-agent workflow engine that plans, orchestrates, and adversarially verifies parallel AI coding agents across OpenCode, Codex, Antigravity, and VS Code (MIT). -
multica-ai/andrej-karpathy-skills: Source for the
andrej-karpathyskill - English Karpathy-inspired LLM coding guidelines for simplicity, surgical changes, assumption surfacing, and verifiable success criteria (MIT). -
mskadu/opencode-agent-skills: Source for opencode behavior, permission, skill-suggestion, and smart Git automation skills.
-
adelaidasofia/ai-brain-starter: Source for the
ingest-youtubeskill - YouTube transcript ingestion into markdown vaults with yt-dlp metadata, VTT cleanup, and capture-seed stubs (MIT). -
JDDavenport/context-kit: Source reference for the
context-kitskill - local-first Personal Context Artifact setup, installer review, and private context hygiene for Claude Code and adjacent agent workflows. -
JunsW/feature-track: Source for the
feature-trackingskill - lightweight repository-native feature memory for current status, source-of-truth documents, decisions, risks, and cross-session handoff (MIT). -
JularDepick/user-thoughts.SKILL: Source for the
user-thoughtsskill - persistent project idea repository workflows for capturing decisions, tech stack notes, UI/UX rationale, and MDBASE-backed project memory (MIT). -
TheaDust/lore: Source for the
loreskill - Markdown-only, zero-dependency long-term project memory for AI coding agents, with monorepo scopes, two-section platform mirrors, and stdlib Python helpers (MIT). -
rainmanjam/poka-yoke: Source for the
poka-yokeskill - software mistake-proofing through control, warning, detection, and source-inspection guardrails (MIT). -
ZeroPointRepo/youtube-skills: Source for the
youtube-fullskill - TranscriptAPI-backed YouTube transcripts, search, channel browsing, playlists, and cloud-safe video research workflows (MIT). -
ZeroPointRepo/zillow-skills: Source for the
us-property-dataskill - U.S. property lookup, valuation, listing, tax, school, photo, and price-history guidance through the independent Zillapi API (MIT-0). -
Antheurus/anywrite: Source for the
anywriteskill - low-context CLI access to Anytype's local API for objects, properties, files, search, chat, and other workspace operations (MIT). -
Antheurus/sshepherd: Source for the
sshepherdskill - credential-isolated SSH operations, service control, logs, configuration changes, Postgres introspection, and declarative deploys through preconfigured aliases (MIT). -
ejentum/ejentum-mcp: Source for the
ejentum-reasoning-harnessskill - MCP cognitive harness modes for reasoning, code review, anti-deception checks, and memory-drift analysis (MIT). -
luoyuctl/agenttrace: Source for the
agenttrace-session-auditskill - local AI coding-agent session audits for cost spikes, tool failures, latency gaps, anomalies, health gates, and session diffs (MIT). -
ohad6k/ditto: Source for the
dittoskill - mines local coding-agent sessions into private, evidence-backed work, design, and writing profiles with dated source receipts (MIT). -
Necmttn/ax: Source for the
ax-extract-workflowskill - reconstruct workflow behind past coding-agent artifacts using local ax sessions, commits, skills, and tool traces (AGPL-3.0-only). -
Hanyuyuan6/remote-gpu-trainer: Source for the
remote-gpu-trainerskill - rented and remote GPU job orchestration, monitoring, teardown safety, spot resilience, and DL-debug workflows (MIT). -
mturac/recsys-pipeline-architect: Source for the
recsys-pipeline-architectskill - recommendation, ranking, and feed pipeline architecture using Source, Hydrator, Filter, Scorer, Selector, and SideEffect stages (MIT). -
aomi-labs/skills: Source for the
aomi-transactskill — natural-language driver for the Aomi CLI with account-abstraction-first execution and simulate-then-sign across 25+ DeFi apps (MIT). -
mycelos-ai/bumblebee-skill: Source for the
bumblebeeskill - multi-agent implementation workflows with repeatable planning, coding, review, and verification loops (MIT). -
demo112/yunqu-ai-skills: Source for WeChat official account, Xiaohongshu content strategy, and MCP tool development skills for Chinese-language platform workflows (MIT).
-
tellmefrankie/news-engine: Source for the
news-sentiment-engineskill - news ingestion, sentiment analysis, and market/news intelligence workflows (MIT). -
Kench001/antigravity-awesome-skills: Source for the
recursive-context-pruning-token-budgetingskill - context pruning, token budgeting, and long-session compression guidance (MIT). -
rich-elicitation: Source for the
rich-elicitationskill - asks clarifying questions in multiple rounds before starting ambiguous tasks. -
CodeShuX/mockhunter: Source for the
mock-hunterskill - Playwright-based live-page audits that classify visible values as real, mock, LLM-generated, hardcoded, broken, or unknown (MIT). -
commitshow/production-audit: Source for the
production-auditskill - shipped-app readiness auditing across deployment health, RLS, webhooks, secrets exposure, grants, Stripe idempotency, and mobile UX. -
MohamedAbdallah-14/unslop: Source for the
unslopskill - deterministic and LLM-assisted cleanup for AI-generated prose across CLI and agent tool workflows. -
monte-carlo-data/mc-agent-toolkit: Monte Carlo data observability skills — table health checks, change impact assessment, monitor creation, push ingestion, and SQL validation notebooks for dbt changes.
-
openclaw/skills: Source for the
daily-giftskill - relationship-aware creative gift generation with editorial judgment, concept selection, and multi-format rendering. -
umutbozdag/agent-skills-manager: Source for the
manage-skillsskill - cross-tool skill discovery, creation, editing, toggling, copying, moving, and deletion workflows across major agent coding tools. -
pumanitro/global-chat: Source for the Global Chat Agent Discovery skill - cross-protocol discovery of MCP servers and AI agents across multiple registries.
-
bitjaru/styleseed: StyleSeed Toss UI and UX skill collection - setup wizard, page and pattern generation, design-token management, accessibility review, UX audits, feedback states, and microcopy guidance for professional mobile-first UI.
-
yikuansun/PhotopeaAPI: Source for the
photopea-embedded-editorskill - Photopea embedding, host-page messaging, file I/O, scripting, and export workflows for web apps (MIT). -
milkomida77/guardian-agent-prompts: Source for the Multi-Agent Task Orchestrator skill - production-tested delegation patterns, anti-duplication, and quality gates for coordinated agent work.
-
Elkidogz/technical-change-skill: Source for the Technical Change Tracker skill - structured JSON change records, session handoff, and accessible HTML dashboards for coding continuity.
-
vipin-si/article-illustrations: Source for the
article-illustrationsskill - Grav-style hand-drawn article illustrations with whiteboard sketches, sparse annotations, and visual metaphor QA guidance (MIT). -
274326424/video-content-extractor: Source for the
video-content-extractorskill - FFmpeg and Tesseract OCR workflows for extracting timestamped screen text and structured Markdown reports from MP4 videos (MIT). -
metrox-eth/quit-sponsor: Source for the
quit-sponsorskill - evidence-based quit-smoking sponsorship for agents with persistent memory: 44-source cited protocols, sponsor decision tree, three-clause contract, wave protocol, slip attribution coaching, and a timestamped logbook (MIT). -
rmyndharis/antigravity-skills: For the massive contribution of 300+ Enterprise skills and the catalog generation logic.
-
amartelr/antigravity-workspace-manager: Workspace Manager CLI companion to dynamically auto-provision subsets of skills across local development environments.
-
obra/superpowers: The original "Superpowers" by Jesse Vincent.
-
guanyang/antigravity-skills: Core Antigravity extensions.
-
diet103/claude-code-infrastructure-showcase: Infrastructure and Backend/Frontend Guidelines.
-
ChrisWiles/claude-code-showcase: React UI patterns and Design Systems.
-
travisvn/awesome-claude-skills: Loki Mode and Playwright integration.
-
Dimillian/Skills: Curated Codex skills focused on Apple platforms, GitHub workflows, refactoring, and performance (MIT).
-
zebbern/claude-code-guide: Comprehensive Security suite & Guide (Source for ~60 new skills).
-
morsechimwai/lemmaly: Source for the
lemmaly,mathguard,invariant-guard, andcomplexity-cutsskills — algorithm-first discipline layer that forces AI coding agents to state Big-O, name the data structure, prove termination, and pick the right algorithm before writing the loop. Ships a deterministic CI scanner with 59 rules across 11 languages (Apache-2.0). -
alirezarezvani/claude-skills: Senior Engineering and PM toolkit.
-
karanb192/awesome-claude-skills: A massive list of verified skills for Claude Code.
-
VoltAgent/awesome-agent-skills: Curated collection of 1000+ official and community agent skills from leading development teams (MIT).
-
zircote/.claude: Archived Claude Code dotfiles/config repo with a Shopify development skill reference.
-
vibeforge1111/vibeship-spawner-skills: AI agents, integrations, maker tools, and other production-grade skill packs.
-
coreyhaines31/marketingskills: Marketing skills for CRO, copywriting, SEO, paid ads, and growth (23 skills, MIT).
-
iradoweck/antigravity-awesome-skills: Source for the GeminiIgnore FinOps skill -
.geminiignoresetup patterns for context-window efficiency and token cost reduction. -
heyneuron/flowhunt-skill: Source for the FlowHunt automation discovery audit skill - workflow intake, tool-by-tool audit, and opportunity prioritization for productivity automation.
-
Intelligent-Internet/II-Commons-Skills: Source for the II-Commons research skill - deterministic retrieval across arXiv, PubMed/PMC, and supported US policy corpora.
-
AgriciDaniel/claude-seo: SEO workflow collection covering technical SEO, hreflang, sitemap, geo, schema, and programmatic SEO patterns.
-
Leonxlnx/taste-skill: Frontend design taste skill collection covering premium UI generation, redesign audits, GSAP motion, Stitch design systems, minimalist and brutalist visual modes, and full-output enforcement.
-
2slides/slides-generation-2slides-skills: Source for the
2slides-ppt-generatorskill - AI presentation generation, PDF deck creation, narration, theme search, and slide export workflows using the 2slides API (MIT). -
ch040602/mdpr-skill: Source for the
mdpr-skillskill - Codex-assisted MDPR presentation review, semantic hints, visual checks, theme candidates, and deterministic renderer boundaries (MIT). -
whoisabhishekadhikari/lovable-cleanup: Source for the
lovable-cleanupskill — audits and strips Lovable scaffolding from Vite + React projects. -
sarveshtalele/linkedin-content-skill: Source for the
linkedin-content-generatorskill - LinkedIn post, carousel, newsletter, and content-calendar generation workflows with local feedback memory (MIT).
