sickn33/agentic-awesome-skills

★ 48,854⑂ 7,090

2,877+ reusable AI agent skills for Claude Code, Codex, Cursor and Gemini CLI. AAS Core adds local catalog discovery, agent-owned selection and plan preview. CLI, MCP and plugins.

About sickn33/agentic-awesome-skills

sickn33/agentic-awesome-skills is an open-source project on GitHub, mainly written in Python. 2,877+ reusable AI agent skills for Claude Code, Codex, Cursor and Gemini CLI. AAS Core adds local catalog discovery, agent-owned selection and plan preview. It currently holds 48,854 stars and 7,090 forks with 11 open issues, and was last pushed on 2026-10-30 (repository created 2026-01-14).

Project Overview

AI Homed tracks it on the AI Agent Skills board and on the AI AI Agent Skills list.

GitHub Repository Details

Repository sickn33/agentic-awesome-skills · default branch main · size 421902 KB · watchers 303 · source: GitHub REST API and repository README

README

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 2,877+ 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: V20.2.0. 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.

GitHub stars Follow @AASkills_ on X License: MIT Claude Code Cursor Codex CLI Autohand Code Gemini CLI Latest Release Direct skill distribution Kiro Copilot OpenCode Antigravity

Table of Contents

Watch the Introduction

A 40-second introduction to Agentic Awesome Skills. Press play to watch it here on GitHub.

https://github.com/user-attachments/assets/02aa20ca-c3bb-4984-807e-7b06ef77e785

If GitHub's player stalls, watch the video on the AAS website.

Support the Project

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

https://github.com/sickn33/agentic-awesome-skills/blob/HEAD/Vercel OSS Program

| 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.

https://github.com/sickn33/agentic-awesome-skills/blob/HEAD/Support Agentic Awesome Skills 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.

Powered by Atlas Cloud

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 --package=agentic-awesome-skills@20.2.0 -- 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 --package=agentic-awesome-skills@20.2.0 -- \
  agentic-awesome-skills --release 20.2.0 --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 | | Antigravity IDE | npx agentic-awesome-skills --antigravity --skills --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.

Browse 2,877+ 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

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

Community

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 Sources

Official Sources

  • 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](https://github.com

GitHub Stars & Activity

48,854Stars
7,090Forks
11Open issues
PythonLanguage

GitHub Popularity

GitHub stars48,854
Forks7,090
Open issues11
Primary languagePython
LicenseMIT
Stars gained today0
Created2026-01-14
Last pushed2026-10-30

Trending History

Trending statusnot on today's boards

Related AI Projects

1

NousResearch / hermes-agent

Python★ 254,906⑂ 0
→
2

anthropics / skills

Python★ 181,961⑂ 0
→
3

langgenius / dify

Python★ 158,798⑂ 0
→
4

open-webui / open-webui

Python★ 156,073⑂ 0
→
5

langchain-ai / langchain

Python★ 148,033⑂ 0
→
6

Graphify-Labs / graphify

Python★ 128,304⑂ 0
→
7

browser-use / browser-use

Python★ 118,398⑂ 0
→
8

Panniantong / Agent-Reach

Python★ 99,006⑂ 0
→

More AI Rankings