AAS Core — Agentic Awesome Skills

> Local, agent-owned skill stacks for coding agents—from complete catalog access to a reproducible, reviewable plan.

Current release: V15.7.1. This release includes AAS Core for complete local catalog search, agent-owned selection, manifest validation, planning, and diagnosis. Apply and recovery remain experimental and outside the supported preview path.

Codex or Claude inspects your project and chooses exact skills from the complete local AAS catalog. AAS Core does not rank or recommend them: its read-only compose_stack tool validates the agent-owned selection in memory, and a client or the aas CLI can persist it as aas-stack.json and produce an immutable plan before any target change.

Read the AAS Core preview guide →

Project
  -> inspected by Codex or Claude (not by AAS)
  -> agent searches and reads the complete local catalog
  -> AAS MCP (local stdio, read-only)
  -> Codex or Claude chooses exact skill IDs
  -> compose_stack validates the selection in memory (read-only)
  -> client or AAS CLI persists aas-stack.json and optional evidence
  -> AAS CLI validate + immutable plan preview
  -> human review (optionally in Workbench)

The reusable SKILL.md playbooks, specialized plugins, bundles, workflows, and direct installers remain important. They are the content, curation, distribution, and compatibility layers around AAS Core—not competing primary products.

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


AAS Core: Agent-First Preview

> The agent composes. You control. AAS keeps the stack reproducible.

AAS Core gives the repository one product model:

• Let the agent choose. The local MCP preserves search_skills, get_skill, compose_stack, inspect_stack, and diff_stack, and adds read-only export_selection_evidence and inspect_selection_evidence; Core does not rank, recommend, exclude, or hide skills.
• Guide capability coverage. MCP session instructions require the agent to evaluate the full project surface—from architecture, domain behavior, data and integrations through testing, security, UX, deployment, and maintenance—then search each applicable capability, compare multiple candidates, cover it with a non-redundant skill or report a catalog gap, and avoid stopping at a minimal shortlist. Core records and validates the resulting selection, but it does not certify semantic completeness.
• Keep the chosen stack and evidence reviewable. A client or the CLI can persist aas-stack.json and the separate aas-selection-evidence.json sidecar in an artifact-dir; the manifest preserves exact agent-selected IDs, while evidence records factual process trace and the agent-declared capability ledger.
• Validate and preview through the CLI. aas stack validate checks the proposal, while aas stack plan produces an immutable, per-target plan without applying it.
• Review in Workbench. The hosted Workbench imports and reviews stack/plan JSON in browser memory; it does not access your filesystem or install anything.
• Retain every useful distribution path. Direct installs, plugins, bundles, workflows, and the full catalog remain available as payload and compatibility surfaces.

> [!IMPORTANT]
> Structural and identity validity does not certify semantic fit, compatibility, setup correctness, operational safety, or safety to apply.

Read the AAS Core guide for the exact trust boundaries, current preview status, Codex/Claude setup model, and CLI lifecycle.

Why This Repo

• Agent-first, locally controlled: Codex or Claude inspects the project and chooses from the complete local catalog without uploading your repository to AAS.
• Complete and inspectable: every catalog skill is searchable, readable, and available for agent selection; Core does not certify suitability, compatibility, or operational safety, and metadata is informational rather than an eligibility gate.
• Approval before writes: the durable artifacts are an approved stack and immutable plan, not an opaque one-shot install.
• Installable, not just inspirational: use the compatible legacy installer or plugin distributions when direct delivery is the right path.
• Built for major agent workflows: Claude Code, Cursor, Codex CLI, Autohand Code, Gemini CLI, Antigravity, Kiro, OpenCode, Copilot, and more.
• Broad coverage with real utility: 1,998+ skills across development, testing, security, infrastructure, product, and marketing.
• Inspect before installing: the hosted Skill Workbench reviews agent-produced stack manifests and immutable plans without browser-side installation.
• Focused delivery remains available: specialized plugins package proven sets for web, security, data, docs, DevOps, QA, OSS, or agent/MCP workflows.
• Useful whether you want breadth or curation: install the full catalog, choose a specialized plugin, start with bundles, or compare alternatives before installing.

Why not just search the skills directory?

Direct file search can find candidate prose, but it leaves the result in the conversation. AAS Core adds verified catalog identity, explicit target binding, durable desired state, optional selection evidence, deterministic validation, immutable planning, and dedicated review surfaces. Its value is not choosing better than the coding agent; it is turning the agent's choice into reproducible, inspectable state.

Table of Contents

• AAS Core: Agent-First Preview
• Why This Repo
• Installation
• Recommended Specialized Plugins
• Choose Your Tool
• Quick FAQ
• Bundles & Workflows
• Browse 1,998+ Skills
• Troubleshooting
• Stable Skills Manifest v1
• Support the Project
• Contributing
• Community
• Credits & Sources
• Repo Contributors
• Star History
• License

Installation

For Codex and Claude, start with the AAS Core guide: configure the local MCP, ask the agent to inspect the project and choose exact IDs from the full catalog, review the proposed aas-stack.json, then run CLI validation and planning. The MCP and validation are read-only. Planning writes only the requested plan artifact; it does not materialize skill payloads or AAS managed state in the target.

Use direct installation when your host does not yet have a native AAS Core adapter, when you already know the exact skill IDs, or when you deliberately prefer manual selection:

• Specialized plugins when the job has a clear domain.
• Full library install when you want every skill available in a local skills directory.
• Bundles and workflows when you want role-based recommendations or ordered execution playbooks.

Direct skill install

# Antigravity: preview an exact, agent-selected set before writing.
npx agentic-awesome-skills --antigravity --skills brainstorming,systematic-debugging --dry-run

# Antigravity CLI slash commands (agy): ~/.gemini/antigravity-cli/skills/<skill>/SKILL.md
npx agentic-awesome-skills --agy

The npm installer uses a shallow, release-pinned clone by default so first-run installs stay lighter than a full repository history checkout while matching the published npm package version. Use --tag main only when you intentionally want the current repository tip.

Antigravity watches ~/.agents/skills and may load enough installed instructions
to exhaust its context, slow startup, trigger truncation errors, or enter a crash
loop. For that target, the installer stops before cloning or writing unless you
provide --skills, a metadata filter, or the explicit --all override. The bare
npx agentic-awesome-skills command uses the same protected Antigravity target.

The recommended flow is to ask Codex or Claude with the read-only AAS Core MCP
configured to inspect the project, search the complete catalog, and choose exact
skill IDs. AAS MCP selects and validates IDs but does not install them; the agent
or user then previews the direct installation with the command above and repeats
it without --dry-run after review.

Other direct-install targets retain the legacy-compatible full-catalog behavior
when no selectors are supplied. The CLI prints the catalog's risk summary first:
a full install includes critical and authorized-use-only offensive
instructions. Installation copies files; it does not execute their commands,
but an agent may act on an installed skill later. Prefer an exact reviewed set:

npx agentic-awesome-skills audit --skills brainstorming,backend-dev-guidelines
npx agentic-awesome-skills --skills brainstorming,backend-dev-guidelines --dry-run

If you deliberately accept the context and crash-loop risk, the complete
Antigravity catalog remains available through explicit consent:

npx agentic-awesome-skills --antigravity --all

The audit reads the selected skill directories without executing them and
reports command, network, credential, filesystem, privileged, destructive,
symlink, and binary signals. It is a review aid, not a safety certificate. See
Security, trust, and antivirus alerts.

Focused single-skill install with GitHub CLI (preview)

GitHub CLI can preview and install one exact skill for Copilot and other supported hosts. Use an exact SKILL.md path in this large, mirrored repository so the selected source is unambiguous and discovery stays fast:

gh skill preview sickn33/agentic-awesome-skills skills/brainstorming/SKILL.md
gh skill install sickn33/agentic-awesome-skills skills/brainstorming/SKILL.md 
  --agent github-copilot --scope user --pin v14.2.0

gh skill support is currently a GitHub CLI preview and may change. Install a focused skill or plugin surface for the job; do not use --all unless you intentionally want every discovered canonical and mirrored skill.

Verify the install

test -d ~/.agents/skills && echo "Skills installed in ~/.agents/skills"

Run your first skill

Use @brainstorming to plan a SaaS MVP.

Prefer plugins for Claude Code or Codex?

• Use a specialized plugin when you want a focused marketplace-style distribution.
• Use the full-library plugin only when you want the widest plugin-safe catalog.
• Read Plugins for Claude Code and Codex for full-library plugin install vs specialized plugin install vs direct skills install.

Recommended Specialized Plugins

Do not install everything first if you already know the work. Start with the focused plugin for your job, then add more only when the task expands.

All specialized plugins are generated as Claude Code and Codex plugin bundles. For Antigravity, use the same SKILL.md content through the installer or supported skills paths.

Next-wave plugins cover marketing/SEO/growth, automation, observability/incident response, Python APIs, mobile apps, data engineering, privacy/compliance, and localization/international growth.

• Read the specialized plugin roadmap.
• Read the plugin guide for Claude Code and Codex.
• Compare the hosted specialized plugin landing page.
• Browse the generated plugin folders in <code class="ra0-md-code">plugins/</code>.

Choose Your Tool

Use the same repository, but install or invoke it in the way your host expects.

Use the Codex and Claude guides for the AAS Core MCP preview path. For other hosts—or when you deliberately want manual delivery—use the table's direct install targets, specialized plugins, and host-specific path guidance.

• Claude Code skills: install paths, starter skills, prompt examples, and plugin marketplace flow.
• Cursor skills: .cursor/skills/ setup, UI-heavy work, and pair-programming flows.
• Codex CLI skills: planning, implementation, debugging, and review skills for local coding loops.
• Gemini CLI skills: research, agent systems, integrations, and engineering workflows.
• AI agent skills guide: breadth vs curation, skill-library evaluation, and starting-point selection.

Quick FAQ

What is Agentic Awesome Skills?

Agentic Awesome Skills is the repository behind AAS Core, a local agent-first control plane for recording and validating agent-chosen skill stacks. The read-only AAS MCP gives Codex and Claude complete catalog search and skill inspection; the stack CLI and Workbench make the chosen state reproducible and reviewable. Direct installers, specialized plugins, bundles, and workflows remain supported distribution and discovery surfaces.

Is AAS Core fully certified?

The supported path covers complete local catalog search and inspection, agent-owned selection, stack composition and validation, immutable planning, and diagnosis. Transactional apply/recovery safety remains outside the supported claim; apply and recovery are explicitly experimental and disabled without additional opt-in flags.

How do I install it?

For AAS Core, follow the preview guide and use only a package release whose notes explicitly state that it includes Core. Release 14.6.0 predates Core; Core-capable releases begin with the 15.x line.

For direct skill distribution, use a tool-specific flag such as --codex,
--cursor, --gemini, or --claude to place skills in the directory your
assistant watches. The default target is Antigravity; it requires --skills, a
metadata filter, or explicit --all consent before cloning or writing because a
full watched catalog can exhaust context or trigger a crash loop.

For Autohand Code, use the installer with a custom path:

npx agentic-awesome-skills --path ~/.autohand/skills
npx agentic-awesome-skills --path .autohand/skills

What are AAS specialized plugins?

AAS specialized plugins are focused, domain-specific distributions of the skill library. They package the most relevant skills for web apps, security, data analytics, documents, DevOps, QA, OSS maintenance, and agent or MCP work so users can start with the right surface instead of activating the entire catalog.

Should I use the full library or a plugin?

Use the full library if you want the biggest catalog and direct filesystem control. Use a specialized plugin when you want a smaller, marketplace-style distribution for a specific workflow in Claude Code or Codex. For Antigravity, install the matching skills into the supported skills path. The complete explanation lives in Plugins for Claude Code and Codex.

How are plugins, bundles, and workflows different?

Plugins are installable packaging surfaces, bundles are curated skill recommendations, and workflows are ordered execution playbooks. Start with a plugin when the domain is clear, use bundles to compare adjacent skills, and use workflows when the important part is sequencing planning, coding, testing, auditing, or release work.

Where do I browse plugins, bundles, workflows, and the full catalog?

Start with Specialized Plugins when you want an installable domain pack. Use Bundles for role-based recommendations, Workflows for ordered execution playbooks, CATALOG.md for the full registry, and the hosted GitHub Pages catalog for searchable browsing.

Bundles & Workflows

Core, plugins, bundles, and workflows answer different questions. Codex or Claude selects skills; AAS Core records and validates that selection; plugins package a focused delivery surface; bundles are curated starting points; workflows are ordered playbooks for getting a result.

Use a specialized plugin first when your domain is clear. Use bundles to explore adjacent skills or assemble a custom install. Use workflows when the hard part is sequencing the work.

Start with bundles

Bundles are curated groups of recommended skills for a role or goal such as Web Wizard, Security Engineer, or OSS Maintainer.

• Bundles are recommendations, not separate installs.
• Install the closest specialized plugin when one matches your work, or install the repository once and use docs/users/bundles.md to pick a starting set.
• Good starter combinations:
• SaaS MVP: Essentials + Full-Stack Developer + QA & Testing
• Production hardening: Security Developer + DevOps & Cloud + Observability & Monitoring
• OSS shipping: Essentials + OSS Maintainer

Use workflows for outcome-driven execution

• Read docs/users/workflows.md for human-readable playbooks.
• Use data/workflows.json for machine-readable workflow metadata.
• Initial workflows include shipping a SaaS MVP, security audits, AI agent systems, QA/browser automation, and DDD-oriented design work.

Need fewer active skills at runtime?

If Antigravity starts hitting context limits with too many active skills, the activation guidance in docs/users/agent-overload-recovery.md can materialize only the bundles or skill ids you want in the live Antigravity directory.

If you use OpenCode or another .agents/skills host, prefer a reduced install up front instead of copying the full library into a context-sensitive runtime. The installer now supports --risk, --category, and --tags so you can keep the installed set narrow.

For a reproducible exact set, pin the package and catalog release and preview the full per-target plan before writing:

npx agentic-awesome-skills@14.3.0 --codex --release 14.3.0 --skills frontend-design,game-development/2d-games --dry-run

Remove --dry-run only after reviewing the install, update, and removal plan. Unknown or ambiguous skill identifiers fail closed, and metadata filters combine with --skills using AND.

The hosted Skill Workbench imports and reviews AAS Core stack manifests and immutable plans in browser memory. It does not access the filesystem, generate an approved plan, or install skills.

Browse 1,998+ Skills

Use the root repo as a landing page, then jump into the deeper surface that matches your intent.

What you get in this repository

• Skills library in <code class="ra0-md-code">skills/</code>
• AAS Core in <code class="ra0-md-code">tools/lib/aas-v1</code>, exposed through the aas CLI and local aas-mcp server
• Versioned stack and result schemas in <code class="ra0-md-code">schemas/aas-v1</code>
• Compatible legacy installer CLI powered by the npm package in <code class="ra0-md-code">package.json</code>
• Generated catalog and metadata in <code class="ra0-md-code">CATALOG.md</code>, skills_index.json, and <code class="ra0-md-code">data/</code>
• Hosted and local web app in <code class="ra0-md-code">apps/web-app</code> and on GitHub Pages
• Role-based bundles in docs/users/bundles.md
• Specialized plugin surfaces in docs/users/specialized-plugin-roadmap.md, docs/users/plugins.md, and <code class="ra0-md-code">plugins/</code>
• Execution workflows in docs/users/workflows.md
• User, contributor, and maintainer docs under <code class="ra0-md-code">docs/</code>
• Project visuals in <code class="ra0-md-code">assets/</code>, including the hero, social card, logo, and support banner

Best ways to explore

• Read the full catalog in <code class="ra0-md-code">CATALOG.md</code>.
• Browse the hosted catalog at https://sickn33.github.io/agentic-awesome-skills/.
• Start with Getting Started and Usage if you are new after installation.
• Use Bundles for role-based discovery and Workflows for step-by-step execution.
• Use Plugins for Claude Code and Codex when you care about marketplace-safe distribution, and the Specialized Plugin Roadmap when you want the best plugin candidates.

Compare alternatives

• Agentic Awesome Skills vs Awesome Claude Skills for breadth vs curated-list tradeoffs.
• Best Claude Code skills on GitHub for a high-intent shortlist.
• Best Cursor skills on GitHub for Cursor-compatible options and selection criteria.
• Vexilo · A field guide to Claude Code — different scope: a visual, searchable index of every Claude Code primitive (31 agents / 99 commands / 123 skills / 13 rules), organized around the 5-step workflow. Useful as a navigation layer over any skill library, not as a skill library itself. (companion repo)

Troubleshooting

Keep the root README short; use the dedicated docs for recovery and platform-specific guidance.

• If you are confused after installation, start with the Usage Guide.
• For Core setup, trust boundaries, stack manifests, and preview status, use the AAS Core guide.
• On native Windows, AAS_ADAPTER_WINDOWS_ACL_FAILED refers to the configuration path checked with PowerShell Get-Acl, not the cache and not icacls; do not approve until preview returns an approval digest.
• If you integrate agentic-awesome-skills into a host, read the discovery contract first: Stable Skills Manifest v1.
• For Windows truncation or context crash loops, use docs/users/windows-truncation-recovery.md.
• For Linux/macOS overload or selective activation, use docs/users/agent-overload-recovery.md.
• For OpenCode or other .agents/skills installs, prefer a reduced install such as npx agentic-awesome-skills --path .agents/skills --category development,backend --risk safe,none.
• For plugin install details, host compatibility, and marketplace-safe distribution, use docs/users/plugins.md.
• For contributor expectations and guardrails, use CONTRIBUTING.md, <code class="ra0-md-code">CODE_OF_CONDUCT.md</code>, and <code class="ra0-md-code">SECURITY.md</code>.

Stable Skills Manifest v1

This is the stable direct-host discovery manifest for integrations that load individual SKILL.md files. It is not aas-stack.json, the verified AAS Core catalog, or the Core composition contract. Core users should start with the AAS Core guide; custom host integrations can continue using the manifest below.

Host integrations should use:

• <code class="ra0-md-code">skills_index.json</code> as the canonical array-format manifest.
• <code class="ra0-md-code">schemas/skills-index.v1.schema.json</code> for the JSON shape.
• <code class="ra0-md-code">data/skills_index.json</code> as the compatibility mirror.

This keeps discovery stable (id, path, metadata) while ensuring hosts only load SKILL.md for requested @skill-id values.

Support the Project

Support is optional. The project stays free and open-source for everyone.


• Buy me a book on Buy Me a Coffee
• Security tooling support: Snyk
• Star the repository
• Open reproducible issues
• Contribute docs, fixes, and skills

Contributing

• Add new skills under skills//SKILL.md.
• Follow the contributor guide in <code class="ra0-md-code">CONTRIBUTING.md</code>.
• Use the template in <code class="ra0-md-code">docs/contributors/skill-template.md</code>.
• Validate with npm run validate before opening a PR.
• Keep community PRs source-only: do not commit generated registry artifacts like CATALOG.md, skills_index.json, or data/*.json.
• If your PR changes SKILL.md, expect the automated skill-review check on GitHub in addition to the usual validation and security scans.
• If your PR changes skills or risky guidance, manual logic review is still required even when the automated checks are green.

Community

• Discussions for questions, ideas, showcase posts, and community feedback.
• Issues for reproducible bugs and concrete, actionable improvement requests.
• Follow @AASkills_ on X for daily skills, practical workflows, and example prompts from the repo.
• Follow @sickn33 on X for project updates and releases.
• <code class="ra0-md-code">CODE_OF_CONDUCT.md</code> for community expectations and moderation standards.
• <code class="ra0-md-code">SECURITY.md</code> for security reporting.

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