by sickn33
AAS Core preview is the local, agent-first control plane for discovering, recommending, validating, and planning exact skill stacks, backed by 1,965+ agentic skills. Includes CLI, local MCP, catalog, plugins, and Workbench.
# Add to your Claude Code skills
git clone https://github.com/sickn33/agentic-awesome-skillsGuides for using ai agents skills like agentic-awesome-skills.
Last scanned: 7/9/2026
{
"issues": [
{
"file": "plugins/agentic-awesome-skills/skills/2slides-ppt-generator/SKILL.md",
"line": 768,
"type": "secret-exfiltration",
"message": "Instruction appears to send credentials/secrets to an external endpoint",
"severity": "medium"
}
],
"status": "PASSED",
"scannedAt": "2026-07-09T07:46:09.429Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}agentic-awesome-skills is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by sickn33. AAS Core preview is the local, agent-first control plane for discovering, recommending, validating, and planning exact skill stacks, backed by 1,965+ agentic skills. Includes CLI, local MCP, catalog, plugins, and Workbench. It has 43,554 GitHub stars.
Yes. agentic-awesome-skills passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/sickn33/agentic-awesome-skills" and add it to your Claude Code skills directory (see the Installation section above).
agentic-awesome-skills is primarily written in Python. It is open-source under sickn33 on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh agentic-awesome-skills against similar tools.
No comments yet. Be the first to share your thoughts!
Local, deterministic skill-stack composition for coding agents—from an explicit project profile to a reviewable plan before any target change.
Current release: V15.0.0. This release includes AAS Core under the Agent-First Preview claim for local search, inspection, recommendation, manifest validation, planning, and diagnosis. Apply and recovery remain experimental and outside the supported preview path.
Codex or Claude inspects your project using its own capabilities; AAS does not scan it. The agent sends the local, read-only AAS MCP an explicit project profile. AAS Core evaluates that profile and your policy against a verified local catalog, returns an explainable recommendation, and lets the agent propose aas-stack.json. The aas CLI validates that desired state and creates an immutable per-target plan before any skill changes are made.
Read the AAS Core preview guide →
Project
-> inspected by Codex or Claude (not by AAS)
-> explicit, allowlisted project profile
-> AAS MCP (local stdio, read-only)
-> deterministic AAS Core + verified local catalog
-> recommendation with evidence, exclusions, coverage, and unknowns
-> agent proposes aas-stack.json
-> AAS CLI validate + immutable plan preview
-> human review (optionally in Workbench)
The 1,967+ 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.
The agent composes. You control. AAS keeps the stack reproducible.
AAS Core gives the repository one product model:
search_skills, get_skill, recommend_stack, inspect_stack, and diff_stack; it does not install skills, scan source files, call a remote model, or write to the project.aas-stack.json. The manifest pins catalog identity, targets, goals, policy, and exact skill IDs without storing repository source or model reasoning.aas stack validate checks the proposal, while aas stack plan produces an immutable, per-target plan without applying it.Read the AAS Core guide for the exact trust boundaries, current preview status, Codex/Claude setup model, and CLI lifecycle.
For Codex and Claude, start with the AAS Core guide: configure the local MCP through the explicit preview flow, ask the agent for a recommendation, 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:
# Default: ~/.agents/skills (Antigravity 2.0 global). Use --path for other locations.
npx agentic-awesome-skills
# 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.
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.
test -d ~/.agents/skills && echo "Skills installed in ~/.agents/skills"
Use @brainstorming to plan a SaaS MVP.