k3-agentic-skills

A collection of curated AI agent skills for coding assistants, paired with a local semantic search engine over those skills powered by the Gemma embedding model, with no API keys or cloud dependency.

Visit website github.com

k3-agentic-skills packages dozens of curated skill files that document agent frameworks and workflows, such as Google's ADK, Gemini embeddings, and VPS-management patterns, for use in IDEs and agents that support skill-style instructions, including Antigravity, Cursor, Windsurf and Claude Code.

A companion local semantic search tool, mrl-indexer, builds a vector index over the skills and documentation using the EmbeddingGemma-300M model so an agent can find the right skill by natural-language query, entirely on the user's own machine. A separate guide covers running the Gemma 4 26B model locally for free inference.

More in Agent skills

See all 581

Provenance gate
github.com
A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.
- Agent skills
- AI evals
Expected Harm Calculus (EHC-4): Asimov's Four Laws for Autonomous AI Agents
github.com
A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.
- Agent skills
Vitruvius
github.com
An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.
- Agent skills
- AI evals

More in Agent skills

Provenance gate

Expected Harm Calculus (EHC-4): Asimov's Four Laws for Autonomous AI Agents

Vitruvius

Cookies