Back to directory

SkillPack

An open-source way to package AI skills into runnable local agents that a team can deploy in their own environment and use from Slack and Telegram.

SkillPack

SkillPack packages AI skills into runnable local agents that a team can deploy in its own environment and reach from tools such as Slack and Telegram, keeping sensitive data off any third-party service. A packaged skillpack runs with a start script that launches a local web server, where an LLM API key (OpenAI or Claude) is entered to use it.

A CLI creates a new skillpack interactively, setting a name and description, adding skills from GitHub repositories, URLs, or local paths, and writing prompts that tell the agent how to orchestrate those skills; it can also build a skillpack from an existing JSON configuration, whether local or remote. Finished packs are zipped for distribution, either with their skills included or referencing skills that will be installed separately.

It installs and runs through npx (@cremini/skillpack).

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.