SKILLHUB

Local skill registry and installer for AI agents

AI Agents & LLMOps — build, route, evaluate, and secure agents.

pip install cognis-skillhub
skillhub scan .            # → prioritized findings in seconds

Usage — step by step

1. Install (Python 3.9+):

   pip install skillhub

2. List skills in a registry (defaults to the current directory):

   skillhub list -r ./registry

3. Search and inspect. Rank skills by a query, then view a manifest with its dependencies:

   skillhub search "pdf extraction" -r ./registry
   skillhub info pdf-extract -r ./registry

4. Install a skill into a target directory, overwriting if needed:

   skillhub install pdf-extract -r ./registry -t ./agent/skills --force
   skillhub installed -t ./agent/skills

5. Automate / clean up. Emit JSON for tooling, and uninstall a skill in scripts:

   skillhub --format json installed -t ./agent/skills | jq '.[].name'
   skillhub remove pdf-extract -t ./agent/skills

Related MCP server: vibecheck

Contents

• Why skillhub? · Features · Quick start · Example · Architecture · AI stack · How it compares · Integrations · Install anywhere · Related · Contributing

Why skillhub?

ride the viral skills-registry pattern

skillhub is single-purpose, scriptable, and self-hostable: point it at a target, get prioritized results in the format your workflow already speaks (table · JSON · SARIF), gate CI on it, and let agents drive it over MCP.

Features

• ✅ Parse Version

• ✅ Parse Manifest

• ✅ Resolve Dependencies

• ✅ Runs on Linux/macOS/Windows · Docker · devcontainer

• ✅ Ports in Python, JavaScript, Go, and Rust (ports/)

Quick start

pip install cognis-skillhub
skillhub --version
skillhub scan .                       # scan current project
skillhub scan . --format json         # machine-readable
skillhub scan . --fail-on high        # CI gate (non-zero exit)

Example

$ skillhub scan .
  [HIGH    ] SKI-001  example finding             (./src/app.py)
  [MEDIUM  ] SKI-002  another signal              (./config.yaml)

  2 findings · risk score 5 · 38ms

Architecture

flowchart LR
  IN[agent / A2A traffic] --> P[skillhub<br/>map + analyze]
  P --> OUT[graph + flags]

Use it from any AI stack

skillhub is interoperable with every popular way of using AI:

• MCP server — skillhub mcp (Claude Desktop, Cursor, Cognis.Studio, uncensored-fleet)

• OpenAI-compatible / JSON — pipe skillhub scan . --format json into any agent or LLM

• LangChain · CrewAI · AutoGen · LlamaIndex — wrap the CLI/JSON as a tool in one line

• CI / scripts — exit codes + SARIF for non-AI pipelines

How it compares

Built in the spirit of OpenClaw ClawHub, re-framed the Cognis way. Missing a credit? Open a PR.

Integrations

Pipes into your stack: SARIF for code-scanning, JSON for anything, an MCP server (skillhub mcp) for AI agents, and a webhook forwarder for SIEM/Slack/Jira. See docs/INTEGRATIONS.md.

Install — every way, every platform

pip install "git+https://github.com/cognis-digital/skillhub.git"    # pip (works today)
pipx install "git+https://github.com/cognis-digital/skillhub.git"   # isolated CLI
uv tool install "git+https://github.com/cognis-digital/skillhub.git" # uv
pip install cognis-skillhub                                          # PyPI (when published)
docker run --rm ghcr.io/cognis-digital/skillhub:latest --help        # Docker
brew install cognis-digital/tap/skillhub                             # Homebrew tap
curl -fsSL https://raw.githubusercontent.com/cognis-digital/skillhub/main/install.sh | sh

Related Cognis tools

• agentsmith — Config-first scaffolding and orchestration for multi-agent workflows

• toolguard — Runtime allowlist and policy for agent tool-calls

• evalbench — Offline LLM / agent eval harness with regression gates

• ragkit — Batteries-included local RAG pipeline — ingest, index, serve

• memorybank — Portable long-term memory store for agents, exposed over MCP

• promptpack — Versioned prompt / template registry with A/B and rollbacks

Explore the suite → 🗂️ all 170+ tools · ⭐ awesome-cognis · 🔗 cognis-sources · 🤖 uncensored-fleet · 🧠 engram

Contributing

PRs, new rules, and demo scenarios are welcome under the collaboration-pull model — see CONTRIBUTING.md and SECURITY.md.

⭐ If skillhub saved you time, star it — it genuinely helps others find it.

Interoperability

{} composes with the 300+ tool Cognis suite — JSON in/out and a shared OpenAI-compatible /v1 backbone. See INTEROP.md for the suite map, composition patterns, and reference stacks.

License

Source-available under the Cognis Open Collaboration License (COCL) v1.0 — free for personal, internal-evaluation, research, and educational use; commercial / production use requires a license (licensing@cognis.digital). See LICENSE.