SkillCorpus
Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.
What is SkillCorpus?
Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.
Overview of SkillCorpus
What it is
SkillCorpus is EverMind's open-source pipeline for turning scattered SKILL.md files from public repositories into reliable agent context. It aggregates sources, applies safety and license gates, evaluates quality, and matches task-specific skills before the agent answers.
Key features
- Aggregates SKILL.md files from public repositories into a curated, retrieval-ready corpus.
- Applies safety and license gates, quality evaluation, and deduplication.
- Provides retrieval models (bi-encoder and reranker) fine-tuned from Qwen3-Embedding-0.6B and Qwen3-Reranker-0.6B.
- Includes evaluation tooling and benchmarks (SkillsBench, GDPVal, QwenClawBench).
- Supports multiple agent hosts: OpenClaw, Hermes, Raven, WorkBuddy, DeepSeek Harness.
- Offers two retrieval modes: on-demand (skill_search tool) and auto (every turn).
- Public artifacts: 1,000-skill demo corpus, retrieval models, plugins, and the pipeline code.
Use cases
- Build your own skill layer by pointing the pipeline at your own source registry and applying curation, safety, and license gates.
- Change the behavior by modifying taxonomy, quality and dedup rules, retrieval recipe, export schema, evaluation suites, or host plugins.
- Keep control of deployment by self-hosting the released retrieval models and connecting your own agent host instead of using the hosted SkillHub API.
- Strengthen agents with task-specific procedural knowledge retrieved automatically or on demand.
Getting started
bash curl 'https://skillhub.evermind.ai/openapi/v1/skills?q=extract+tables+from+a+PDF' # search + read the bodies — stdlib only, no install, no API key python examples/skillhub_demo.py 'extract tables from a scanned PDF invoice' # also fetch the bundled scripts of the top hit python examples/skillhub_demo.py --install ./skills 'convert a PDF to images' # retrieve AND run the task — any OpenAI-compatible LLM export OPENAI_API_KEY=... python examples/skillhub_demo.py --ask 'extract tables from a scanned PDF invoice'
License and pricing
The core code is Apache-2.0 licensed (match/ and evaluate/ are MIT); each skill retains its upstream license. The project is open source (pricing type: open_source).
Based on the project's public README and repository metadata.