SkillCorpus

English · 简体中文

What SkillCorpus gives you

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.

You can use the live SkillHub without cloning this repository. Clone SkillCorpus when you want the open-source machinery behind that experience:

• Build your own skill layer — point the pipeline at your own source registry, apply the curation, safety, and license gates, and export a corpus for your agents.
• Change the behavior — modify the taxonomy, quality and dedup rules, retrieval recipe, export schema, evaluation suites, or host plugins.
• Keep control of deployment — self-host the released retrieval models and connect your own agent host instead of using the hosted SkillHub API.

The core code is Apache-2.0 licensed (match/ and evaluate/ are MIT); each skill retains its upstream license. The public 1,000-skill demo, three agent benchmarks, and live SkillHub show the result.

https://github.com/user-attachments/assets/4d9a3241-df13-4b20-9798-fb7920069995

🔥 Latest Updates

• 2026-09-17 · v0.4.0 Adds a shared skills library across all six hosts: they read one ~/.evermind-skillsearch/ directory and register their own, so a skill you have in one agent is available in the rest; skills retrieved from a catalog are kept instead of discarded at the end of the turn; and changes take effect on the next turn, with no restart. Raven and Hermes also gain skills_dirs / SKILLSEARCH_SKILLS_DIRS.
• 2026-09-02 Adds OpenClaw 2.0 support and smarter skill delivery: retrieve automatically on every query, or let the main agent call skill_search on demand.
• 2026-08-27 Supports multi-source retrieval across local skills, EverMind SkillHub, ClawHub, and skillhub.cn, with filtering, deduplication, and final 0–2 selection.
• 2026-08-26 Supports PathGuard placeholder resolution and host-aware paths for skill files and agent workspaces.
• 2026-08-25 Adds official SkillCorpus plugins for WorkBuddy, OpenClaw, Hermes, Raven, and DeepSeek Harness.

Stronger agents, one turn at a time

At answer time, the practical difference is a retrieval layer: SkillHub selects vetted procedural knowledge for the task and puts it into the agent's context.

Dimension

Without SkillCorpus

With SkillCorpus

Context

Model knowledge plus a manually maintained prompt.

Task-specific, license-audited SKILL.md retrieved automatically or on demand.

Execution

Generic workflows can miss exact steps, edge cases, or supporting scripts.

Procedures, references, and optional scripts arrive before execution.

Integration

Each host maintains its own collection of task instructions.

One curated skill layer serves OpenClaw, Hermes, Raven, WorkBuddy, DeepSeek Harness, and other hosts.

The result is the same agent with better task-specific procedures available at the moment it needs them — stronger execution without asking users to memorise skill names or wire up tool calls.

Results

Pass rate with no skills → with SkillCorpus, same harness, same backbone (paper, Table 1):

The gain is largest where the task needs procedural knowledge the model does not already have (SkillsBench), and smallest on open-ended economic tasks it can already do (GDPVal).

SkillHub integrations

SkillHub brings skill retrieval to the five agent platforms below. Choose a platform to open its plugin guide:

DeepSeek Harness

Hermes

OpenClaw
1.x / 2.0

Raven

WorkBuddy

Two modes, one setting. On demand — the default — gives the agent a skill_search tool and lets it decide: a long task pays for retrieval at the step that needs it and nothing on the turns that do not. mode: auto is the older behaviour: search every turn, before the model answers, with no tool call and no skill names to memorise. They are exclusive; running both would search twice for one turn.

OpenClaw ships as two packages, because 2.0 dropped the hook the 1.x plugin injects through: plugin-openclaw for releases up to 2026.7.x, plugin-openclaw2 for 2.0 (2026.8.1) and newer. The packaged Raven plugin installs and its on-demand mode works today; mode: auto there will claim the skills stage once Raven merges its upstream context_segments slot, and is inert until then. Raven's built-in retrieval keeps working either way.

Install SkillCorpus Plugins following https://github.com/EverMind-AI/SkillCorpus/blob/main/skillcorpus_plugin/INSTALL.agent.md

Paste that line to your agent and it installs itself. Per-host setup, the five settings you will actually touch, what each turn costs and what leaves your machine — skillcorpus_plugin/.

Public artifacts

This is the concrete inventory of what is public today.

Open source today: the code, the 1,000-skill demo corpus, and the retrieval models. The full 114,190-skill corpus is being prepared for release on HuggingFace. The hosted SkillHub service itself stays closed.

The 96,401-skill snapshot measured in the paper, organised by a 16-class taxonomy and three quality facets (utility / robustness / safety), with 1024-dim retrieval embeddings. Column contract: docs/corpus-schema.md.

Query the API directly

SkillHub serves the corpus in three tiers — discover (metadata), read (skill_md), download (zip with scripts/). Most skills are pure instructions, so the read tier is usually sufficient.

curl "https://skillhub.evermind.ai/openapi/v1/skills?q=extract+tables+from+a+PDF"

Take an id from the results, fetch its skill_md, and inject it into your agent's prompt. examples/skillhub_demo.py runs all three tiers:

# 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 (OpenAI, OpenRouter, local vLLM, …)
export OPENAI_API_KEY=...                                # OpenRouter / vLLM: also set
# export OPENAI_BASE_URL=https://openrouter.ai/api/v1   # OPENAI_BASE_URL + --model openai/gpt-4o-mini
python examples/skillhub_demo.py --ask "extract tables from a scanned PDF invoice"

task: extract tables from a scanned PDF invoice

[1/2] search  → 2 hit(s), metadata only
  1. ocr-and-documents   q=0.808  DOC-PROC  MIT
     Extract text from PDFs/scans (pymupdf, marker-pdf).
  2. document-workflows  q=0.86   DOC-PROC  MIT
     Build end-to-end document processing workflows and pipelines …

[2/2] detail  → fetching skill_md for 2 skill(s)
  ocr-and-documents: 4916 chars  u=8 r=7 s=9  files=4  flags=['no_steps']
  document-workflows: 31628 chars  u=9 r=9 s=9  files=7

→ built a prompt of 36,742 chars with the skill bodies injected

Endpoints, response envelope, status codes and rate limits: docs/integrations.md.

Self-host the models

To avoid depending on the hosted endpoint, run selection yourself. The corpus and both retrieval models are released: load the data, serve the two models, and run your own encode → top-k → rerank.

# the data — a 1,000-skill demo for now; the full 114,190-skill corpus follows
from datasets import load_dataset
skills = load_dataset("EverMind-AI/skillcorpus-demo-1k", split="train")   # 1,000 demo skills
# or read the file directly with pandas (no `datasets`):  pip install pandas
import pandas as pd; skills = pd.read_parquet("skills.parquet")

Attachments (scripts/, references/) ship as a sibling attachments.tar.zst.

# install the serving deps (torch, transformers, …), then point the two env vars at
# the released checkpoints (the script's defaults are training outputs absent from a
# fresh clone) and serve both models behind one endpoint  ->  /embed + /score
pip install -r skillcorpus/match/requirements.txt
EMBEDDING_MODEL= RERANKER_MODEL= \
  bash skillcorpus/match/scripts/run_server.sh

This endpoint speaks /embed + /score (skillcorpus/match/ → Serving) — it is not a drop-in for SkillHub's hosted-only /openapi/v1/skills API. So:

• examples/skillhub_demo.py and the section-C integrations talk only to the hosted SkillHub; a self-hosted setup runs its own selection directly over /embed + /score.
• It is also the embedding endpoint the producer's dedup uses — set embedding.provider: skillrouter_remote to build your own corpus with it.

To curate your own sources instead, see Build your own corpus.

How it works

The collection pipeline is the foundation; the payoff is task-specific skill retrieval before the agent acts.

skillcorpus/
├── core/       data models · SQLite/faiss store · LLM & embedding clients
├── aggregate/  source registry + multi-repo clone
├── curate/     parse · safety · license · classify · quality · dedup + full-library passes
├── export/     corpus writer (parquet + attachments + dataset card)
├── match/      the 2 released models + training recipe                 ← isolated deps
├── evaluate/   skillsbench · qwenclawbench · gdpval benchmarks          ← isolated deps
└── cli.py      build · stats · export

cli build runs the whole curation chain (ingest → quality_pass → dedup_pass → license_audit → export.corpus). LLM classification and quality scoring degrade gracefully to rules when no model endpoint is reachable, so the pipeline always runs end to end.

match/ and evaluate/ are standalone toolkits with their own requirements.txt (torch / transformers, per benchmark); they are not pulled in by pip install of the producer.

• Retrieval — skillcorpus/match/ is the two released models: a bi-encoder fine-tuned from Qwen3-Embedding-0.6B for candidate recall, and a reranker fine-tuned from Qwen3-Reranker-0.6B that scores the top candidates. SkillHub serves both; to run them yourself see Serving (serve.py + run_server.sh). The directory also holds the training recipe (synthetic queries → InfoNCE → listwise CE) and eval_compare.py for the retrieval metrics (nDCG / MRR / Hit / Recall).
• Benchmarks — skillcorpus/evaluate/: skillsbench, qwenclawbench, gdpval — each self-contained with its own README and dependencies.

Build your own corpus

Only needed if you want to curate your own sources. Requires an LLM endpoint for classification / quality scoring and an embedding endpoint for dedup — see docs/running.md.

git clone https://github.com/EverMind-AI/SkillCorpus.git skillcorpus && cd skillcorpus
python3 -m venv .venv && source .venv/bin/activate
python -m pip install --upgrade pip && pip install -e .

python -m skillcorpus.cli build     # 4 demo sources -> curate -> export
python -m skillcorpus.cli stats     # counts by source / category / license
python -m skillcorpus.cli export --out ./corpus

Only skills from GREEN-licensed sources are exported (the demo trusts the whitelist in audit/license_safe_sources.json wholesale; production gates per source-repo SPDX). The per-row license is each skill's declared value, so a demo corpus can still carry non-GREEN license strings. Use --sources-config your.yaml for your own registry, or --source for one source.

pip install -e ".[dev]"
python -m pytest skillcorpus/tests -p no:cacheprovider --import-mode=importlib

Roadmap

• [x] Curation pipeline: 16-class taxonomy, 3-facet quality, per-source license audit
• [x] Fine-tuned retrieval stack + three-benchmark evaluation
• [x] Public SkillHub endpoint
• [x] Retrieval models (bi-encoder + reranker) and a 1k demo corpus on HuggingFace
• [ ] Full 114,190-skill corpus on HuggingFace — coming soon
• [x] Deployment script for the two retrieval models (self-hosting match/)
• [x] Plugins for WorkBuddy · Hermes · OpenClaw · DeepSeek Harness (+ HTTP adapter for any other host)
• [ ] Raven plugin — packaged, waiting on the upstream context_segments slot

EverMind Ecosystem

EverMind connects memory research, production-ready products, and practical integrations into one open-source ecosystem.

Products

EverOS

A local-first, Markdown-native long-term memory runtime for agents and users.

Raven

A memory-first, self-improving agent harness with proactivity, context control, and skill evolution.

EverMe (CLI)

A CLI and agent plugin suite for cross-device, cross-agent personal memory.

Research & Evaluation

SkillCorpus

Curated, retrieval-ready agent skill corpora with retrieval and evaluation tooling.

EverAlgo

Stateless extraction, ranking, parsing, and memory operators that power EverOS.

HyperMem

Hypergraph-based hierarchical memory for coarse-to-fine long-term conversation retrieval.

MSA

Memory Sparse Attention for scalable latent memory and 100M-token contexts.

EverMemBench

Evaluation of factual recall, applied reasoning, and personalized generalization in memory systems.

EvoAgentBench

Longitudinal evaluation of agent self-evolution, transfer efficiency, error avoidance, and skill use.

Integrations

OpenClaw

OpenClaw plugin for automatic recall, capture, and session-memory lifecycle management.

Hermes Agent

Hermes plugin for persistent memory across Hermes sessions.

DeepSeek Harness

DSH plugin for memory-aware DeepSeek Harness agents.

Dify

Self-hosted and cloud tools for explicit memory search and storage in workflows and agents.

Together, these projects form EverMind's research-to-runtime stack: methods and benchmarks become reusable memory infrastructure, products, and agent integrations.

Citation

@article{wang2026skillcorpus,
  title         = {SkillCorpus: Consolidating and Evaluating the Open Skill Ecosystem for Real-World LLM Agents},
  author        = {Wang, Yanze and Yao, Pengfei and Sun, Tianyi and Hu, Chuanrui and Xiao, Yan and Luo, Xiaotian and Han, Yunyun and Chen, Yifan and Sun, Jun and Deng, Yafeng},
  year          = {2026},
  eprint        = {2607.15557},
  archivePrefix = {arXiv},
  url           = {https://arxiv.org/abs/2607.15557}
}

License

• Code — Apache-2.0 (the match/ and evaluate/ toolkits are each MIT — see their own LICENSE).
• Corpus — every skill keeps its original upstream license; only GREEN (MIT / Apache-2.0 / BSD / ISC / …) skills are included, none relicensed. Each row carries source, source_url, and license, so downstream use must follow the per-skill terms.

Full GREEN/RED/YELLOW policy, license data flow, and opt-out: docs/licence-and-governance.md.