StackMap
Subscribe
Explore / SkillNet
zjunlp

SkillNet

ZJU NLP's six-layer skill lifecycle platform: search a 500K+ index, author skills from traces/repos/docs/prompts, score quality on 5 dimensions, analyze skill graphs, orchestrate. SDK + CLI + MCP.

1,250 141 Python MITupdated 8 days ago
View on GitHubDispute this mapping →
Curator's take

Not an installer — a lifecycle platform (the maintainers put it well: calling it one is like calling GitHub a git-clone tool). Search over the 500K+ index is credential-free; authoring works from traces, repos, docs or prompts; `evaluate` scores 5 dimensions (safety, completeness, executability, maintainability, cost) with optional script execution; graph analysis spans relationships to scenario-level handoff detection. NOT for you if you only need 3-5 fixed skills (a flat directory suffices), need cross-agent format translation across 46 hosts (skillkit), need scriptable CI auditing with dedupe and security scans (asm), or want a small editorially-curated marketplace (n-skills) — the 500K index prioritizes coverage; quality ranking filters, it doesn't curate.

Mapped by ShipWithAI editors · links verified
README.md
SkillNet Logo

SkillNet

Open infrastructure for discovering, evaluating, composing, and orchestrating reusable AI agent skills.

SkillNet treats agent skills as software assets: searchable, installable, inspectable, evaluable, and composable.

PyPI version GitHub stars License: MIT Python 3.10+ arXiv Hugging Face Website

Website · Python SDK · Examples · Experiments · Paper


Why SkillNet?

Agents should not rebuild the same capability from scratch every time. SkillNet provides the infrastructure layer for skill reuse:

  • Discovery: search a public skill library by keyword or semantic intent.
  • Installation: download skill folders from GitHub into local agent workspaces.
  • Creation: generate structured skills from repositories, documents, prompts, or execution traces.
  • Evaluation: score skills for safety, completeness, executability, maintainability, and cost awareness.
  • Composition: infer relationships and scenario handoffs between local skills.
  • Orchestration: select scene-specific skills and generate a prompt for a downstream execution agent.

Search and public skill installation are credential-free. Create, evaluate, and analyze work with OpenAI-compatible endpoints. Orchestration runs through Claude Agent SDK and requires a compatible gateway configured with the same API_KEY, BASE_URL, and SKILLNET_MODEL variables.


Quick Start

Install the SDK and CLI:

pip install skillnet-ai

Search and install a skill:

from skillnet_ai import SkillNetClient

client = SkillNetClient()

results = client.search("pdf understanding", limit=5)
print(results[0].skill_name)
print(results[0].skill_url)

client.download(results[0].skill_url, target_dir="./my_skills")

CLI equivalent:

skillnet search "pdf understanding" --limit 5
skillnet download <skill_url> -d ./my_skills

No API key is required for search or public GitHub downloads.


News

  • [2026-07-11] SkillNet update. The library now indexes 500K+ GitHub skills with improved deduplication, expands scientific-research and data-analysis skill coverage, and adds local scenario graphs plus orchestration.
  • [2026-03-26] JiuwenClaw integration released. JiuwenClaw now includes SkillNet as a built-in skill marketplace. View guide
  • [2026-03-12] SkillNet MCP server released. MCP support is maintained by CycleChain.
  • [2026-03-04] Technical report released. Read the SkillNet report on arXiv.
  • [2026-02-23] OpenClaw integration released. SkillNet is available as a built-in skill for OpenClaw.

What You Can Build

Layer Capability What it enables
Skill library Search and download Reuse existing agent skills instead of rebuilding them
Skill authoring Create Turn traces, prompts, repositories, and documents into portable skill packages
Skill quality Evaluate

Continue your stack

What teams reach for next — and why each earns a place beside SkillNet. Ranked by curator confidence.