vellum-ai publishes 95 agent skills on the atlas: 74 SAFE, 13 CAUTION, 8 BLOCK, with a mean score of 87/100. Every listing below is audited on its own.
Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
Cite
Cite this page
ModelsAtlas. “vellum-ai: skills and MCP servers”. Retrieved 14 Oct 2026. https://modelsatlas.com/orgs/vellum-ai
- Listings
- 95
- Mean score
- 87 / 100
- Findings
- 615
- Stars
- 135K
0 MCP servers · 95 skills
mean of the audit scores
across all listings
on the listed repositories
✓SAFE 74!CAUTION 13✕BLOCK 8
Everything vellum-ai publishes here
Most stars first · stamps show the audited version
Showing the 60 most-starred of 95 listings. The rest have their own pages and are linked from the skills and MCP server hubs.
Questions
Are vellum-ai's skills safe to install?
Of 95 listings, 74 are SAFE, 13 CAUTION and 8 BLOCK, with a mean score of 87 out of 100. That is an average over separate audits: check each listing's own stamp before installing.
What does this page tell me about vellum-ai?
It collects every skill and MCP server on the atlas whose source lives under github.com/vellum-ai, with each one's verdict. It says nothing about who runs the organisation, and publisher identity is not verified here.
Can a publisher change its verdicts?
No. Each verdict comes from reading the source at a named commit. If a finding is wrong, report it with your reasoning on the listing's page and it is re-audited; the correction is public.
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- Are vellum-ai's skills safe to install?
- What does this page tell me about vellum-ai?
- Can a publisher change its verdicts?