Publisher · GitHub organization

tanstack

github.com/tanstack ↗Last audit 8 Oct 2026

tanstack publishes 13 agent skills on the atlas: 12 SAFE, 0 CAUTION, 1 BLOCK, with a mean score of 87/100. Every listing below is audited on its own.
Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “tanstack: skills and MCP servers”. Retrieved 8 Oct 2026. https://modelsatlas.com/orgs/tanstack
Listings
13

0 MCP servers · 13 skills

Mean score
87 / 100

mean of the audit scores

Findings
2

across all listings

Stars
41K

on the listed repositories

SAFE 12CAUTION 0BLOCK 1

Everything tanstack publishes here

Most stars first · stamps show the audited version

Skill ★ 3.2K
✓SAFEB · 89 · 8 Oct 2026
Ag Ui ProtocolTanStack/ai
Skill ★ 3.2K
✓SAFEB · 89 · 8 Oct 2026
Ai CoreTanStack/ai
Skill ★ 3.2K
✓SAFEB · 89 · 8 Oct 2026
Chat ExperienceTanStack/ai
Skill ★ 3.2K
✓SAFEB · 89 · 8 Oct 2026
Skill ★ 3.2K
✓SAFEB · 89 · 8 Oct 2026
Debug LoggingTanStack/ai
Skill ★ 3.2K
✓SAFEB · 89 · 8 Oct 2026
Gap AnalysisTanStack/ai
Skill ★ 3.2K
✓SAFEB · 89 · 8 Oct 2026
Media GenerationTanStack/ai
Skill ★ 3.2K
✓SAFEB · 89 · 8 Oct 2026
MiddlewareTanStack/ai
Skill ★ 3.2K
✓SAFEB · 89 · 8 Oct 2026
Skill ★ 3.2K
✓SAFEB · 89 · 8 Oct 2026
Tool CallingTanStack/ai
Skill ★ 3.2K
✓SAFEB · 89 · 8 Oct 2026
Triage GithubTanStack/ai
Skill ★ 3.2K
✓SAFEB · 89 · 8 Oct 2026
Ai Code ModeTanStack/ai
Skill ★ 3.2K
✕BLOCKD · 69 · 8 Oct 2026

Questions

Are tanstack's skills safe to install?
Of 13 listings, 12 are SAFE, 0 CAUTION and 1 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 tanstack?
It collects every skill and MCP server on the atlas whose source lives under github.com/tanstack, 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.