Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Publisher · GitHub organization

zolotukhin

github.com/zolotukhin ↗Last audit 16 Oct 2026

zolotukhin publishes 10 agent skills on the atlas: 10 SAFE, 0 CAUTION, 0 BLOCK, with a mean score of 89/100. Every listing below is audited on its own.
Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “zolotukhin: skills and MCP servers”. Retrieved 16 Oct 2026. https://modelsatlas.com/orgs/zolotukhin
Listings
10

0 MCP servers · 10 skills

Mean score
89 / 100

mean of the audit scores

Findings
9

across all listings

Stars
5.2K

on the listed repositories

✓SAFE 10!CAUTION 0✕BLOCK 0

Everything zolotukhin publishes here

Most stars first · stamps show the audited version

Speckit Analyzezolotukhin/zinc
Skill ★ 522
✓SAFEB · 89 · 16 Oct 2026
Speckit Checklistzolotukhin/zinc
Skill ★ 522
✓SAFEB · 89 · 16 Oct 2026
Speckit Clarifyzolotukhin/zinc
Skill ★ 522
✓SAFEB · 89 · 16 Oct 2026
Speckit Constitutionzolotukhin/zinc
Skill ★ 522
✓SAFEB · 89 · 16 Oct 2026
Speckit Implementzolotukhin/zinc
Skill ★ 522
✓SAFEB · 89 · 16 Oct 2026
Speckit Planzolotukhin/zinc
Skill ★ 522
✓SAFEB · 89 · 16 Oct 2026
Speckit Specifyzolotukhin/zinc
Skill ★ 522
✓SAFEB · 89 · 16 Oct 2026
Speckit Taskszolotukhin/zinc
Skill ★ 522
✓SAFEB · 89 · 16 Oct 2026
Speckit Taskstoissueszolotukhin/zinc
Skill ★ 522
✓SAFEB · 89 · 16 Oct 2026
Zig Docgenzolotukhin/zinc
Skill ★ 522
✓SAFEB · 89 · 16 Oct 2026

Questions

Are zolotukhin's skills safe to install?
Of 10 listings, 10 are SAFE, 0 CAUTION and 0 BLOCK, with a mean score of 89 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 zolotukhin?
It collects every skill and MCP server on the atlas whose source lives under github.com/zolotukhin, 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.