Cuts one signed NemoClaw semver tag after required candidate checks and the maintainer's E2E decision, then follows the tag-triggered release work and drafts the Announcement. Use when preparing or publishing a vX.Y.Z release tag.
73
92%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
At runtime this skill reads outsider-authored free text from GitHub PRs/commits (e.g., `references/candidate-evidence.md` uses `gh api` to fetch PR commits/files and `git log` output, and the resulting evidence fields are incorporated into `release-brief.md`, which is later used as the signed tag annotation).
e987b00
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.