babysit

babysit is a Review feedback & PR process skill for AI agents, published by nubjs in the nub repository on GitHub. Skillspace rates babysit D (65/100) and it passed the safety scan; the rating is based on static analysis only.

Bring one nubjs/nub pull request to merge-readiness — pull the inline reviews, verify each finding against the code, re-verify every fix round locally, fix CI, and loop. Invoke (via the Skill tool) when asked to babysit a PR, to get one merge-ready, or when you own a PR and are waiting on reviews or CI. Scope — babysit ENDS at merge-readiness and hands back; only an instruction to babysit it TO MERGE authorizes the merge, and that phrasing also delegates the readiness judgment, so decide rather than ask. Carries the traps that each cost a round trip: the GitHub CLI's PR-view JSON silently omits the inline review comments where the real findings live, the CI gate aggregator check registers LAST so a partial green rollup is not done, and PR CI is opt-in, so a pull request nobody labelled has no checks at all and a re-based or re-targeted branch keeps the checks of its old head.

Grade
D
Quality
65 / 100
Safety
Passed
GitHub stars
4,285

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Our review

Architecture
94 / 100
Maturity
Basic: a single SKILL.md
Security scan
No issues found
License
Not declared. Check the repository before reusing it.

Not checked yet

  • Category is a classifier prediction; no model has read this skill yet
  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.