verify-and-stop
verify-and-stop is a Plan & work review gates skill for AI agents, published by JuliusBrussee in the caveman repository on GitHub. Skillspace rates verify-and-stop D (68/100) and it passed the safety scan; a judge model has also reviewed it.
Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.
- Grade
- D
- Quality
- 68 / 100
- Safety
- Passed
- GitHub stars
- 105,328
Placed #5 of 6 in the judged category final for Plan & work review gates.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 100 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
Judge review
Placed #5 of 6 in the judged category final for Plan & work review gates.
- Trigger
82 82 - Instructions
65 65 - Specificity
45 45 - Safety
92 92 - Disclosure
70 70 - Maintenance
55 55
Crisp, scope-safe principles (no edits, no post-pass polish, stop immediately) but reads as a set of maxims rather than a procedure, with no concrete examples of what 'sufficient proof' looks like.
Not checked yet
- 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.