Analyzed Aug 17, 2026
juliusbrussee/caveman
verify-and-stop
Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.
Installation
npx skills add juliusbrussee/caveman --skill verify-and-stop
Similar popular skills
Related neighbors and high-traction skills in the same topics — useful to compare before installing.
Verify a WordPress plugin's Abilities API registrations: enumerate abilities, check that callba…
1.8K installsCheck whether a Playwright, Puppeteer, Selenium or CDP-driven browser presents a coherent finge…
43.5K installsProve a Convex feature works — seed, drive as multiple mocked users via convex-test, assert beh…
18.3K installsUse when about to say "done", "fixed", "passing", or "shipped" - or when reporting the outcome …
5.3K installsConfigure a PreToolUse hook to prevent AI agents from skipping git pre-commit hooks with --no-v…
5.3K installsVerify a claim with fresh local evidence: restate it falsifiably, capture baseline and treatmen…
1.8K installsSecurity audits
Partner security reviews for this skill.
Analyzed Aug 17, 2026
Analyzed Aug 17, 2026
0 alerts
Also in this package
Other skills from juliusbrussee/caveman · top by installs.
npx skills add juliusbrussee/caveman
More details
Agent compatibility
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
Repository health
main
Package contents
Files included with this skill beyond the listing page.
-
skill md
SKILL.md704 B -
docs
SUMMARY.md185 B
History
- First seen on skills.sh
- First recorded snapshot · 39,800 installs
SKILL.md
Verify and stop
Translate acceptance conditions into smallest sufficient proof set.
- Reuse still-current results with matching repository state.
- Run focused checks before wider gates.
- Distinguish pass, fail, unavailable, and blocked exactly.
- Do not edit product code unless verification request includes fixes.
- Do not add polish, cleanup, or unrelated tests after criteria pass.
Stop immediately when acceptance proof is complete. Report commands, results, and unresolved risk only.