Back to skills

Agent Skill

Verify And Stop

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.

JuliusbrusseeTestingGoAiAnthropicCavemanClaudeClaude-codeLlmMemePrompt-engineeringSkillTokens

59K installs

juliusbrussee/caveman

by Juliusbrussee

Score

8.5

/ 10

Installs

59K

Repo Stars

106.6K

Last Updated

0d ago

Fresh

Quality Ratio

86%

Description

Verified

Language

Go

First Published

Aug 2026

Summary

The Verify And Stop agent skill guides agents to validate existing work against defined acceptance criteria without expanding scope. Developers and QA engineers who need precise, contained validation for completed tasks benefit from this agent skill. This is a skill with 12K installs. This agent skill directs the agent to translate acceptance conditions into the smallest sufficient proof set, reusing current results and running only focused checks. It strictly mandates precise status reporting (pass, fail, unavailable, blocked) and instructs the agent to stop immediately once acceptance proof is complete, actively preventing scope creep like adding polish or editing product code without explicit instructions.

Skill Definition

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.

How to Use

Use in O-mega

Claude Code

npx skills add juliusbrussee/caveman verify-and-stop
Verify And Stop | Agent Skills | o-mega