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.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An efficient, well-structured instruction skill that gives clear actionable rules and a logical verification workflow without padding. Its only weak spot is the absence of explicit validation feedback loops and concrete executable commands.

Suggestions

Add a short feedback-loop note for failed checks (e.g., 'On fail: isolate the failing check, re-run it alone, then report') to push workflow_clarity toward 5.

Include one concrete example of a focused-check command and a wider-gate command to make the actionability fully executable rather than directive-only.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no concept over-explanation; every line ('Run focused checks before wider gates', 'Stop immediately when acceptance proof is complete') earns its place and assumes Claude's competence.	5 / 5
Actionability	Provides concrete actionable directives ('Do not edit product code unless verification request includes fixes', 'Distinguish pass, fail, unavailable, and blocked exactly') appropriate for an instruction-only skill, with minor gaps in executable specifics.	4 / 5
Workflow Clarity	A clear logical sequence is present (translate proof set, reuse results, focused-then-wider checks, distinguish outcomes, stop) with an explicit stop checkpoint, though validation feedback loops are only implicit.	4 / 5
Progressive Disclosure	Under 50 lines with no need for external references, yet well-organized with a header, lead directive, and bulleted rules — meeting the simple-skill exception for a top score.	5 / 5
	Total	18 / 20 Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, concise description that clearly states both capability and explicit trigger conditions in third person. It is specific and well-differentiated, with only minor gaps in action breadth and natural-term synonyms.

Dimension	Reasoning	Score
Specificity	Names the verification domain and lists several concrete trigger scenarios ('validation-only tasks, completion checks, focused gate runs, and last-mile proof') with a concrete action ('Prove existing work meets acceptance conditions'), though the core action is singular rather than a broad action list.	4 / 5
Completeness	Explicitly answers both what ('Prove existing work meets acceptance conditions without expanding scope') and when ('Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural keyword coverage ('completion checks', 'validation-only tasks') a user might say, but 'focused gate runs' and 'last-mile proof' lean toward jargon and common synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	The anti-scope-creep verification niche is mostly distinct with clear triggers, but 'completion checks' could overlap with general review or verify skills, so minor conflict risk remains.	4 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: JuliusBrussee/caveman
Path: skills/verify-and-stop/SKILL.md
Commit: f5d7294

Reviewed: 1 hour ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

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.