verify

AI DevKit · Enforce evidence-based completion claims — require fresh command output before reporting success. Use when completing any task, fixing a bug, finishing a phase, running tests, building, deploying, or making any "it works" claim.

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

100%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.

The body is a tight, highly actionable verification protocol with explicit gates, feedback loops, and concrete evidence requirements. It is exemplary for an instruction-only skill and needs no bundle files.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no padding and no explanation of concepts Claude already knows; every section and table earns its place, assuming Claude's competence.	5 / 5
Actionability	Fully actionable guidance — a concrete 5-step gate, an executable regression recipe, an exact evidence-pattern table ('Test output: 0 failures, exit 0'), and a copy-paste memory-store command.	5 / 5
Workflow Clarity	Clear ordered 5-step sequence with an explicit feedback loop ('If any step fails, stop. Fix the issue and restart from step 1.') and a regression checklist with explicit pass/fail checkpoints.	5 / 5
Progressive Disclosure	A single-purpose, under-50-line skill with no external references needed; well-organized into clear sections per the simple-skill exception.	5 / 5
	Total	20 / 20 Passed

Description

91%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 description that clearly states the skill's purpose and gives rich, natural trigger guidance. It reads like a polished Anthropic-style description and is unlikely to mis-trigger for unrelated work.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete actions ('Enforce evidence-based completion claims', 'require fresh command output before reporting success') with a broad list of trigger contexts, but capabilities are framed as enforcement/requirement rather than a fully enumerated action set, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both 'what' (enforce evidence-based completion claims) and 'when' (the 'Use when...' clause with concrete trigger phrases), matching the top anchor.	5 / 5
Trigger Term Quality	Includes many natural trigger phrases users would say — 'completing any task, fixing a bug, finishing a phase, running tests, building, deploying, or making any "it works" claim' — covering common variations comprehensively.	5 / 5
Distinctiveness Conflict Risk	The verification-of-completion-claims niche is mostly distinct with clear triggers, but 'verify' is a broad concept with minor overlap risk against general testing/validation skills.	4 / 5
	Total	18 / 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: codeaholicguy/ai-devkit
Path: skills/verify/SKILL.md
Commit: d56e554

Reviewed: 3 days 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.