verification

Prove that a coding task is actually complete. Use this after meaningful code changes, when tests/builds fail or are skipped, before marking a plan or goal complete, and whenever acceptance depends on runtime, security, recovery, performance, or cross-module evidence.

Quality

88%

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

92%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 an excellent instruction-only verification skill: concise, free of padding, with concrete test-case enumeration and an explicit validation-gated completion checklist. It would only gain from a couple of concrete command or assertion examples to make the guidance copy-paste ready.

Suggestions

Add one or two concrete executable examples (e.g., a shell snippet that asserts a test command selected non-zero tests, or an assertion that a diff is empty) to move actionability from actionable prose to copy-paste-ready.

Optionally show a tiny evidence-matrix template with stable IDs so the 'record evidence with stable IDs' instruction has a concrete artifact shape.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: it never explains what tests, parsers, or state machines are, and every line adds verification-specific judgment Claude would not trivially know. Every token earns its place.	5 / 5
Actionability	As an instruction-only skill it gives concrete, specific guidance such as exact boundary cases to test (adjacent escapes, escaped delimiters, malformed escapes, one below/above the limit). It is highly actionable prose rather than executable code, so it sits just below fully copy-paste-ready.	4 / 5
Workflow Clarity	The numbered completion gate (1–6) and the 'Interpret results correctly' section provide an explicit checklist with validation signals and feedback for rejecting false-success evidence, matching the anchor for a clear sequence with explicit validation steps and a checklist.	5 / 5
Progressive Disclosure	It is a single-purpose skill under 50 lines with no need for external references and clear section organization, qualifying for the simple-skill exception with well-organized sections.	5 / 5
	Total	19 / 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.

The description is strong: it clearly states both what the skill does and when to use it, with concrete trigger conditions tied to realistic coding-agent moments. The main gap is that it centers on a single core action spread across domains rather than enumerating multiple distinct verification actions.

Suggestions

Add one or two distinct concrete verification actions (e.g., 'produce an evidence matrix', 'check the completion gate') alongside 'Prove' to lift specificity toward comprehensive coverage.

Include common trigger synonyms such as 'verify the fix', 'confirm the task is done', or 'close out the goal' so natural user phrasings are better covered.

Dimension	Reasoning	Score
Specificity	"Prove that a coding task is actually complete" names the domain and core action, and the clause enumerates several concrete verification contexts (runtime, security, recovery, performance, cross-module). It stops short of anchor 5 because it expresses one core action across domains rather than multiple distinct concrete actions.	4 / 5
Completeness	It explicitly states what ("Prove that a coding task is actually complete") and when via concrete "Use this after... before... whenever..." trigger phrases, matching the anchor for clearly answering both what and when.	5 / 5
Trigger Term Quality	Natural trigger phrases like "tests/builds fail", "tests/builds... are skipped", and "marking a plan or goal complete" are phrases users would realistically say, with good coverage but a few common synonyms absent.	4 / 5
Distinctiveness Conflict Risk	The completion-verification niche with specific triggers is mostly distinct with only minor overlap risk against general testing skills; not a fully isolated niche so it does not reach 5.	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: ageerle/ruoyi-ai
Path: ruoyi-modules/ruoyi-chat/src/main/resources/coding-harness/skills/verification/SKILL.md
Commit: f92e510

Reviewed: 2 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.