verify

Decide whether the diagnosed behaviour is actually a bug or whether the code is doing what it was designed to do. Gate the fix stage.

Quality

67%

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

Fix and improve this skill with Tessl

tessl review fix ./.flue/skills/verify/SKILL.md

Quality

Content

85%Weight 40%Scale 1-3

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, well-structured instruction-only skill: a clearly sequenced procedure with explicit self-checks, concrete domain-specific verdict examples, and an exact output contract. The only soft spot is minor tightening opportunity in the intro and closing steps.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and assumes Claude's competence without explaining generic concepts, but the introductory paragraph and steps 6-7 contain prose that restates the verdict criteria and could be tightened.	2 / 3
Actionability	It gives a concrete, sequenced procedure with specific EmDash examples for each verdict (e.g. missing locale filter, off-by-one pagination, route returning 500 vs 404) and an exact output specification; for an instruction-only skill this is directly actionable, copy-paste-ready guidance.	3 / 3
Workflow Clarity	The 7-step procedure is clearly sequenced and step 6 ("Resist two failure modes") acts as an explicit self-check/validation checkpoint before the verdict is finalized, satisfying the feedback-loop criterion.	3 / 3
Progressive Disclosure	At roughly 43 lines with no need for external references, the content is organized into clearly headed sections (Hard prohibitions, Procedure, Output); per the scoring note this qualifies for the top score without bundle files.	3 / 3
	Total	11 / 12 Passed

Description

50%Weight 40%Scale 1-3

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 conveys a clear purpose and concrete actions but stops short on every dimension at the same middle level: it states what the skill does without an explicit when-to-use trigger clause and with only modest natural-keyword coverage.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when reviewing a diagnosed issue to decide whether it is a real bug or intended behavior before allowing a fix.'

Broaden trigger-term coverage to include variations users actually say, such as 'issue', 'by design', 'intended behavior', and 'false positive'.

Tighten the action phrasing into a compact list of concrete capabilities (e.g. 'Verify whether diagnosed code is a bug or intended behavior, cross-reference docs and tests, and gate the fix stage') to lift specificity toward the score-3 anchor.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions ("Decide whether the diagnosed behaviour is actually a bug" and "Gate the fix stage"), but it is one decision plus its consequence rather than a comprehensive list of separable capabilities, so it does not reach the multi-action bar of the score-3 anchor.	2 / 3
Completeness	The "what" is stated clearly, but there is no "Use when..." clause or equivalent explicit trigger guidance, so per the rubric guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	"bug" and "fix" are natural terms a reporter or reviewer would say, but coverage is thin and missing common variations such as "issue", "by design", "intended", or "false positive".	2 / 3
Distinctiveness Conflict Risk	The pipeline framing ("diagnosed behaviour", "gate the fix stage") gives it a clear niche, but with no explicit distinct triggers and the broad term "bug", it could still overlap with general debugging or triage skills.	2 / 3
	Total	8 / 12 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: emdash-cms/emdash
Path: .flue/skills/verify/SKILL.md
Commit: 53dbf22

Reviewed: 8 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.