qa

General-purpose QA verdict for any artifact type

Quality

51%

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 ./skills/qa/SKILL.md

Quality

Content

63%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 delivers actionable, well-sequenced guidance with a clear MCP/fallback structure and concrete output templates, but it is somewhat verbose and inlines content that, with bundle files, could be split into references for leaner loading. The single-file monolithic structure limits progressive disclosure.

Suggestions

Tighten step 3.5 and the RFC #1392 breadcrumb footer section into bullet points to remove verbosity while preserving the verification requirement.

Move the full worked example and the verdict output template into a references/ file (e.g. references/verdict-format.md) and link to it, keeping only a compact template inline in SKILL.md to improve progressive disclosure.

Add an explicit validate->fix->retry feedback loop to the fallback path so non-MCP verdicts have the same recovery checkpoint rigor as the MCP path.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and task-relevant without explaining concepts Claude already knows, but step 3.5 and the RFC breadcrumb footer section are wordy and could be tightened. It is not a 4 because several padded passages remain, and not a 2 because there is no extensive padding of basic concepts.	3 / 5
Actionability	Concrete executable guidance is provided: explicit MCP tool arguments, a fallback agent path, and a copy-pasteable verdict output template plus a worked example. It is not a 5 because some argument placeholders remain abstract and the fallback relies on an external file path rather than fully inline instructions.	4 / 5
Workflow Clarity	Steps are clearly sequenced (0 through 5) with a verdict-threshold table, explicit acting-verification checkpoint (3.5), and a defined fallback path. It is not a 5 because validation/error-recovery feedback loops are only loosely specified (no re-run-on-failure loop for the fallback path), and not a 3 because most checkpoints are present.	4 / 5
Progressive Disclosure	No bundle files (references/, scripts/, assets/) exist, so all ~205 lines are inlined in one file with section headers but no external references; the only pointed-to file (<project-root>/src/ouroboros/agents/qa-judge.md) is not a bundled reference. It is not a 4 because content that could be split (e.g. the verdict template, the full example) is inline, and not a 2 because the file has clear section structure rather than being an unstructured wall.	3 / 5
	Total	14 / 20 Passed

Description

38%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 states a clear purpose but is too generic: it omits explicit trigger guidance and uses broad "general-purpose / any artifact" language that raises conflict risk with other review skills. Trigger terms that exist in the body are not surfaced in the description field.

Suggestions

Add a concrete 'Use when...' clause to the description with natural trigger phrases such as 'Use when the user asks for a QA check, quality check, or wants a quick single-pass verdict on code, docs, API responses, or test output.'

Replace 'General-purpose QA verdict for any artifact type' with specific concrete actions, e.g. 'Scores an artifact against a quality bar and returns a PASS/REVISE/FAIL verdict with dimension scores and actionable suggestions.'

Tighten distinctiveness by contrasting the skill with formal verification pipelines, e.g. 'Use for fast single-pass QA verdicts; use ooo evaluate for 3-stage formal verification.'

Dimension	Reasoning	Score
Specificity	The description names the domain ("QA verdict") and a concrete action ("verdict") with the broad qualifier "for any artifact type", matching the anchor that names the domain plus 1-2 actions without comprehensive coverage. It is not a 4 because no multiple specific actions are listed, and not a 2 because the action is concrete rather than minimal.	3 / 5
Completeness	It gives a clear "what" (a QA verdict for any artifact) but no "Use when..." clause in the description, and per the judging guideline a missing explicit trigger clause caps completeness at 3. It is above 2 because the "what" is clear rather than vague.	3 / 5
Trigger Term Quality	The description field itself contains only the generic phrase "QA verdict" with no natural user-facing trigger terms ("qa check", "quality check" appear only in the body, not the description), so it has one generic keyword and misses the natural phrases users say. It is not a 3 because no relevant natural variations are present in the description.	2 / 5
Distinctiveness Conflict Risk	The phrase "General-purpose QA verdict for any artifact type" is very broad and the word "General-purpose" signals high overlap risk with many other quality/review skills. It is not a 3 because "any artifact type" leaves it less specific than the "Works with document files" example.	2 / 5
	Total	10 / 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: Q00/ouroboros
Path: skills/qa/SKILL.md
Commit: 80333ae

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.