intent

Turn rough ideas into clear work orders before planning or building. Use when request is vague like "add a button", "make it better", "fix the thing". Triggers on ambiguous or underspecified requests.

0.00x

Quality

—

Does it follow best practices?

Impact

0.00x

Average score across 2 eval scenarios

Securityby

Passed

No known issues

Quality

Content

92%

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 exceptionally lean, actionable, well-sequenced instruction skill with explicit validation and feedback loops. Its one real gap is progressive disclosure: doc-gen markers reference ../card.md, ../prompts.md, and ../gate.md, but none of those files are present, so the promised split content is not actually externalized.

Suggestions

Provide the referenced bundle files (../card.md, ../prompts.md, ../gate.md) or move them into references/ and update the doc-gen src paths so the signaled one-level-deep references resolve to real files.

If the inlined card/prompts/gate blocks are meant to live in SKILL.md, remove the doc-gen FILE markers that imply external files to avoid a broken reference signal.

Confirm the doc-gen tooling actually generates those files at build time; if so, note in the body that the markers are build-time directives so the inline copy is not mistaken for a missing split.

Dimension	Reasoning	Score
Conciseness	Every line is high-signal, opinionated guidance (e.g. 'carry only what the next stage can't cheaply re-derive', 'No empty scaffolding, ever') with no padding of concepts Claude already knows; every token earns its place.	3 / 3
Actionability	As an instruction-only skill it gives concrete executable mechanics ('exactly 3 candidate answers + 1 uniform escape hatch', 'Present verdict-FIRST via AskUserQuestion', 'at least once, ask what this should NOT do') rather than vague direction.	3 / 3
Workflow Clarity	A clear 4-step work loop feeds a gate with explicit two-pass validation (deletion pass then completeness pass) and a FAIL feedback loop ('name exactly what is missing and ask for it'), matching the validate->fix->retry pattern.	3 / 3
Progressive Disclosure	The body signals one-level-deep references via doc-gen markers (src=../card.md, ../prompts.md, ../gate.md) but those files do not exist, so content that should be split (card/prompts/gate) is inlined in SKILL.md rather than actually externalized.	2 / 3
	Total	11 / 12 Passed

Description

90%

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 explicitly states what the skill does and when to use it, with vivid natural-language trigger phrases users would actually say. Its only weakness is that it describes a single composite action rather than listing multiple concrete operations.

Dimension	Reasoning	Score
Specificity	Names the domain and a concrete action ('Turn rough ideas into clear work orders before planning or building') but does not enumerate multiple distinct concrete actions like the score-3 examples, so it sits at 'names domain and some actions'.	2 / 3
Completeness	Explicitly answers both what ('Turn rough ideas into clear work orders') and when ('Use when request is vague like...', 'Triggers on ambiguous or underspecified requests') with explicit triggers.	3 / 3
Trigger Term Quality	Quotes natural user utterances a person would actually say ('add a button', 'make it better', 'fix the thing') plus the abstract trigger class 'ambiguous or underspecified requests', giving good coverage of natural terms.	3 / 3
Distinctiveness Conflict Risk	Carves a clear pre-planning clarification niche with distinct triggers (vague/underspecified requests) that are unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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: saadshahd/moo.md
Commit: 6f578c4

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.