shape

Resolves technical HOW decisions — architecture choices, technology selection, and design patterns. Use shape when the intent is clear but the technical path is not. Triggers on "shape this", "architecture for X", "how should I build", "which pattern", "technical approach".

1.72x

Quality

—

Does it follow best practices?

Impact

83%

1.72x

Average score across 3 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 lean, highly actionable, and ships a clear validated workflow with feedback loops. Its main weakness is progressive disclosure: dense spec blocks are inlined monolithically rather than split into signaled, navigable reference files.

Suggestions

Move the card specification, decision-prompt mechanics, and gate audit into separate reference files under references/ (e.g. references/card.md, references/gate.md) and link to them one level deep, keeping SKILL.md as a concise overview.

Soften the most cryptic aphorisms (e.g. "Cheap local facts always answer yes. Two kinds answer no.") with a half-line gloss so the rule is actionable without re-deriving the intent.

Add a short quick-start or worked example showing one HOW decision flowing through prime → extract → resolve → gate, so the abstract loop is grounded concretely.

Dimension	Reasoning	Score
Conciseness	The body is dense and imperative ("Decide HOW before building", "Carry only what the next stage can't cheaply re-derive") and never explains concepts Claude already knows; every line earns its place.	3 / 3
Actionability	Guidance is concrete and specific: the AskUserQuestion mechanics ("exactly 3 candidate answers + 1 uniform escape hatch", "Label = recommendation"), the loop-selection table with reliability rules, and the gate passes give copy-ready instruction rather than vague direction.	3 / 3
Workflow Clarity	"The work loop" is a numbered 1–5 sequence ending in a gate, with explicit validation checkpoints (deletion pass, completeness pass) and a feedback loop ("On FAIL: name exactly what is missing and ask for it").	3 / 3
Progressive Disclosure	Sections are well-labeled, but the card/prompts/gate blocks are large inline walls (inlined via doc-gen from ../card.md etc.) rather than one-level-deep navigable bundle references, and no bundle files exist under references/scripts/assets to split the content.	2 / 3
	Total	11 / 12 Passed

Description

100%

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 tight, third-person description that concretely names the capability, gives explicit trigger guidance, and carves out a distinct niche. It hits every anchor at the top of the scale with no padding.

Dimension	Reasoning	Score
Specificity	"Resolves technical HOW decisions — architecture choices, technology selection, and design patterns" names the domain and lists multiple concrete action areas, matching the score-3 anchor.	3 / 3
Completeness	It states what the skill does ("Resolves technical HOW decisions...") and explicitly when to use it ("Use shape when the intent is clear but the technical path is not" plus a Triggers clause), satisfying both what and when.	3 / 3
Trigger Term Quality	"Triggers on 'shape this', 'architecture for X', 'how should I build', 'which pattern', 'technical approach'" gives good coverage of natural phrases a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The niche is clearly bounded to technical HOW decisions when intent is already locked, with distinct trigger phrases that are unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 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: about 7 hours 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.