consult

Use when you want to learn how experts would think about a design tradeoff, architecture choice, repeated failure, or domain question. Triggers on expert names, "mentor", "panel", "debate", "what would [X] say", "stuck on", style requests.

0.00x

Quality

—

Does it follow best practices?

Impact

0.00x

Average score across 1 eval scenario

Securityby

Passed

No known issues

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-engineered instruction skill: lean, operationally specific, with a clearly sequenced four-step workflow and explicit decision checkpoints. No significant weaknesses across the content dimensions.

Dimension	Reasoning	Score
Conciseness	Lean and disciplined — terse principle bullets, no explaining of concepts Claude already knows, and the Domain Map table earns its tokens as routing data the skill actually needs.	3 / 3
Actionability	Concrete, operational guidance throughout: exact AskUserQuestion option names, 'one Agent per selected expert launched in a single message', pool sizing (~6-8), max-2-per-domain, and the dissent-line requirement — copy-paste-ready for this instruction skill.	3 / 3
Workflow Clarity	A clear 4-step sequence (Route → Pick mode → Reason → Present) with explicit decision checkpoints after mode selection (Accept/Reshuffle/Switch) and a closing direction question.	3 / 3
Progressive Disclosure	Self-contained and cleanly sectioned with no bundle files to navigate; the `profiles/` reference is described inline via the Domain Map rather than split into bundled files, appropriate for this skill's structure.	3 / 3
	Total	12 / 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.

A strong description with an explicit 'Use when...' trigger clause and a rich set of natural trigger phrases. The only soft spot is specificity, which describes a conceptual activity rather than enumerating multiple concrete actions.

Suggestions

Consider listing a few concrete operations (e.g., 'surfaces expert reasoning and named disagreements') alongside the conceptual framing to lift specificity toward level 3.

Ensure the description remains in third person; it currently reads as a directive ('Use when you want...') rather than third-person voice, which the rubric flags as a specificity concern.

Dimension	Reasoning	Score
Specificity	Names the domain (design tradeoffs, architecture, repeated failure, domain questions) and the activity of learning how experts think, but stops at a conceptual activity rather than a list of multiple concrete operations.	2 / 3
Completeness	A clear 'Use when...' clause answers both what (learn how experts reason about tradeoffs/choices/failures/questions) and when (the listed trigger terms), with the 'when' stated explicitly rather than implied.	3 / 3
Trigger Term Quality	Explicitly enumerates natural trigger phrases a user would say — 'mentor', 'panel', 'debate', 'what would [X] say', 'stuck on', style requests, expert names — covering common variations.	3 / 3
Distinctiveness Conflict Risk	The expert-consultation framing and trigger set ('mentor', 'panel', 'what would [X] say') carve a distinct niche unlikely to collide with document, code, or data 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: 4 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.