consult

Bring how named experts would think about the question. Use when the user wants expert thinking on a tradeoff, choice, or stuck problem — not a verdict.

1.19x

Quality

76%

Does it follow best practices?

Impact

55%

1.19x

Average score across 2 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./hope/skills/consult/SKILL.md

Quality

Content

75%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.

A tightly written behavioral workflow with clear sequencing, gating checkpoints, and a self-handling missing-profile fallback. It loses points mainly for a dangling `profiles/` reference and slight repetition of the no-verdict constraint.

Suggestions

Provide a `profiles/` directory (or state up front that profiles are optional/model-supplied) so the "Read `profiles/`" reference is not dangling.

Consolidate the three restatements of the no-verdict boundary (Output section) into one to tighten conciseness.

Add one explicit validate-style checkpoint in the Pick or Voice step (e.g., confirm the chosen experts genuinely pull against each other before voicing) to push workflow clarity toward 5.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude's competence, and explains no background concepts, but the no-verdict boundary is restated three times ("no verdict assembled," "never as a ruling," "never as another round of consulting"), a minor trim opportunity that keeps it just below 5.	4 / 5
Actionability	Concrete, executable behavioral guidance is given — "Take two or three," "invoked by name once per expert," and named voice examples ("Fowler argues…") — with only minor gaps, fitting the mostly-executable 4-anchor rather than the copy-paste 5-anchor.	4 / 5
Workflow Clarity	A clear Extract → Gate → Pick → Voice → Output sequence is present with checkpoints (the Gate) and a feedback loop ("Easy agreement means the picking was wrong — swap one"), but it lacks the crisp validate-then-proceed loop of the 5-anchor.	4 / 5
Progressive Disclosure	Sections are well-organized and the single external reference ("Read `profiles/") is clearly signaled and one level deep, but the referenced `profiles/` directory is absent from the bundle, a minor organization gap below the 5-anchor.	4 / 5
	Total	16 / 20 Passed

Description

78%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.

A concise, third-person description that clearly states both capability and trigger conditions with natural phrasing. Its main weakness is specificity: the "what" is a single abstract action rather than a concrete capability list.

Dimension	Reasoning	Score
Specificity	The description names the domain and one concrete action — "Bring how named experts would think about the question" — but offers only a single, somewhat abstract action rather than a list of concrete capabilities, matching the 3-anchor more than the multi-action 4-anchor.	3 / 5
Completeness	It explicitly answers both what ("Bring how named experts would think about the question") and when ("Use when the user wants expert thinking on a tradeoff, choice, or stuck problem — not a verdict") with concrete trigger phrases, matching the 5-anchor.	5 / 5
Trigger Term Quality	Natural user phrasings appear — "expert thinking on a tradeoff, choice, or stuck problem" — giving good coverage, though common synonyms like "decision," "dilemma," or "can't decide" are absent, keeping it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	The "not a verdict" carve-out distinguishes it from sibling judge/interrogate skills, but the broad expert-thinking framing leaves minor overlap risk with closely related advisory skills rather than a fully sealed niche.	4 / 5
	Total	16 / 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: saadshahd/moo.md
Path: hope/skills/consult/SKILL.md
Commit: 7f55b8e

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.