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.

3.30x

Quality

79%

Does it follow best practices?

Impact

86%

3.30x

Average score across 3 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

88%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.

An exceptionally lean, well-structured instruction-only skill with a concrete output template, hard formatting rules, and explicit boundary routing to adjacent skills. The only real defect is the dangling `profiles/` reference, which the workflow depends on when the user names no experts.

Suggestions

Ship the `profiles/` directory the Pick section depends on, or replace the reference with inline guidance on how to select experts when the user names none.

Include one fully worked example of a formatted idea line (with the bold change, italic why, and a Win: clause) so the output format is copy-paste unambiguous.

Clarify what "each bringing a different idea to try, not a side in an argument" means operationally — e.g., that ideas must be mutually exclusive changes, not variations on one.

Dimension	Reasoning	Score
Conciseness	The body is ~29 lean lines with zero concept explanation and no padding — rules like "The change alone is bold: it is what the user acts on. The name stays plain, the why italic." carry real instruction weight, matching the "every token earns its place" anchor.	5 / 5
Actionability	It gives a concrete copy-structured template ("1. <Expert> — <the change>"), hard numeric rules ("Three to five ideas", "No line past 72 characters"), and exact output strings ("Win: <one clause>", "Build all <N>?"). It falls short of fully executable because "read `profiles/`" points to a directory absent from the bundle and no fully worked example of an idea line is shown.	4 / 5
Workflow Clarity	The Pick → Ideas → Result sequence is unambiguous for a single-purpose skill, with explicit disambiguation rules ("The question has one retrievable answer → retrieve it... use judge skill... use interrogate skill"). No destructive or batch operations exist, so the validation cap does not apply.	5 / 5
Progressive Disclosure	Under 50 lines with well-organized sections (Pick, Ideas, Result) and no inlined content that belongs elsewhere. The single deduction is that the one external reference, `profiles/`, does not exist in the bundle, leaving a broken navigation path.	4 / 5
	Total	18 / 20 Passed

Description

70%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, well-bounded description with an explicit use-when clause and a clear negative boundary against verdict-type skills. Its main weakness is the abstract, single-action statement of what the skill actually produces.

Suggestions

State the concrete deliverable in the description, e.g., "Generate 3-5 concrete change proposals from a panel of named experts" instead of the abstract "Bring how named experts would think about the question".

Add a few natural trigger synonyms users would actually say, such as "advice", "second opinion", or "what would <expert> do", to broaden keyword coverage.

The negative boundary "not a verdict" is effective; consider pairing it with one or two adjacent-skill exclusions (e.g., not for retrieving a factual answer) to further reduce conflict risk.

Dimension	Reasoning	Score
Specificity	"Bring how named experts would think about the question" names the domain and a single main action but enumerates no concrete deliverables (e.g., a panel of expert-perspective ideas), matching the anchor for 1-2 concrete actions with gaps rather than a list of several.	3 / 5
Completeness	It explicitly answers both: "Bring how named experts would think about the question" (what) and "Use when the user wants expert thinking on a tradeoff, choice, or stuck problem" (when). The when-clause is concrete with a clear boundary, but the what is a single abstract clause rather than explicit concrete actions, so it falls short of the top anchor.	4 / 5
Trigger Term Quality	"expert thinking", "tradeoff", "choice", "stuck problem" are natural phrases users would say, but common synonyms like "advice", "second opinion", or "what would X do" are missing, so coverage is good rather than comprehensive.	4 / 5
Distinctiveness Conflict Risk	The explicit boundary "not a verdict" plus the tradeoff/choice/stuck-problem framing carves a clear niche, with only minor overlap risk against general brainstorming or advice skills.	4 / 5
	Total	15 / 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: 595eda0

Reviewed: 1 day 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.