peer-role

Switch into evidence-backed convergence-pressure mindset when reviewing a peer's design proposal. Suspends Auto Mode "ack-and-move-on" bias for the duration. Triggers: Use this skill IMMEDIATELY when reviewing an Ideation Sandbox discussion / architectural proposal, an epic shape, a skill shape, a roadmap or milestone proposal, or a `/lead-role` convergence artifact. Do NOT auto-fire on ordinary status broadcasts where the right action is mark-read or "no collision".

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

100%Weight 40%Scale 1-3

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 exemplary progressive-disclosure pointer: lean, concrete, correctly ordered, and cleanly delegating detail to a single verified one-level-deep reference. It fully respects the token budget while remaining actionable.

Dimension	Reasoning	Score
Conciseness	The body is a 7-line pointer that assumes Claude's competence and explains no background concepts; every token earns its place, matching anchor 3. It is not 2 because there is no unnecessary explanation or padding to tighten.	3 / 3
Actionability	It gives fully executable, copy-paste-ready directives — an exact tool call (`view_file` on a specific path) and an exact required first-payload declaration string — matching anchor 3. Per the instruction-only scoring note, the absence of code is not penalized because the guidance is concrete and actionable.	3 / 3
Workflow Clarity	The single-purpose workflow is unambiguous and correctly ordered ("read…before drafting ANY A2A messages…or executing tasks in parallel"). Per the simple-skills scoring note, a single unambiguous action can score 3, and no destructive/batch operation in the body requires a validation checkpoint.	3 / 3
Progressive Disclosure	The body is a lean overview that signals one one-level-deep reference (`.agents/skills/peer-role/references/peer-role-mode.md`, verified present in ./references/) with a clear navigation instruction, matching anchor 3. It is not 2 because the reference is clearly signaled and content is appropriately split rather than inlined.	3 / 3
	Total	12 / 12 Passed

Description

75%Weight 40%Scale 1-3

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 clearly answers both what the skill does and when to use it, with strong distinctiveness via an explicit negative trigger. Its weak points are jargon-heavy trigger terms and abstract mental-mode phrasing rather than concrete actions.

Suggestions

Reword the capability statement as concrete actions the skill performs (e.g., 'Audit the artifact's source of authority, surface precedent gaps, and produce evidence-backed challenges or refinements') instead of 'Switch into…mindset' to raise specificity.

Soften substrate-internal jargon in trigger terms (e.g., gloss 'epic shape' / 'skill shape' / 'convergence artifact') or pair them with plainer phrasing a user would naturally say, so trigger_term_quality reaches natural-keyword coverage.

Consider whether 'convergence-pressure mindset' and 'Auto Mode ack-and-move-on bias' can be stated more plainly without losing the niche, to reduce buzzword density.

Dimension	Reasoning	Score
Specificity	The description frames the skill as a mental-mode switch ("Switch into evidence-backed convergence-pressure mindset", "Suspends Auto Mode 'ack-and-move-on' bias") plus one activity ("reviewing a peer's design proposal") rather than a list of concrete operations, matching anchor 2. It is not 3 because it lacks multiple specific concrete actions, and not 1 because it does name a domain and some actions.	2 / 3
Completeness	It explicitly answers both what ("Switch into evidence-backed convergence-pressure mindset… Suspends Auto Mode 'ack-and-move-on' bias") and when ("Triggers: Use this skill IMMEDIATELY when…"), plus a negative trigger. This clearly matches the anchor 3 example answering both what and when with explicit triggers.	3 / 3
Trigger Term Quality	It enumerates broad trigger contexts ("Ideation Sandbox discussion / architectural proposal, an epic shape, a skill shape, a roadmap or milestone proposal, or a `/lead-role` convergence artifact") but the terms are heavily internal jargon ("epic shape", "convergence artifact") rather than natural general-user keywords. It is not 3 because the language is jargon-dense, and not 1 because the trigger coverage is substantial and domain-relevant.	2 / 3
Distinctiveness Conflict Risk	The explicit negative trigger ("Do NOT auto-fire on ordinary status broadcasts where the right action is mark-read or 'no collision'") alongside specific positive triggers carves a clear niche and reduces conflict with adjacent skills, matching anchor 3.	3 / 3
	Total	10 / 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: neomjs/neo
Path: .agents/skills/peer-role/SKILL.md
Commit: c1ce853

Reviewed: 8 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.