lead-role

Switch into relaxed-planning + dialogue-first mindset when delegated lead role for coordination. Suspends Auto Mode velocity-bias for the duration. Triggers: Use this skill IMMEDIATELY when the user delegates lead with explicit phrases ("you take the lead", "coordinate the team", "lead this phase", "drive the next planning step", "chief-architect" when scope is swarm/substrate/roadmap/multi-ticket), OR when the Mailbox Check Protocol surfaces a valid `lead-role-baton`, OR when you have just authored a substrate-shaped ticket about to enter implementation, OR via direct /lead-role invocation.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

86%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.

The content is a tightly written, well-structured pointer skill that delegates detail to a single clearly-signaled reference file. Its main limitation is that nearly all substantive guidance lives in the reference rather than the body, and the exit condition for the suspended mode is not stated.

Suggestions

Briefly state the exit condition that ends the suspended Auto Mode velocity-bias so the workflow is complete within the body.

Add a one-line summary of what the reference file governs so the body is self-contained enough to act on without first opening the reference.

Confirm the `view_file` tool name and the `.agents/skills/lead-role/references/lead-role-mode.md` path match the actual runtime environment to keep the instruction executable.

Dimension	Reasoning	Score
Conciseness	The 8-line body is lean and efficient: a single mandatory read instruction plus one required payload line, with zero concept over-explanation and every token earning its place; it fully assumes Claude's competence.	5 / 5
Actionability	Provides concrete executable guidance — a named tool (`view_file`), an exact reference path, and a verbatim required payload line — but the substantive operating instructions are offloaded to the reference file rather than present in the body, leaving a minor gap in self-contained actionability.	4 / 5
Workflow Clarity	A clear two-step sequence (read the reference, then emit the declared payload line before drafting anything) with the simple-skill exception applying, but the 'exit condition' that ends the suspended Auto Mode velocity-bias is referenced without being defined here, a minor gap.	4 / 5
Progressive Disclosure	The body is a concise overview pointing to a single one-level-deep reference (`lead-role-mode.md`, confirmed to exist in ./references/) that is explicitly signaled by path, giving clean navigation with no nested references.	5 / 5
	Total	18 / 20 Passed

Description

85%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.

The description is strong on triggers, completeness, and distinctiveness, with rich natural-language activation phrases and a clear what/when split. Its only weakness is specificity: the stated actions are abstract mindsets framed in second-person imperative voice rather than concrete operations.

Suggestions

Rephrase the 'what' with concrete operations instead of mindsets (e.g., 'Drafts planning tickets, facilitates design dialogue, and coordinates peer agents') to lift specificity.

Convert the second-person 'Use this skill IMMEDIATELY' to third-person declarative voice (e.g., 'Activate when the user delegates lead...') to avoid the voice penalty.

Tighten the abstract phrase 'relaxed-planning + dialogue-first mindset' into specific behaviors Claude will perform.

Dimension	Reasoning	Score
Specificity	Names the domain ('delegated lead role for coordination') and a couple actions ('Switch into relaxed-planning + dialogue-first mindset', 'Suspends Auto Mode velocity-bias'), but the actions are abstract mindsets rather than concrete operations, and the second-person imperative 'Use this skill IMMEDIATELY' triggers the -1 voice penalty, pulling it from 3 to 2.	2 / 5
Completeness	Explicitly answers both 'what' ('Switch into relaxed-planning + dialogue-first mindset', 'Suspends Auto Mode velocity-bias') and 'when' with a dedicated 'Triggers:' clause enumerating concrete trigger phrases and conditions.	5 / 5
Trigger Term Quality	Comprehensive natural-language triggers including 'you take the lead', 'coordinate the team', 'lead this phase', 'drive the next planning step', 'chief-architect', plus the `lead-role-baton` protocol trigger and direct /lead-role invocation — covers synonyms and natural phrasings users would actually say.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (lead-role coordination scoped to swarm/substrate/roadmap/multi-ticket) with distinctive triggers like the `lead-role-baton` Mailbox Check Protocol and /lead-role invocation, giving it minimal overlap with other skills.	5 / 5
	Total	17 / 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: neomjs/neo
Path: .agents/skills/lead-role/SKILL.md
Commit: 210c03c

Reviewed: 3 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.