lane-intent

Narrow, non-authoritative, TTL-bound pre-V-B-A signal for collision-prone / high-blast / long-V-B-A lanes (deep memory-mining, tech-debt-radar, multi-turn architectural V-B-A). Distinct from authoritative `[lane-claim]` (post-V-B-A). Triggers: Use this skill BEFORE broadcasting `[lane-intent] evaluating #N` to confirm scope-trigger qualifies — narrow scope, not blanket coverage. Do NOT auto-fire for short single-turn V-B-A where direct `[lane-claim]` after V-B-A suffices.

Quality

86%

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.

An efficiently written single-purpose skill body that defers detail to one well-signaled, verified reference. Actionability and workflow clarity sit just below the top because the actual gating/validation logic is delegated to that reference rather than surfaced in the body.

Suggestions

Surface the 3-condition scope-trigger gate as a short inline checklist so the body is self-sufficient for the core go/no-go decision, not just a pointer to the reference.

Add an explicit validation/feedback step after reading the protocol (e.g., 'If any of the 3 conditions fails, do NOT broadcast; use direct [lane-claim] instead') to make the feedback loop visible in the body.

Clarify the recovery/TTL step in the body briefly so the lifecycle (declare → 2h TTL → recover) is sequenced rather than only named.

Dimension	Reasoning	Score
Conciseness	About nine lean lines with no padding and no explanation of concepts Claude already knows; every line (read-path, source of authority, required payload line) earns its place.	5 / 5
Actionability	Gives a concrete reference path to read and a copy-paste-ready first payload line, but the core gating logic (the 3-condition scope-trigger gate) is delegated to the reference rather than stated here, leaving a minor gap.	4 / 5
Workflow Clarity	The sequence is clear (read protocol, then broadcast with the required payload line) and "read protocol before broadcasting" acts as a gating checkpoint, but explicit validation/feedback steps live in the reference rather than the body.	4 / 5
Progressive Disclosure	A lean overview that points to one clearly-signaled, one-level-deep reference (`.agents/skills/lane-intent/references/lane-intent-protocol.md`, verified present) describing exactly what it contains; navigation is unambiguous.	5 / 5
	Total	18 / 20 Passed

Description

87%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 precise, third-person description that answers both what and when with concrete positive and negative triggers and an explicit boundary against the sibling lane-claim skill. It is slightly jargon-heavy, which keeps trigger-term and specificity scores just below the top.

Dimension	Reasoning	Score
Specificity	Names concrete applications ("deep memory-mining, tech-debt-radar, multi-turn architectural V-B-A") and concrete actions ("broadcasting `[lane-intent] evaluating #N`", "confirm scope-trigger qualifies"); not a 5 because the skill really performs one signal action across contexts rather than multiple distinct actions.	4 / 5
Completeness	Clearly states what it is ("Narrow, non-authoritative, TTL-bound pre-V-B-A signal") and explicitly answers when to use it with concrete positive and negative trigger phrases.	5 / 5
Trigger Term Quality	Includes the ecosystem's natural trigger phrase ("Use this skill BEFORE broadcasting `[lane-intent] evaluating #N`") plus an explicit negative trigger ("Do NOT auto-fire for short single-turn V-B-A"); held below 5 because the surrounding terms (V-B-A, TTL, scope-trigger) are dense internal jargon with no synonyms.	4 / 5
Distinctiveness Conflict Risk	Explicitly distinguishes from the sibling skill ("Distinct from authoritative `[lane-claim]` (post-V-B-A)") with a clear pre/post-V-B-A and authoritative/non-authoritative boundary, minimizing conflict risk.	5 / 5
	Total	18 / 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/lane-intent/SKILL.md
Commit: 210c03c

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.