architecture-pre-flight

High-level umbrella router for navigating broad, cross-substrate architectural ambiguity. Triggers: Use when no narrower pre-flight clearly applies, or when work spans multiple trigger families such as new subsystems, protocols, MCP tools, or cross-substrate refactors.

Quality

82%

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 body is a well-structured, maximally concise router that correctly defers detail to a single real one-level-deep reference. Its only weakness is that, being a pure redirect, it surfaces no validation or decision checkpoint in the body itself.

Dimension	Reasoning	Score
Conciseness	The body is extremely lean (three short lines) with no padding or explanation of concepts Claude already knows; every token earns its place, matching the score-5 'lean and efficient' anchor.	5 / 5
Actionability	Provides one concrete, executable instruction ('Use `view_file` to read `references/architecture-pre-flight-workflow.md`'), but all substantive guidance is delegated to the reference, leaving the body itself as a single redirect with that one minor gap.	4 / 5
Workflow Clarity	The single primary action ('read the reference before deciding on broad architecture') is unambiguous, but the body surfaces no validation or decision checkpoint itself — the sequenced protocol with verification lives entirely in the referenced file.	4 / 5
Progressive Disclosure	A clear, concise overview that points to a single well-signaled, one-level-deep reference (verified to exist) via an explicit MANDATORY ACTION, matching the score-5 anchor for clean overview with easy navigation.	5 / 5
	Total	18 / 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.

The description is strong: it explicitly covers both what and when with concrete trigger families and good keyword coverage. Its main weakness is that the core action ('router'/'navigating ambiguity') is an abstract metaphor rather than a concrete operation.

Dimension	Reasoning	Score
Specificity	Names the domain ('cross-substrate architectural ambiguity') and the function ('umbrella router', 'navigating') plus several concrete trigger domains (subsystems, protocols, MCP tools, refactors), but the core action is an abstract routing metaphor rather than multiple concrete operations, matching the score-3 anchor of naming a domain with 1-2 actions.	3 / 5
Completeness	Explicitly answers both what ('High-level umbrella router for navigating broad, cross-substrate architectural ambiguity') and when ('Triggers: Use when no narrower pre-flight clearly applies, or when work spans multiple trigger families...') with concrete trigger phrases, matching the score-5 anchor.	5 / 5
Trigger Term Quality	Good keyword coverage with natural terms users would say ('new subsystems', 'protocols', 'MCP tools', 'cross-substrate refactors', 'pre-flight'), though 'cross-substrate' is somewhat jargon-heavy and a few common synonyms are absent, placing it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Has a clear niche as the catch-all router that explicitly defers to narrower pre-flights, but its umbrella nature ('spans multiple trigger families') creates inherent minor overlap risk with the very skills it routes to, keeping it just below minimal-conflict.	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: neomjs/neo
Path: .agents/skills/architecture-pre-flight/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.