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

70%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/architecture-pre-flight/SKILL.md

Quality

Content

72%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 lean router: a clear overview pointing to one well-signaled, verified reference file with no padding. Its only gap is that actionable specificity and the actual routing workflow live entirely in the reference rather than the body.

Suggestions

Add a one-line summary of the routing decision the reader should produce after reading the reference, so the body states the outcome not just the input.

Optionally surface the single highest-value checkpoint from the reference (e.g. 'state the selected discipline and why the nearest alternative was rejected') inline for quick reference.

Dimension	Reasoning	Score
Conciseness	The body is three lean lines with no padding and no explanation of concepts Claude already knows; every token earns its place. Not below 3 because nothing is superfluous.	3 / 3
Actionability	It gives one concrete executable directive ('Use view_file to read references/architecture-pre-flight-workflow.md'), but no examples, parameters, or specific guidance beyond 'go read this file'. Not a 1 because the directive is concrete and executable; not a 3 because it lacks specific examples or copy-paste-ready detail.	2 / 3
Workflow Clarity	It states a single unambiguous step (read the reference before deciding on broad architecture), but the actual multi-step routing protocol is deferred entirely to the reference file, with no checkpoints or sequence in the body. Not a 1 because the one step is clear; not a 3 because the real workflow and any validation live outside the body.	2 / 3
Progressive Disclosure	The body is a clear overview that signals one one-level-deep reference via a prominent 'MANDATORY ACTION' and an explicit path; the referenced file exists and contains the detail without further content nesting. Not below 3 because the split and navigation are exactly appropriate.	3 / 3
	Total	10 / 12 Passed

Description

67%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 is grammatically third-person and explicitly covers both what the skill does and when to use it, which is a strong baseline. Its weakness is reliance on internal jargon ('cross-substrate', 'trigger families') and an inherently catch-all trigger that blurs distinctiveness.

Suggestions

Reword jargon terms ('cross-substrate', 'trigger families') into phrases a user would naturally say, e.g. 'spans multiple subsystems or technologies'.

Tighten the action statement with concrete routing verbs (e.g. 'Routes ambiguous architectural decisions to the right specialized pre-flight skill').

Clarify the catch-all trigger so it more sharply excludes cases a narrower skill already handles.

Dimension	Reasoning	Score
Specificity	It names the domain ('cross-substrate architectural ambiguity') and the action ('umbrella router for navigating'), but the phrasing is abstract and does not list concrete routing actions. Not a 3 because it lacks multiple specific concrete actions; not a 1 because it does name a domain and an action.	2 / 3
Completeness	It answers both 'what' ('umbrella router for navigating broad, cross-substrate architectural ambiguity') and 'when' with an explicit 'Use when no narrower pre-flight clearly applies, or when work spans multiple trigger families' clause. Not below 3 because both what and when are explicit; cannot exceed the scale.	3 / 3
Trigger Term Quality	It offers some natural terms ('new subsystems, protocols, MCP tools') and an explicit trigger clause, but leans on jargon like 'cross-substrate', 'trigger families', and 'pre-flight' that users would rarely say verbatim. Not a 3 due to missing common natural-language variations; not a 1 because several terms are plausible user language.	2 / 3
Distinctiveness Conflict Risk	The umbrella framing ('no narrower pre-flight clearly applies') is a catch-all that intentionally overlaps the very narrower skills it routes to, creating moderate conflict risk. Not a 1 because the cross-substrate scope is a real niche; not a 3 because the broad trigger can fire for skills it should defer to.	2 / 3
	Total	9 / 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/architecture-pre-flight/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.