An excellent, dense procedural skill: a complete numbered workflow with before/after validation, exact commands and dependency values, and a pitfalls section that preempts the common failure modes. The only noticeable gap is that the BUILD.gn layout is specified in prose rather than as a single complete example block.

Suggestions

Include one complete, copy-paste-ready BUILD.gn example for a hypothetical model (e.g., front_end/models/example_model/BUILD.gn with all three targets filled in) instead of describing the targets in prose.

Add the specific grep command for updating consumers (e.g., how to find all importers of the old barrel path) to make section 4 as executable as sections 0 and 5.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: every line is a rule, an exact command, or a pitfall, with no explanations of concepts Claude already knows (no 'what BUILD.gn is', no library overviews). It matches the 'lean and efficient; every token earns its place' anchor and is above level 4, which would still contain minor trimmable over-explanation.	5 / 5
Actionability	Guidance is mostly executable: exact commands ('npm run test -- front_end/<old_location>', 'autoninja -C out/Default', 'npm run lint'), exact BUILD.gn field values ('ts_deps = [ ":bundle" ]', 'entrypoint = "<model_name>.ts"'), and a concrete import statement. The minor gap keeping it below level 5 is that the central artifact — the BUILD.gn file — is described in prose target-by-target rather than shown as one complete copy-paste-ready block. It is above level 3 because nothing is pseudocode and all field names and values are exact.	4 / 5
Workflow Clarity	A clear 0→5 sequence with explicit validation checkpoints: baseline tests before touching anything ('Run existing tests... to ensure they pass before you touch anything'), and a final verification checklist covering build, lint, new tests, and regression tests on the old location. This matches the 'clear sequence with explicit validation steps' anchor, and the pitfalls section supplies the error-recovery knowledge, so it is above level 4's 'minor validation gaps'.	5 / 5
Progressive Disclosure	This is a ~50-line single-file skill with no bundle files, well organized into numbered sections (Preparation, File Structure, Build Configuration, Global Registration, Refactoring, Verification) plus a pitfalls section. Per the scoring notes, a short skill with no need for external references and well-organized sections scores 5; there is nothing that belongs in a separate file and no navigation debt.	5 / 5
	Total	19 / 20 Passed

Description

70%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 tight, third-person description that names concrete actions and highly specific artifacts, giving it strong distinctiveness and good trigger terms. Its main weakness is the complete absence of a 'Use when...' clause, which caps completeness at 3 because there is no explicit guidance on when the skill should be invoked.

Suggestions

Append an explicit trigger clause, e.g.: 'Use when creating a new model, migrating an existing model into front_end/models/, or when BUILD.gn or devtools_grd_files.gni need updating for a model.'

Add natural synonyms a developer might use when asking for this (e.g., 'moving a model', 'new module', 'barrel file', 'registering a module') to broaden trigger-term coverage.

Optionally enumerate one or two more of the covered sub-tasks (updating consumer imports, registering test targets) so the 'what' is more comprehensive.

Dimension	Reasoning	Score
Specificity	The description lists several specific actions ('creating, migrating, and registering models') and names concrete artifacts ('BUILD.gn', 'devtools_grd_files.gni', 'entrypoints'), but stops short of comprehensive coverage of what the procedure involves (e.g., build configuration, import refactoring, test registration), matching the 'several specific actions; minor gaps' anchor. It is above level 3 (which covers only 1-2 actions) and below level 5 (which requires comprehensively enumerated actions).	4 / 5
Completeness	It has a clear 'what' ('Guidelines for creating, migrating, and registering models in front_end/models/'), but there is no 'Use when...' clause or any equivalent explicit trigger guidance; use is only weakly implied by the domain. Per the judging guidelines, a missing 'Use when' clause caps completeness at 3, which also matches the 'clear what, when missing or only weakly implied' anchor.	3 / 5
Trigger Term Quality	Good keyword coverage with terms a DevTools contributor would naturally say ('models', 'migrating', 'BUILD.gn', 'entrypoints', 'front_end/models/'). A few natural variations are missing (e.g., 'moving a model', 'new module', 'barrel file'), so it fits the 'good coverage; a few natural terms missing' anchor rather than level 5's comprehensive synonym coverage, and is clearly above level 3's partial coverage.	4 / 5
Distinctiveness Conflict Risk	The description carves out a clear niche with repo-specific triggers ('front_end/models/', 'BUILD.gn', 'devtools_grd_files.gni') that would not naturally collide with any other skill, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor. It is well above level 4's 'minor overlap risk with closely related skills'.	5 / 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: ChromeDevTools/devtools-frontend
Path: .agents/skills/devtools-model-management/SKILL.md
Commit: de3f9ca

Reviewed: 9 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.