asset-librarian

Skill para inventariar e organizar imagens, icones, logos, fontes, tokens visuais e referencias graficas do projeto. Use quando precisar mapear assets existentes, evitar inconsistencias visuais e apoiar UI/UX, Frontend e Image Generator. Trigger em: "asset librarian", "inventariar assets", "inventario de assets", "mapear assets", "organizar assets", "design tokens", "biblioteca de assets", "auditar assets visuais", "catalogar logos", "incoerencia visual".

Quality

91%

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

82%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.

A highly actionable, token-efficient body with executable commands and a concrete template, weakened only by a missing validation checkpoint before its destructive removal suggestions and unverified external file references.

Suggestions

Add an explicit validation step before removal actions, e.g. confirm a candidate-obsolete asset is unreferenced via grep and surface it for user approval before deleting (workflow_clarity).

Either create the referenced bundle files (templates/asset-inventory.md, the policies/*.md) or remove the references so progressive disclosure is backed by real, one-level-deep material.

Number the core workflow steps (discover assets -> build inventory -> run consistency checks -> list gaps/handoff) so the sequence is explicit rather than implied by section order.

Dimension	Reasoning	Score
Conciseness	Dense and lean throughout — it skips concept explanations Claude already knows and every section (commands, template, checks, anti-patterns) earns its tokens; no padding despite the breadth of coverage.	3 / 3
Actionability	Provides fully executable bash commands (find/grep with real flags), a copy-paste-ready markdown inventory template, and concrete six-item consistency checks — copy-paste ready and specific.	3 / 3
Workflow Clarity	The discovery/scan sequence is implicit via commands and the "Evidencia de Conclusao" acts as a completion checklist, but the workflow recommends destructive actions ("remover" obsolete assets) without an explicit validate-before-removing checkpoint, capping it at 2 per the batch/destructive guideline.	2 / 3
Progressive Disclosure	It references external files (GLOBAL.md, policies/*.md, templates/asset-inventory.md) and lists a docs output path, but no bundle directories exist in references/scripts/assets and the referenced paths are not present as real files, so navigation is signaled but not verifiable into well-structured one-level-deep material.	2 / 3
	Total	10 / 12 Passed

Description

100%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.

A concise, well-scoped description that states concrete actions, an explicit Use-when clause, and a rich set of natural trigger phrases, clearly distinguishing itself from sibling skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "inventariar e organizar imagens, icones, logos, fontes, tokens visuais e referencias graficas" — matching the multiple-specific-actions anchor.	3 / 3
Completeness	It explicitly states what ("inventariar e organizar..."), when ("Use quando precisar mapear assets existentes, evitar inconsistencias visuais..."), and adds explicit trigger phrases, satisfying both what AND when.	3 / 3
Trigger Term Quality	The "Trigger em:" clause provides ~10 natural phrases users would say ("inventariar assets", "mapear assets", "design tokens", "incoerencia visual"), giving strong coverage of natural terms.	3 / 3
Distinctiveness Conflict Risk	Scoped to visual assets only and distinguished from skill 17 (image generation) and skill 18 (code audit) via the "Trigger em" niche, making conflict unlikely.	3 / 3
	Total	12 / 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: felvieira/claude-skills-fv
Path: skills/19-asset-librarian/SKILL.md
Commit: 030ef22

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.