image-generator

Skill para geracao e adaptacao de assets visuais. Use quando o projeto precisar de hero image, background, ilustracao, icone, favicon, mascote ou derivacao de imagem existente sem destoar do app. Trigger em: "gerar imagem", "criar imagem", "hero image", "background image", "favicon png", "icone", "mascote", "illustration", "remover fundo", "transparent icon", "tauri icons".

Quality

85%

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

75%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.

Highly actionable content with concrete commands, a priced model table, and an explicit validation checkpoint with a feedback loop. Its main weaknesses are redundancy of the context-analysis message across sections and inlining of reference-grade model details that the referenced docs file already covers.

Suggestions

Consolidate the repeated 'analyze existing visual context first' guidance into one section (Regra Mais Importante or Analise de Contexto Visual) and have other sections reference it instead of restating it.

Move the full fal.ai model pricing table and decision tree into docs/skill-guides/image-generator-models.md, keeping only the canonical default-rule table and a pointer inline in SKILL.md.

Add a single unified numbered execution workflow (analyze context → choose t2i/i2i → generate → visual checkpoint → save to output path) so the end-to-end sequence is readable in one place rather than assembled across sections.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and information-dense, but the "analyze existing visual context first" message is restated across Regra Mais Importante, Analise de Contexto Visual, Checklist Antes de Gerar, Regras de Prompt, and Evidencia de Conclusao — more than minor redundancy that could be tightened.	3 / 5
Actionability	Provides copy-paste-ready `node scripts/generate-image.mjs` commands with concrete flags (--prompt, --ref, --model, --aspect, --out, --list), env vars with fallbacks, a priced model table with endpoints, a decision tree, and a multi-stage pipeline covering the common cases.	5 / 5
Workflow Clarity	Clear phased sequence with ordered analysis steps, a pre-generation checklist, a recommended pipeline, and an explicit visual-validation Checkpoint with a feedback loop (adjust prompt and regenerate rather than retry blindly). Held at 4 because the end-to-end workflow is distributed across several sections instead of one unified sequenced procedure.	4 / 5
Progressive Disclosure	Well-sectioned body acting as an overview with clearly signaled one-level-deep references (docs/skill-guides/image-generator-models.md "carregado sob demanda", models/image-models.json as "Fonte única"). Held at 4 because the model pricing table and decision tree are inlined reference-grade content that could be delegated to the referenced detail file.	4 / 5
	Total	16 / 20 Passed

Description

96%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 strong, bilingual description that explicitly answers what and when with comprehensive, natural trigger phrases and concrete asset types. Its only weakness is minor overlap with a sibling favicon/social-card skill that the description does not itself disambiguate.

Dimension	Reasoning	Score
Specificity	Names concrete actions ("geracao e adaptacao de assets visuais", "derivacao de imagem existente", "remover fundo") and comprehensively enumerates asset types (hero, background, ilustracao, icone, favicon, mascote), matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly states both what (generation and adaptation of visual assets, enumerated types) and when ("Use quando o projeto precisar de..." plus concrete "Trigger em:" phrases), matching the anchor that requires both with concrete triggers.	5 / 5
Trigger Term Quality	The "Trigger em:" list covers natural bilingual phrases with synonyms ("gerar imagem"/"criar imagem") and file/format terms ("favicon png", "tauri icons", "transparent icon"), matching the comprehensive-coverage-with-synonyms-and-extensions anchor.	5 / 5
Distinctiveness Conflict Risk	Clear visual-asset niche with distinct triggers, but "favicon" / "tauri icons" overlap with the sibling Web Asset Generator skill (skill 36) whose disambiguation lives only in the body, not the description — minor overlap risk rather than full distinctiveness.	4 / 5
	Total	19 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
metadata_version	'metadata.version' is missing	Warning
relative_links	Relative link issues: 1 suspicious	Warning
referenced_paths_exist	Referenced path issues: 8 missing	Warning

	Total	12 / 16 Passed

Repository: felvieira/claude-skills-fv
Path: skills/17-image-generator/SKILL.md
Commit: 74aa7c1

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.