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

78%

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 ./skills/17-image-generator/SKILL.md

Quality

Content

65%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.

Highly actionable content with concrete commands and clear asset-type delegation, weakened by an inline time-sensitive pricing table that duplicates a referenced guide and a workflow that is fragmented across sections rather than presented as one validated sequence.

Suggestions

Collapse the inline fal.ai pricing table into a short pointer to docs/skill-guides/image-generator-models.md (keep only the default-rule table) to remove time-sensitive duplication and tighten conciseness.

Add a single ordered end-to-end workflow (analyze context -> checklist -> choose t2i/i2i -> prompt -> generate -> verify against Evidencia de Conclusao -> handoff) with an explicit validation checkpoint so the sequence is not implicit.

Move the per-model endpoint/parameter detail fully into the referenced guide and keep SKILL.md as the overview, improving progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept padding, but it carries a full inline model pricing table dated '2026-05' (time-sensitive data) that duplicates content already deferred to docs/skill-guides/image-generator-models.md; the guidelines penalize time-sensitive values that are not isolated in a deprecated/old-patterns section.	2 / 3
Actionability	Provides copy-paste-ready executable commands with real flags ('node scripts/generate-image.mjs --prompt ... --aspect 16:9 --out ...'), concrete override/listing examples, env var names, and explicit output-path rules, fully matching the executable-guidance anchor.	3 / 3
Workflow Clarity	Sequenced fragments exist (5-step context analysis, 3-step pipeline, pre-generation checklist, completion evidence), but the end-to-end workflow is spread across sections with no single ordered sequence or explicit validate-fix-retry checkpoint, leaving the overall order implicit.	2 / 3
Progressive Disclosure	References are one-level-deep and well-signaled (policies, models/image-models.json, docs/skill-guides/image-generator-models.md, templates), but the inline ~40-line model pricing/decision section duplicates a referenced detail file, so content that should be separate remains inline.	2 / 3
	Total	9 / 12 Passed

Description

92%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 strong, well-structured description with explicit capabilities, natural bilingual trigger terms, and clear what/when guidance. Its only weakness is trigger overlap with the dedicated Web Asset Generator skill for favicon and tauri-icon terms.

Suggestions

Drop or qualify 'favicon png' and 'tauri icons' in the trigger list, or note they route to skill 36, to reduce conflict with the dedicated Web Asset Generator skill.

Consider adding a one-line scoping clause ('creative assets only; web-format derivation handled by skill 36') to make the niche boundary explicit in the description itself.

Dimension	Reasoning	Score
Specificity	Names concrete capabilities ('geracao e adaptacao de assets visuais') and enumerates specific asset types (hero image, background, ilustracao, icone, favicon, mascote, derivacao), matching the 'lists multiple specific concrete actions' anchor; the imperative 'Use quando' mirrors accepted good examples rather than a first/second-person pronoun penalty.	3 / 3
Completeness	Clearly answers both 'what' (generate/adapt visual assets and which asset types) and 'when' ('Use quando o projeto precisar de...' plus an explicit trigger list), satisfying the anchor for explicit what-and-when guidance.	3 / 3
Trigger Term Quality	An explicit 'Trigger em:' list provides natural user phrasings in both Portuguese and English ('gerar imagem', 'criar imagem', 'hero image', 'favicon png', 'mascote', 'remover fundo', 'tauri icons'), giving good coverage of terms users would actually say.	3 / 3
Distinctiveness Conflict Risk	The core niche (creative image generation/adaptation) is distinct, but the description lists 'favicon png' and 'tauri icons' as triggers even though the body delegates favicon/social-card/PWA to skill 36, creating overlap with a sibling skill.	2 / 3
	Total	11 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	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: 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.