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", "icone", "mascote", "illustration", "remover fundo", "transparent icon", "tauri icons".
72
67%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/17-image-generator/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly defines its scope (visual asset generation and adaptation), provides explicit trigger guidance with a comprehensive list of natural keywords in both Portuguese and English, and answers both what the skill does and when to use it. The description is concise yet thorough, with distinct triggers that minimize conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: generation and adaptation of visual assets, hero image, background, illustration, icon, favicon, mascot, and derivation of existing images. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (generation and adaptation of visual assets including hero images, backgrounds, icons, favicons, mascots) and 'when' (explicit 'Use quando' clause and a dedicated 'Trigger em' list with specific trigger terms). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms in both Portuguese and English: 'gerar imagem', 'criar imagem', 'hero image', 'background image', 'favicon', 'icone', 'mascote', 'illustration', 'remover fundo', 'transparent icon', 'tauri icons'. These are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly occupies a distinct niche around visual asset generation for apps, with specific triggers like 'hero image', 'favicon', 'mascote', 'tauri icons' that are unlikely to conflict with other skills. The scope is well-bounded to visual assets. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a comprehensive conceptual framework for image asset generation but lacks concrete actionability — there are no executable commands, code snippets, API calls, or specific tool references. The workflow is reasonably sequenced but missing validation/feedback loops after asset generation. The content is moderately concise but has redundancy across sections and includes some generic advice Claude already knows.
Suggestions
Add concrete, executable examples for at least the most common workflows (e.g., specific commands for favicon generation, Tauri icon packaging, or image processing with a real tool/library)
Add explicit validation steps after asset generation — e.g., verify file exists, check dimensions, validate favicon format, preview in context — and include a retry loop if validation fails
Remove or consolidate redundant sections: 'Regra Mais Importante' repeats what 'Quando Nao Usar' and 'Analise de Contexto Visual' already cover; 'Codigo Limpo' is generic advice that adds no skill-specific value
Specify concrete model names or at least categories (e.g., DALL-E, Stable Diffusion, specific API endpoints) instead of abstract descriptions like 'modelo mais barato e rapido'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably organized but includes several sections that are somewhat redundant or could be tightened. The 'Quando Usar/Nao Usar', 'Entradas Esperadas/Saidas Esperadas', 'Responsabilidades', and 'Regra Mais Importante' sections overlap significantly. The 'Codigo Limpo' section at the end is generic advice Claude already knows. However, the tables and checklists are efficient. | 2 / 3 |
Actionability | The skill is almost entirely abstract guidance with no concrete code, commands, or executable examples. Phrases like 'seguir o fluxo dele', 'adaptar ao mecanismo disponivel', and 'modelo mais barato e rapido' give no specific tool names, commands, API calls, or code snippets. There's nothing copy-paste ready or directly executable. | 1 / 3 |
Workflow Clarity | There is a clear sequence in 'Analise de Contexto Visual' (5 ordered steps) and a checklist before generation, but there are no explicit validation checkpoints or feedback loops. The 'Execucao' section is vague ('seguir o fluxo dele') with no concrete validation step after generation. For an operation producing visual assets, there's no verify-and-retry loop. | 2 / 3 |
Progressive Disclosure | The skill references multiple external policy files (GLOBAL.md, policies/execution.md, etc.) and other skills, which is good progressive disclosure. However, the main file itself is quite long with content that could be split out (e.g., the asset types table, model selection guidance, prompt rules could be separate references). The references to other skills are well-signaled but the body content is somewhat monolithic. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 |
Total | 9 / 11 Passed | |
- Repository
- felvieira/claude-skills-fv
- Commit
e9f6648
- Reviewed
Table of Contents
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.