ai-studio-image
Geracao de imagens humanizadas via Google AI Studio (Gemini). Fotos realistas estilo influencer ou educacional com iluminacao natural e imperfeicoes sutis.
46
33%
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/ai-studio-image/SKILL.mdQuality
Discovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description communicates a specific visual style and tool (Gemini via Google AI Studio) for generating realistic humanized images, which gives it moderate distinctiveness. However, it lacks an explicit 'Use when...' clause, reducing its effectiveness as a skill selector. The description reads more like a feature summary than actionable selection guidance.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks for realistic humanized photos, influencer-style images, or educational visuals generated via AI.'
Include natural trigger terms users might say, such as 'generate photo', 'create realistic image', 'AI-generated portrait', 'Gemini image', both in Portuguese and English if applicable.
List more concrete actions beyond style description, e.g., 'Generates portrait photos, creates educational scene images, produces social media content visuals.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (image generation) and some specific qualities (realistic photos, influencer/educational style, natural lighting, subtle imperfections), but doesn't list multiple distinct concrete actions—it's more of a style description than a list of capabilities. | 2 / 3 |
Completeness | Describes what the skill does (generates humanized images via Gemini) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and since the 'when' is entirely absent and the 'what' is only moderate, this scores at 1. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'imagens humanizadas', 'Google AI Studio', 'Gemini', 'fotos realistas', 'influencer', 'educacional', but misses common user variations (e.g., 'generate image', 'photo generation', 'AI image', 'realistic photo'). The terms are somewhat niche and in Portuguese only. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Google AI Studio (Gemini)' and the specific style (humanized, influencer, educational) provides some distinctiveness, but it could overlap with other image generation skills. The niche is somewhat defined but not sharply delineated. | 2 / 3 |
Total | 7 / 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.
The skill provides a structured workflow with useful tables and concrete CLI commands, but is severely bloated with unnecessary explanations, generic boilerplate sections, and detailed reference material that should be in separate files. The hardcoded user-specific paths reduce reusability, and the lack of validation checkpoints in a multi-step generation workflow is a notable gap. The 'humanization layers' concept is interesting but over-explained for Claude's capabilities.
Suggestions
Remove all generic boilerplate sections (Best Practices, Common Pitfalls, Limitations, Related Skills) that contain no domain-specific information and waste tokens.
Move the template tables, model comparison table, humanization levels, and time-of-day options into separate reference files, keeping only a brief summary with links in the main skill.
Replace hardcoded paths (C:\Users\renat\...) with relative paths or a variable placeholder to improve portability and reduce clutter.
Add explicit validation steps: verify API key works before generating, check output file exists after generation, and provide concrete commands for the iteration step (Passo 5) instead of vague bullet points.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with significant padding. The 'How It Works' section explains obvious concepts about photography that Claude already knows. The 5 'humanization layers' describe basic photography concepts at length. Boilerplate sections like 'Best Practices', 'Common Pitfalls', 'Limitations', and 'Related Skills' are generic filler with no domain-specific value. The 'When to Use' / 'Do Not Use' sections are redundant with the overview. Hardcoded Windows paths (C:\Users\renat\) add clutter. | 1 / 3 |
Actionability | Provides concrete CLI commands with specific flags and parameters, which is good. However, the commands reference scripts (generate.py, prompt_engine.py, templates.py) whose existence and behavior we must take on faith — there's no inline code showing what these scripts do. The prompt transformation (Passo 3) describes conceptual layers rather than showing executable prompt engineering. The hardcoded user-specific paths reduce portability. | 2 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced and well-structured with tables for modes, formats, and models. However, there are no validation checkpoints — no step to verify the API key works, no validation that the generated image meets quality standards before presenting to the user, and no error-handling feedback loop (just a troubleshooting table at the end). The iteration step (Passo 5) is vague with no concrete commands. | 2 / 3 |
Progressive Disclosure | References to external files exist at the bottom (references/setup-guide.md, prompt-engineering.md, api-reference.md), which is good. However, the main file is monolithic — the extensive template tables, humanization levels, time-of-day options, and model comparison tables could all be in separate reference files. The content that is inline is far too detailed for an overview skill file. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- sickn33/antigravity-awesome-skills
- Commit
1a9f5ac
- 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.