CtrlK
BlogDocsLog inGet started
Tessl Logo

gemini-3-image-generation

Generate images with Gemini 3 Pro Image (Nano Banana Pro). Covers 4K generation, text rendering, grounded generation with Google Search, conversational editing, and cost optimization. Use when creating images, generating 4K images, editing images conversationally, fact-verified image generation, or image output tasks.

64

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/gemini-3-image-generation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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.

A thorough, actionable skill with executable examples and a clean reference structure, weakened by structural redundancy (Quick Start vs Task 1, multiple overlapping capability lists) and a batch workflow that lacks validation checkpoints.

Suggestions

Remove the Quick Start Python example or Task 1's example so the same generation flow isn't shown twice; consolidate Overview 'Key Capabilities', 'When to Use', 'Best Practices', and the 'Summary' checklist into a single list to cut ~100 lines of repetition.

Add per-item error handling and an output validation checkpoint (verify the saved file is a non-empty image) inside the Batch Image Generation loop, and surface the actual API parameter for aspect ratio/resolution rather than relying on prompt text.

Push the full per-task code blocks into the corresponding reference files, keeping SKILL.md as a concise overview with one representative example plus clearly signaled links.

DimensionReasoningScore

Conciseness

Mostly task-focused and useful, but noticeably redundant: the Quick Start code essentially repeats Task 1, and Overview 'Key Capabilities', 'When to Use', 'Best Practices', and the 'Summary' checklists restate the same points, so it could be tightened considerably.

3 / 5

Actionability

Provides copy-paste-ready Python and Node.js code, error handling with specific exception types, and cost-tracking logic, but Tasks 2 and 6 rely on prompt text rather than showing the actual API mechanism for resolution/aspect-ratio control, leaving minor gaps.

4 / 5

Workflow Clarity

Single-generation tasks are unambiguous, but the Batch Image Generation loop performs no per-item error handling, retry, or output validation, so the batch-operation validation cap holds at 3.

3 / 5

Progressive Disclosure

Well-organized with clearly signaled one-level-deep references to real files (e.g. 'See: references/generation-guide.md') and a consolidated References section, though the 510-line body inlines full code for all seven tasks that partly duplicates the reference guides.

4 / 5

Total

14

/

20

Passed

Description

92%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, specific description that clearly states capabilities and provides explicit trigger guidance with concrete natural phrases. The only gap is a few missing synonyms (e.g. 'text-to-image') that would round out trigger coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — '4K generation, text rendering, grounded generation with Google Search, conversational editing, and cost optimization' — covering the model's capabilities comprehensively, matching the score-5 anchor.

5 / 5

Completeness

Explicitly answers both what ('Generate images... Covers 4K generation, text rendering...') and when ('Use when creating images, generating 4K images...'), with concrete trigger phrases — a clear match for the score-5 anchor.

5 / 5

Trigger Term Quality

Includes natural phrases users say ('creating images', 'generating 4K images', 'editing images conversationally', 'fact-verified image generation', 'image output tasks'), but misses common synonyms like 'text-to-image' or 'AI image generation'; not quite the comprehensive synonym coverage of a 5.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (image output/generation) with distinct triggers (4K, grounded, conversational editing) and is explicitly differentiated from image-input skills, giving minimal conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (512 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
fernandezbaptiste/Skrillz
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.