generate-image
Generate or edit images using AI models (FLUX, Nano Banana 2). Use for general-purpose image generation including photos, illustrations, artwork, visual assets, concept art, and any image that is not a technical diagram or schematic. For flowcharts, circuits, pathways, and technical diagrams, use the scientific-schematics skill instead.
79
75%
Does it follow best practices?
Impact
82%
1.78xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/generate-image/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 an excellent skill description that covers all key dimensions well. It specifies concrete actions, names the underlying models, provides rich trigger terms across multiple image types, and explicitly delineates its boundary with a related skill. The negative guidance ('use the scientific-schematics skill instead') is a particularly strong feature for disambiguation.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists concrete actions ('Generate or edit images'), names specific AI models (FLUX, Nano Banana 2), and enumerates multiple output types (photos, illustrations, artwork, visual assets, concept art). | 3 / 3 |
Completeness | Clearly answers 'what' (generate or edit images using AI models) and 'when' (use for general-purpose image generation including specific types). Also includes explicit negative guidance ('For flowcharts, circuits... use the scientific-schematics skill instead'), which strengthens the 'when' clause. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'image generation', 'photos', 'illustrations', 'artwork', 'visual assets', 'concept art', 'edit images'. Good coverage of common variations. | 3 / 3 |
Distinctiveness Conflict Risk | Explicitly distinguishes itself from the scientific-schematics skill by naming the boundary ('not a technical diagram or schematic') and listing specific examples of what belongs elsewhere (flowcharts, circuits, pathways). This clear delineation minimizes conflict risk. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides excellent actionability with concrete, executable commands and clear parameter documentation. However, it is significantly bloated with redundant examples, unnecessary explanations (editing tips Claude already knows, verbose use case sections that repeat the same pattern), and sections that could be trimmed or moved to separate files. The workflow is simple enough but lacks explicit validation checkpoints after image generation.
Suggestions
Remove the 'Example Use Cases' section entirely or collapse it into 1-2 examples — the 'Common Usage Patterns' section already demonstrates all the functionality with clearer examples.
Remove the 'Image Editing Tips' section — Claude already understands prompt engineering principles like being specific and referencing elements.
Trim the 'Notes' section to only non-obvious information (e.g., supported input formats); remove explanations of base64, generation time, and other concepts Claude already knows.
Add a brief validation step after generation: e.g., 'Verify the output file exists and confirm to the user with the file path and size.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Significant verbosity throughout. The 'When to Use This Skill' section repeats information from the description. The 'Example Use Cases' section provides many redundant examples that don't add new information beyond what 'Common Usage Patterns' already covers. The 'Error Handling' and 'Notes' sections explain things Claude already knows (e.g., what base64 is, that generation time varies). The 'Image Editing Tips' section contains generic advice Claude would already understand. | 1 / 3 |
Actionability | Provides fully executable bash commands with concrete examples covering generation, editing, model selection, and custom output paths. All commands are copy-paste ready with clear parameter documentation. | 3 / 3 |
Workflow Clarity | The API key setup section provides a clear sequence for checking configuration, and the basic workflow (run script, check output) is straightforward. However, there's no explicit validation step after image generation (e.g., verify the output file exists and is valid), and the error handling section just says 'read the error message' without a proper feedback loop. | 2 / 3 |
Progressive Disclosure | Content is reasonably structured with clear sections, but it's monolithic — the extensive example use cases, editing tips, and notes sections could be in a separate reference file. The cross-references to other skills at the end are helpful but the main content is too long for what should be a quick-reference skill. | 2 / 3 |
Total | 8 / 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 |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
25e1c0f
- 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.