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.
84
82%
Does it follow best practices?
Impact
82%
1.78xAverage score across 3 eval scenarios
Passed
No known issues
Quality
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 capabilities, includes natural trigger terms across multiple image types, clearly states both what it does and when to use it, and explicitly delineates its boundary with a related skill to prevent conflicts.
| 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' (for general-purpose image generation including specific types). Also includes explicit negative guidance directing to scientific-schematics for diagrams, 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 listing what NOT to use it for (flowcharts, circuits, pathways, technical diagrams). This boundary-setting makes it highly distinctive and reduces conflict risk. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a functional skill with strong actionability — the executable commands and parameter documentation are excellent. However, it suffers from verbosity: the 'When to Use' section duplicates frontmatter, the example use cases are excessive, and several notes/tips sections explain things Claude already knows. Trimming ~40% of the content would improve token efficiency without losing any practical value.
Suggestions
Remove or drastically shorten the 'When to Use This Skill' section since this information belongs in the frontmatter description, not the body.
Consolidate the 'Example Use Cases' section — 2-3 examples max instead of 8, as Claude can generalize from the Quick Start and Common Usage Patterns.
Remove the 'Image Editing Tips' section — advice like 'be specific about what changes you want' is something Claude already knows.
Add a brief validation step after generation (e.g., 'Verify the output file exists and is non-empty before reporting success to the user').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary content like the 'When to Use This Skill' section which repeats the frontmatter description, overly detailed example use cases (scientific documents, presentations, marketing), and tips that Claude would already know (e.g., 'Be specific about what changes you want'). The Notes section contains implementation details Claude doesn't need. However, the core command patterns are reasonably efficient. | 2 / 3 |
Actionability | The skill provides fully executable bash commands with clear parameter documentation. Every usage pattern includes copy-paste ready examples with realistic prompts and flags. The script parameters are well-documented with defaults specified. | 3 / 3 |
Workflow Clarity | The API key setup section provides a clear sequence for checking prerequisites, 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, check file size) and the error handling section just says 'read the error message' without a retry loop or specific recovery steps. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and sections, but it's somewhat monolithic — the extensive example use cases, editing tips, and notes sections could be trimmed or moved to a separate reference file. The 'Integration with Other Skills' section is a nice touch for navigation, but the main file is longer than it needs to be for a skill that wraps a single script. | 2 / 3 |
Total | 9 / 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
b58ad7e
- 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.