generate-image

Generate or edit images using AI models (FLUX, Gemini). Use for general-purpose image generation including photos, illustrations, artwork, visual assets, concept art, and any image that isn't a technical diagram or schematic. For flowcharts, circuits, pathways, and technical diagrams, use the scientific-schematics skill instead.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable commands and a clear single-script workflow, but it is somewhat verbose: pattern examples duplicate Quick Start, several example use cases are near-redundant, and a time-sensitive model-retirement note sits inline rather than in a deprecated section.

Suggestions

Collapse 'Common Usage Patterns' into the Quick Start block since the basic generation, model, output, and edit examples are already shown there, removing the duplication.

Trim 'Example Use Cases' to one representative example per category, or move the full set into a separate references file linked from the body.

Move the retired 'google/gemini-3-pro-image-preview' slug (retires 2026-06-25, now past) into a clearly labeled 'Deprecated models' note or remove it to keep time-sensitive information isolated.

Dimension	Reasoning	Score
Conciseness	The 'Common Usage Patterns' section repeats the Quick Start examples and 'Example Use Cases' pads several near-identical prompt variations; an inline note that a preview slug 'retires 2026-06-25' (already past) is time-sensitive content not isolated in a deprecated section. This is mostly efficient but could be tightened, matching anchor 2 rather than the lean level 3.	2 / 3
Actionability	Every usage pattern is a copy-paste-ready executable bash command invoking scripts/generate_image.py, and a complete parameter list (prompt, --input, --model, --output, --api-key) is provided, matching the fully-executable anchor.	3 / 3
Workflow Clarity	This is a simple single-script skill whose single action is unambiguous, and the API-key resolution order (flag -> env -> .env -> synced env) is explicitly sequenced with a retry-on-error feedback loop, so the simple-skill exception lets it reach anchor 3.	3 / 3
Progressive Disclosure	Sections are well-organized and the script reference is one level deep, but the file exceeds 50 lines with all content inline — the verbose 'Example Use Cases' and repeated pattern blocks could be split out, matching the some-structure-but-could-be-better-organized anchor rather than the clean one-level-deep level 3.	2 / 3
	Total	10 / 12 Passed

Description

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.

The description is exemplary: it states concrete capabilities, uses natural trigger terms, answers both what and when explicitly, and proactively distinguishes itself from the scientific-schematics skill. Third-person voice is used correctly with no fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Generate or edit images') alongside named models (FLUX, Gemini) and specific output categories, matching the multiple-specific-actions anchor rather than the domain-only level below.	3 / 3
Completeness	Explicitly answers what ('Generate or edit images using AI models') and when ('Use for general-purpose image generation including...'), with an explicit trigger clause, matching the both-what-and-when anchor.	3 / 3
Trigger Term Quality	Covers natural user terms — 'photos, illustrations, artwork, visual assets, concept art' — that a user would actually say, satisfying the good-coverage anchor rather than partial coverage at level 2.	3 / 3
Distinctiveness Conflict Risk	Carves a clear niche and actively routes conflicting cases ('For flowcharts, circuits, pathways... use the scientific-schematics skill instead'), making wrong-skill triggering unlikely and matching the distinct-triggers anchor.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/llm-tools/generate-image/SKILL.md
Commit: 52845c3

Reviewed: about 10 hours ago

Table of Contents

Discovery Implementation Validation

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.