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

81%

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

75%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 highly actionable, well-structured skill body built around one executable script, with clear prerequisites and parameter documentation. Its main weakness is redundancy across the Quick Start, Common Usage Patterns, and Example Use Cases sections that inflates token cost without adding new capability.

Suggestions

Collapse the 'Basic generation' and duplicate single-command examples in 'Common Usage Patterns' since they restate Quick Start; keep only the patterns that introduce a new flag combination.

Move the three 'Example Use Cases' categories into a separate examples file referenced from the body, or trim to one representative example per category, to reduce token weight.

Make the error-handling feedback loop explicit (e.g., 'If the API returns a 401, re-check OPENROUTER_API_KEY and retry') rather than the generic 'read the error message and address the issue'.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but 'Basic generation' and several patterns in 'Common Usage Patterns' repeat the Quick Start examples, and the 'Example Use Cases' section re-demonstrates the same flag combinations, which could be tightened.	3 / 5
Actionability	Fully executable, copy-paste-ready bash commands cover generate, edit, model selection, custom output, and multiple images, and the 'Script Parameters' section documents every flag concretely.	5 / 5
Workflow Clarity	The prerequisite (API key resolution order) and core action (run the script) are sequenced clearly with an error-handling retry hint, but validation feedback is implicit rather than an explicit checkpoint; this single-action skill is otherwise unambiguous.	4 / 5
Progressive Disclosure	Well-organized into clear sections (Quick Start, API Key Setup, Model Selection, Parameters, etc.) with the single bundle script (scripts/generate_image.py) referenced cleanly; the long 'Example Use Cases' block could arguably live in a separate file, which is the minor gap.	4 / 5
	Total	16 / 20 Passed

Description

87%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 well-crafted description that clearly states capability, gives concrete trigger terms, and explicitly disambiguates from the sibling scientific-schematics skill. The only weakness is a narrow action vocabulary (generate/edit) amid otherwise comprehensive category coverage.

Dimension	Reasoning	Score
Specificity	Names the domain plus two concrete actions ('Generate or edit images') and enumerates many output categories (photos, illustrations, artwork, visual assets, concept art), but the action vocabulary itself is limited to generate/edit rather than a broader action list.	4 / 5
Completeness	Explicitly answers both 'what' ('Generate or edit images using AI models') and 'when' ('Use for general-purpose image generation including...') with concrete trigger phrases and an explicit exclusion boundary.	5 / 5
Trigger Term Quality	Strong natural-term coverage ('photos, illustrations, artwork, visual assets, concept art, technical diagram, schematic, flowcharts, circuits, pathways') that users would actually say, though a few common variants ('draw', 'create a picture') are absent.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche (general-purpose images) and adds explicit conflict guidance ('use the scientific-schematics skill instead' for flowcharts/circuits/pathways), minimizing wrong-skill triggering.	5 / 5
	Total	18 / 20 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: 3a6c3a9

Reviewed: 1 day 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.