generate-image

Generate or edit images with AI models through the OpenRouter Image API (Gemini, Seedream, Recraft, GPT-Image, Riverflow). Use for photos, illustrations, artwork, concept art, visual assets, logos, and image editing or compositing from reference images. For flowcharts, circuits, pathways, and other technical diagrams, use the scientific-schematics skill instead.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

82%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, competence-assuming reference with copy-paste commands, real validation checkpoints, and a well-signaled catalogue reference. The main gaps are a few trimmable inline sections and validation steps that are present but not consolidated into one explicit sequenced workflow.

Suggestions

Consolidate the scattered validation guidance (preflight, --dry-run, 'look at the image', refine-via-reference) into one short sequenced workflow block so the validate→check→iterate loop is explicit.

Trim or move the streaming-events paragraph since the bundled script does not use streaming, and consider relocating the full API-shape curl/response/cost detail to references/ to slim the SKILL.md overview.

Add a couple of natural trigger synonyms (render, drawing, AI art) to the description's 'Use for' list to round out keyword coverage.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence — no basic-concept padding — but a few sections (full response JSON, streaming events the bundled script does not use) could be trimmed, fitting 'efficient; minor instances of over-explanation'.	4 / 5
Actionability	Commands are copy-paste-ready throughout, and the worked-examples block covers generate, edit, composite, vector, transparent, multi-image, reproducible, and dry-run cases, matching the fully-executable top anchor.	5 / 5
Workflow Clarity	Validation checkpoints exist (preflight check, --dry-run, "Then look at the image", refine-via-reference loop) and a billed operation is guarded, but they are scattered across sections rather than presented as one crisp sequenced procedure with explicit fix/retry framing.	4 / 5
Progressive Disclosure	A single clearly-signaled one-level-deep reference ("references/models.md carries the full catalogue") — verified to exist — keeps structure good, but a fair amount of detailed inline material (full curl + response JSON, streaming, cost breakdowns) could be split out, leaving minor organization gaps.	4 / 5
	Total	17 / 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 strong, third-person description that states concrete capabilities, gives explicit "Use for" trigger guidance, and disambiguates from the adjacent scientific-schematics skill. Keyword coverage is broad though a few natural synonyms are missing.

Dimension	Reasoning	Score
Specificity	"Generate or edit images" and "image editing or compositing from reference images" name the domain plus several concrete actions, with only minor coverage gaps, matching the 'several specific actions' anchor rather than the comprehensive 5.	4 / 5
Completeness	It explicitly answers both what ("Generate or edit images with AI models through the OpenRouter Image API") and when ("Use for photos, illustrations…") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	"photos, illustrations, artwork, concept art, visual assets, logos, and image editing or compositing" gives strong natural-term coverage, but a few plausible synonyms (render, drawing, AI art) are absent, fitting 'good keyword coverage; a few natural terms missing'.	4 / 5
Distinctiveness Conflict Risk	A clear AI-image-generation niche with an explicit boundary redirect ("For flowcharts, circuits, pathways… use the scientific-schematics skill instead") keeps conflict risk minimal.	5 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/generate-image/SKILL.md
Commit: b2a92ba

Reviewed: 3 days 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.