CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

71

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 high-quality, actionable skill body with executable examples, explicit validation feedback loops, and clean one-level-deep disclosure to real bundle files. The only headroom is trimming duplicated guidance to tighten token efficiency.

Suggestions

Consolidate model capabilities that currently appear in both the 'Choosing a model' table and the 'Parameter support varies by model' list to reduce redundant tokens.

The worked-examples section repeats several flags already covered by the parameter table; consider trimming to one or two canonical examples plus a pointer.

DimensionReasoningScore

Conciseness

Mostly efficient and assumes Claude's competence (no 'what is an API key' filler), but the body is long with duplicated guidance across the model table, parameter list, and worked examples that could be consolidated.

4 / 5

Actionability

Fully executable throughout: copy-paste-ready CLI invocations, a runnable curl example, and a concrete five-part prompt recipe cover the common cases with real flag values.

5 / 5

Workflow Clarity

Clear sequence with explicit validation checkpoints — the free preflight capability check, --dry-run, and the 'look at the image / read the file back' verification step provide feedback loops for the billed operation.

5 / 5

Progressive Disclosure

SKILL.md is a well-signaled overview with the bulk catalogue offloaded to references/models.md (verified present) and logic to scripts/generate_image.py; references are one level deep and both bundle files exist.

5 / 5

Total

19

/

20

Passed

Description

88%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 precise, well-scoped description that answers what and when concretely and carves out a distinct niche with an explicit redirect for technical diagrams. Minor headroom only on synonyms for casual phrasing.

DimensionReasoningScore

Specificity

Names the API and lists multiple concrete actions spanning the domain — 'Generate or edit images', 'image editing or compositing from reference images' — plus the specific model families behind it, giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers both 'what' (generate/edit images through the OpenRouter Image API) and 'when' ('Use for photos, illustrations... image editing or compositing'), and adds a negative trigger steering technical diagrams elsewhere.

5 / 5

Trigger Term Quality

Strong natural terms users would say (photos, illustrations, artwork, concept art, logos, image editing) but the more conversational trigger phrases like 'generate a picture' or 'make an image' are not surfaced as synonyms.

4 / 5

Distinctiveness Conflict Risk

Has a clear niche (AI image generation/editing via OpenRouter) and an explicit boundary clause ('For flowcharts, circuits, pathways... use the scientific-schematics skill instead') that minimizes conflict with adjacent skills.

5 / 5

Total

19

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.