All skills & plugins / Scientific Agent Skills (K-Dense)

generate-image

Generates or edits 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.

Type: Skill by K-Dense Inc.
Catalog: Scientific Agent Skills (K-Dense)
Source: K-Dense-AI/scientific-agent-skills/skills/generate-image (3 files scanned)
Install and details: Agent Skills Index entry
License: MIT (SKILL.md frontmatter)
Signals: Pre-approved shellBundled scriptsNetwork calls in codeReads credentials

Pre-approved tools

Shell (any command). Tools listed in allowed-tools (or an agent's tools) can be used without a permission prompt while the skill is active, depending on your agent and settings.

Kind	Tools
read/search	`Read`
write/edit files	`WriteEdit`
shell, any command	`Bash`

Declared in generate-image/SKILL.md.

Hooks

No hooks.

MCP servers and apps

None.

Bundled code

1 code file (Python):

generate-image/scripts/generate_image.py

Network calls

1 file with a network call pattern. First match per file:

skills/generate-image/scripts/generate_image.py:26
```
import http.client
```

Starts other programs

No subprocess, exec or eval pattern found.

Credentials referenced

OPENROUTER_API_KEY

Static scan of commit 5f2bc03 on 2026-10-27. Signals are patterns found in the files, not a verdict: a network call can be the whole point of a skill. Read the linked lines before you decide. How the scan works.