Skip to content
Back to skills

Rumo Imagegen

ASecurity

Generate and save one raster image through a user-configured OpenAI-compatible image endpoint. Use only when the user explicitly selects this configured service; do not use for diagrams, screenshots, or when a first-party image tool is more appropriate.

  • 3 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added October 19, 2026
developmentshellbashnodeapi

Works with

  • api

Security analysis

A100/100

Pro scans all 4 files and shows the line behind each finding

Scanned October 19, 2026

npx -y skills add rumoii/rumo-engineering-skills --skill rumo-imagegen --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Rumo Imagegen?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Rumo Imagegen
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rumoii-rumo-imagegen/badge)](https://www.skillsdirectory.com/skills/rumoii-rumo-imagegen)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: rumo-imagegen
description: Generate and save one raster image through a user-configured OpenAI-compatible image endpoint. Use only when the user explicitly selects this configured service; do not use for diagrams, screenshots, or when a first-party image tool is more appropriate.
disable-model-invocation: true
---

# Image Generation

Requires Node.js 18 or later and these current-process variables:

- `RUMO_IMAGE_ENDPOINT`: complete image-generation endpoint.
- `RUMO_IMAGE_API_KEY`: bearer token.

Optional defaults are `RUMO_IMAGE_MODEL`, `RUMO_IMAGE_SIZE`, and `RUMO_IMAGE_QUALITY`. Project-specific endpoint and model guidance may come from `rumo-project-profile`.

Resolve an exact output path, create a private temporary UTF-8 prompt file, and run `scripts/generate.mjs`. The script never overwrites an existing output and never prints the API key.

If the configured endpoint uses plain HTTP, explain that the token and prompt are unencrypted in transit and obtain explicit acceptance before the API call. Use `--allow-insecure-http` only after that acceptance.

```powershell
node <skill-dir>\scripts\generate.mjs --prompt-file <prompt-file> --output <absolute-output.png>
```

```bash
node <skill-dir>/scripts/generate.mjs --prompt-file <prompt-file> --output <absolute-output.png>
```

A direct request authorizes one generation. Do not automatically retry, create variants, or switch providers. Verify the output signature and file size, inspect the image when useful, delete the temporary prompt file, and distinguish file creation from visual acceptance.

Files in this skill

  • SKILL.md1.5 KB
  • agents/openai.yaml326 B
  • scripts/generate.mjs9.6 KB
  • scripts/generate.test.mjs4.3 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.