Image gen
Your agents forget every correction. otto makes them stick.
npx -y skills add otto-haus/otto --skill image-genAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 7 stars7 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Image generation via Letta tool — artifacts saved locally; publish/external use is a red zone.
SKILL.md
1.0 KB, as published. Nobody here has run it
Image generation skill (stub)
Triggers
- generate image, image gen, gpt-image, illustration, diagram asset
Constraints
- Gate:
image_genLabs feature must be enabled in Settings → Voice & image (Labs). - Keys: OpenAI Images auth lives in Letta — otto never stores or reads back provider keys.
- Artifacts: Saved under
~/.otto/artifacts/with provenance metadata; not auto-canon. - Red: publish, post, or ship generated images externally without explicit approval.
- Red: treat generated pixels as ratified standards, receipts, or canon without human review.
Autonomy
image_gen.request: yellow — allowed when Labs gate on; write artifact + receiptimage_gen.publish: red — external distribution requires approval
UI truth
Generated images display generated · not ratified until a ratification workflow accepts them.