Poster generator
Ready-to-install agent skills, each wrapping a nanoodle visual AI workflow — poster, photo restyle, jingle, narrated poem, video teaser
npx -y skills add nanoodlecom/noodle-skills --skill poster-generatorAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 25 days oldThe repository was created 25 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 0 stars0 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
Generate a poster image from a short idea — an LLM expands the idea into a detailed image prompt, then an image model renders it. Use when the user asks for a poster, illustration, or promo image from a one-line concept.
SKILL.md
2.4 KB, as published. Nobody here has run it
Poster generator
Runs the bundled nanoodle workflow workflows/poster.noodle-graph.json against the NanoGPT
API: a text input (Idea) feeds an LLM that writes a vivid image prompt, which feeds an
image model that renders the poster (Poster). Requires Node.js >= 20 and the nanoodle
npm package (npx nanoodle fetches it).
API key
The run needs a NanoGPT API key. Use whichever is available:
NANOGPT_API_KEYalready set in the environment — prefer this; no extra flags.- A
.envfile containingNANOGPT_API_KEY=...— pass--env-file <path>only when the key is not already in the environment. (With this CLI,--env-fileoverrides ambientNANOGPT_API_KEY.)
Never print the key.
Run
From this skill's directory (or prefix paths if running from elsewhere). Replace the Idea
value with the user's concept:
npx nanoodle run workflows/poster.noodle-graph.json \
--input "Idea=a cozy ramen shop on a rainy night" \
--out ./poster-out
Add --env-file .env only when the key is not already exported. For a machine-readable
payload (paths, cost, balance), add --json.
Optional style override (the workflow also exposes this input):
--input "System prompt=<custom image-prompt writer instructions>"
Inspect the interface anytime with:
npx nanoodle inspect workflows/poster.noodle-graph.json
Inputs
| Key | Required | What to pass |
|---|---|---|
Idea | yes | The poster concept, one line is enough |
System prompt | no | Custom instructions for the prompt-writing LLM |
Outputs
- Media is saved under
--outasPoster.<ext>where<ext>follows the image MIME (oftenjpgorpng). Use the path the CLI prints on thePoster:line — do not hard-code.png. - With
--json, the path is inoutputs.Poster(and cost/balance in the same object). - The CLI also prints total cost (and remaining balance when the API reports it) to stderr.
Cost
Each run costs about $0.04 in NanoGPT credit (the image step, nano-banana-2-lite,
dominates; the LLM prompt-writing step is a fraction of a cent). Runs spend real credit —
tell the user before running repeatedly.