Photo restyler
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 photo-restylerAssembled 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
Restyle an existing photo with a plain-English instruction — an image-edit model repaints the picture in the requested style. Use when the user has an image file and wants it restyled, re-lit, aged, cartoonified, or otherwise transformed while keeping the subject.
SKILL.md
2.1 KB, as published. Nobody here has run it
Photo restyler
Runs the bundled nanoodle workflow workflows/photo-restyler.noodle-graph.json against the
NanoGPT API: an image input (Photo) plus a style instruction (Style) feed an image-edit
model that outputs the transformed picture (Restyled). Requires Node.js >= 20 and the
nanoodle npm package (npx nanoodle fetches it).
API key
The run needs a NanoGPT API key. Prefer NANOGPT_API_KEY already in the environment.
Otherwise pass --env-file <path-to-.env> (this CLI: --env-file overrides ambient env).
Never print the key.
Run
From this skill's directory (or prefix paths if running from elsewhere). @path attaches a
local file; replace both values:
npx nanoodle run workflows/photo-restyler.noodle-graph.json \
--input "Photo=@/path/to/photo.jpg" \
--input "Style=make it look like a vintage 1970s film photograph — warm faded colors, soft grain, slight vignette" \
--out ./restyle-out
Add --env-file .env only when the key is not already exported. Add --json for a
structured result (paths, costUsd, remainingBalance).
Inspect the interface anytime with:
npx nanoodle inspect workflows/photo-restyler.noodle-graph.json
Inputs
| Key | Required | What to pass |
|---|---|---|
Photo | yes | @<path> to the user's image file (jpg/png/webp) |
Style | yes | The restyle instruction in plain English |
Outputs
- Media is saved under
--outasRestyled.<ext>— extension follows the image MIME. Use the path the CLI prints on theRestyled:line; do not hard-code.png. - With
--json, the path is inoutputs.Restyled.
Cost
Each run costs about $0.04 in NanoGPT credit (one nano-banana-2-lite edit). Runs
spend real credit — tell the user before running repeatedly.
Gives 0 of the 12 instructions most images graphics skills give
Counted across 371 of the 372 authors here whose files we hold, read 2026-08-06
- create a complete brand world in one imagein 19 of 371, across 5 files
- infer the brand strategy before generatingin 19 of 371, across 5 files
- use a clean presentation gridin 19 of 371, across 5 files
- confirm connection status is activein 19 of 371, across 4 files
- base the visual system on meaningin 17 of 371, across 3 files
- use very little textin 17 of 371, across 3 files
- make every panel feel connectedin 17 of 371, across 3 files
- call RUBE_SEARCH_TOOLS firstin 17 of 371, across 3 files
- convert dash-format node IDs to colon formatin 17 of 371, across 5 files
- match reference quality and rhythm if providedin 16 of 371, across 2 files
- narrow scope or reduce depth to avoid oversized payloadsin 16 of 371, across 4 files
- generate a simple and memorable logoin 15 of 371, across 1 file
Said here and by no other author read
- Run the nanoodle workflow with Photo and Style inputs
- Use the ambient NANOGPT_API_KEY
- Pass --env-file when the key is not exported
- Use the CLI printed path for the output file
- Pass --json for a structured result
- Inform the user about the cost before running repeatedly
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.