heytea-style skill
A skill that turns one photo into a Heytea-inspired doodle poster, a flavor monster character or a runnable desktop pet.
- 347 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The pet runner downloads npm packages and Electron and runs on the desktop. Run the install after reviewing the `--json-plan` output.
- The style imitates a brand: do not present results as official Heytea material.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/heytea-styleDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The pet runner downloads npm packages and Electron and runs on the desktop. Run the install after reviewing the `--json-plan` output.
- The style imitates a brand: do not present results as official Heytea material.
This is third-party code. Review the repository files before installing.
What it does
The `heytea-doodle-poster` skill takes one photo and first checks that it shows a single clear subject. It then offers three routes: a poster with a wobbly handwritten title, a text-free poster told by tiny figures, or a flavor monster built from the colors, fillings and textures of the subject. Once the character is approved, it can make a fusion poster where the monster interacts with the real product, or build a runnable desktop pet. The pet runs on macOS and Windows through a separate Electron runner installed once; new characters ship as light packs.
Who it is for. Designers and social media authors turning food and drink photos into branded posters inside Codex.
Good fit when
- You need a poster from a cup or dessert photo with wobbly handwritten titles.
- You want a text-free poster where tiny figures carry the story.
- You need a mascot built from a drink flavor for packaging or a channel.
- The monster should come alive as a desktop pet.
Not a fit when
- You need official Heytea materials with the logo.
- The photo has several subjects and you do not want to choose.
- You need a realistic ad shot with no drawn elements.
Example request
Turn this latte photo into a text-free poster and show three composition options.Limitations
The project is unofficial with no tie to Heytea, and the skill adds no brand logos or mascots. The pet runner installs npm and Electron and offers a mirror when downloads fail. The skill targets Codex. Last commit in September 2026. Results depend on photo quality and on image generation in Codex, so a poster may take several attempts and manual touch-ups. Documentation and examples are in Chinese.
How to disable. Delete the `~/.codex/skills/heytea-doodle-poster` folder. Remove the installed pet runner and its packs separately.
FAQ
Which options appear after uploading a photo?
Three: a poster with text, a text-free poster and a flavor monster. If the user already named the result, the question is skipped.
Must the pet runner be installed up front?
No. The environment is checked only after the character is approved and the pet is chosen, with `python3 scripts/desktop_pet.py doctor`.
Is this an official Heytea tool?
No. The README states there is no partnership or license, and logos are not added without authorized assets.
Which systems does the pet support?
The pet runner works on macOS and Windows. Schema v3 for flavor monsters needs runner version 3.1.0 or newer.
What if Electron fails to download?
The README describes a `--mirror` flag for network failures; it switches the npm and Electron downloads to a mirror.
Discussion
No questions or reviews yet.
Related
SkillsA Codex skill that builds an animated companion from two or more of your photos and generates it on your own machine
Codex skill that turns a portrait, photo or text description into a retro illustration in the style of an early CRT interface.
Fifty-one Codex skills that turn a photo into a poster, avatar, comic or illustration in a chosen visual style.
A skill that turns your photo or description into a hand-drawn character and uses it for diagrams, knowledge cards and slides
A skill that generates one-ink and two-ink editorial posters: paper substrate, halftone, negative space and restrained type
A Codex skill that redraws your photo as a watercolor illustration on white paper, with wide margins and a handwritten caption
README in short
A photo becomes a drawn poster or character. The monster starts as a static identity sheet, and the poster and pet appear only after approval.