personal-ip-image-pack skill
Turns one or two of your photos into a cartoon character and extends it into avatars, stickers and scenes with one face.
- 124 ★ on the repository
- Last commit
Extended access
Why this level
- Works with face photos, which must not be uploaded without the person's consent
- Photos go to the agent's image generation service
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/personal-ip-image-packDetects 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.
- Works with face photos, which must not be uploaded without the person's consent
- Photos go to the agent's image generation service
This is third-party code. Review the repository files before installing.
What it does
personal-ip-image-pack works in stages: pick one of six styles, confirm photo rights, create and freeze a character prototype, then extend it into the requested assets. Face, hairstyle, glasses, signature clothing and proportions are locked in a character spec file, and only pose, emotion or props change. Each set ships with templates: an input brief, a character spec, a delivery manifest and an acceptance record. The scripts `init_delivery_package.py` and `validate_delivery.py` create the package skeleton and check sizes, transparency and file hashes. Styles live in `STYLE_LIBRARY.md` and in an interactive HTML gallery.
Who it is for. Bloggers, freelancers and personal-brand authors who want their own cartoon character for avatars and stickers.
Good fit when
- A channel needs an avatar and a set of emotions in one style.
- The author's character is required in new poses and outfits while the face must not change.
- Before releasing a series you want to approve the character prototype and only then generate the rest.
- A client asks for assets delivered with a manifest: sizes, transparency, version.
Not a fit when
- You only have other people's photos without their consent.
- You need a photorealistic double of a person rather than a cartoon.
- You need one quick picture, and a multi-step process with confirmations would be excessive.
Example request
Use `$personal-ip-image-pack`. I confirm I own the photos. Propose a style first, then a prototype, and make no sticker series until I confirm.Limitations
The skill is built for Codex and called as `$personal-ip-image-pack`. It needs image generation inside the agent, and delivery checks need Python 3.10 and Pillow. Use only your own photos or photos of people who consented. The six bundled reference sets are marked `pending_clearance`, so only text style descriptions go into generation. Styles differ in capability, for example `IP-01` does not suit outfit changes. Documentation is in Chinese. The last commit is from August 2026.
How to disable. Delete the `personal-ip-image-pack` folder from the Codex skills directory. Generated packages sit in `outputs/` and are deleted separately along with uploaded photos.
FAQ
Which photos can I upload?
Your own, or those of people who consented. Do not upload passports, addresses or contacts, and original photos are not copied into the skill repository.
How many styles are there and how do they differ?
Six, from `IP-01` with simple lines to `IP-06` in a comic manner. Each states whether it suits avatars, stickers, outfit changes or scenes.
What is delivered?
An approved prototype, separate PNGs of avatars, emotions, poses and scenes, a character spec, a delivery manifest and an acceptance record.
Why is there a validation script?
`validate_delivery.py` checks files against the manifest: format, sizes, transparency and hashes. It does not check photo rights or style match.
Can I install it without manual cloning?
Yes, send Codex the repository link and ask it to install the skill, the wording is in the README.
Discussion
No questions or reviews yet.
Related
SkillsA skill that turns your photo or description into a hand-drawn character and uses it for diagrams, knowledge cards and slides
A skill pack for 3D characters from illustrations: input prep, rigging, expressions and checks in Blender.
A skill that generates extremely simple, cute mascot characters for logos: rounded forms, three colors, lower-corner composition
Five image-generation skills: Qwen-Image prompts, logos with shared geometry, diary comics, transparent PNGs and process dioramas
A Codex skill that builds an animated companion from two or more of your photos and generates it on your own machine
Vane GPT Image Skills: two Codex skills for GIF sticker packs from a photo and pixel covers with illustrations for X articles
README in short
Character and delivery state is kept in versioned files, so a new pose or outfit can be added without changing the face.