Fantasy 生命感人像摄影 skill
Portrait skill that makes a snapshot cinematic while keeping face and scene, or builds an original series from scratch.
- 467 ★ on the repository
- Last commit
Extended access
Why this level
- Photos of people go to the image model the user connects; process only pictures you have the right to use.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/fantasyDetects 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.
- Photos of people go to the image model the user connects; process only pictures you have the right to use.
This is third-party code. Review the repository files before installing.
What it does
The skill guides an agent through three portrait modes. Mode A takes an ordinary photo and re-plans light, depth of field, color temperature and crop while keeping the face, expression, clothing and place. Mode B needs no source image: from a theme and a character brief it outputs original prompts and a series plan. Mode C strengthens atmosphere in an existing frame. The skill draws nothing itself. It organizes decisions, prompts and workflow, and an image tool available in the agent environment makes the picture. Instructions are in Chinese, with the rules in `SKILL.md`.
Who it is for. Photographers, designers and social media managers who polish their own portraits or prepare a visual series through an image model.
Good fit when
- A tourist rooftop photo should reach the level of a staged shot.
- A series needs original portraits on a "summer, backlight" theme.
- A phone snapshot should gain light without changing the person.
- A portfolio needs one consistent visual direction.
Not a fit when
- An exact repeat of one result is required; the authors do not promise the same effect on every run.
- The agent environment has no image generation or editing tool.
- The photo shows another person and there is no consent to edit it.
Example request
Process this cafe photo with fantasy-life-force-portrait-photography: keep the face and clothing, rebuild light and depth of field.Limitations
Installation is manual: download the ZIP and place the `fantasy-life-force-portrait-photography` folder with `SKILL.md` into a skills directory. Setup includes no image service, account or generation quota; the user supplies those. Rules and README are in Chinese, and the default look assumes an East Asian subject, which a request can change. Last repository commit: September 2026. The skill does not guarantee the same result on every run.
How to disable. Delete the `fantasy-life-force-portrait-photography` folder from the skills directory (`~/.agents/skills/` for Codex or `.agents/skills/` in a project).
FAQ
Is a source photo required?
For modes A and C, yes. Mode B works without one: a theme, scene or character description is enough.
Does mode A change a person's face?
No. It preserves identity, expression, clothing and the main scene. Light, depth, color temperature and crop change.
What if the skill is not visible after installing?
Open a new task, because the skill list refreshes at session start. The folder must be named `fantasy-life-force-portrait-photography` and the entry point must be `SKILL.md`.
Does the skill generate images itself?
No. It prepares decisions and prompts, and the image comes from a tool connected in your environment.
Which agents does the skill support?
The repository includes `agents/openai.yaml` and Codex instructions. Other skill-capable environments use the same folder by their own loading rules.
Discussion
No questions or reviews yet.
Related
SkillsFemale Portrait Director
Female Portrait Prompt Director Skill
A skill that turns a short set of parameters into a photography-directed portrait prompt for an adult woman, plus negative constraints
A skill that turns photos of buildings, streets and local culture into art-directed editorial posters via an image model
A Codex skill that builds an original photorealistic character from a brief: face, age, wardrobe, extra angles on request.
A Codex skill that draws 16:9 scenes with the Xiaohei character among real objects for Chinese articles
Nuyoah Xiezhen Prompt
南鸢写真提示词
Portrait photography in Chinese: prompts, series, gacha keywords and reshoots with a new subject from the same plan.
A skill that makes an editorial poster from a photo: the shot stays unchanged, with an abstract panel and a local title beside it.
README in short
The README walks through three modes with before-and-after samples and explains the decision order: identity, event, light, depth, atmosphere, then restrained texture work.