Female Portrait Director skill
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
- 1,704 ★ on the repository
- Last commit
- MIT
Minimal access
Why this level
- The skill is made of instructions, style routes and examples
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/female-portrait-prompt-director-skillDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- The skill is made of instructions, style routes and examples
This is third-party code. Review the repository files before installing.
What it does
The skill turns a short set of portrait parameters into a coherent, photography-directed prompt for a fictional adult woman. It locks the user's explicit parameters, picks exactly one visual route from the style registry, and expands face, body, outfit, scene, camera, lighting and finish into a single photographed moment. Beyond prompt building it has modes for optimization, diagnosis of failed prompts, parameter recommendation, safety rewriting and image-to-prompt extraction. With an uploaded reference it locks the person or product to preserve them during direct generation. It ships around twenty style routes, temperament overlays and examples.
Who it is for. For designers, SMM specialists and marketers who need stable portrait prompts for generative image models.
Good fit when
- You need a detailed portrait prompt in a specific style
- You need to diagnose a poor result and rewrite the prompt
- You need to preserve a person from an authorized reference during generation
Not a fit when
- You need portraits that are not of women or entirely different subjects
- The agent has no image generation and you need an actual image
Example request
Use female-portrait-director to build a prompt: clean lifestyle style, cafe window scene, soft daylight, 3:4 frameLimitations
The skill targets adult female portraits and sets safety boundaries: fictional adult subjects by default, and no sexualized minors, explicit nudity, non-consensual or deceptive images. On its own it only builds the prompt; producing an image needs a connected generation tool whose availability and quality depend on the agent. Reference-preserving direct generation requires rights to the source image. Per the README, Codex was runtime-verified while the other agents are claimed for packaging compatibility.
How to disable. Remove the female-portrait-director folder from the agent's skills directory, for example ~/.codex/skills/ or ~/.claude/skills/.
FAQ
Does the skill draw the image itself?
No. It builds a prompt and negative constraints. Direct generation is possible only if the agent has a connected image generation tool.
Can it keep the face from my photo?
Yes, there is a reference-lock mode for that, but it needs rights to the source image and the subject must be an adult.
Discussion
No questions or reviews yet.
Related
SkillsPortrait skill that makes a snapshot cinematic while keeping face and scene, or builds an original series from scratch.
A skill that turns a picture into a generator prompt: frame breakdown, an enhanced version, three variants and platform editions.
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.
A skill that turns a plot or scene into a cinematic AI video prompt for 6 to 30 seconds, with shots, performance and sound.
Rebuilds light, exposure and skin of a finished portrait while the person stays the same and the skin loses its plastic look.
README in short
The README contrasts a generic prompt pack with a director approach: the skill locks requirements, picks one visual route and directs subject, action, outfit, scene, camera and lighting as one photographed frame. It covers install via the skills CLI and manually via git, compatibility with Codex, Claude Code, Cursor, GitHub Copilot and Gemini CLI, about twenty styles and a four-part output format. It states safety boundaries and notes that only Codex was runtime-verified while the other rows are packaging compatibility. MIT license, version V1.6.
README badge
Original SKILL.md
--- name: female-portrait-director description: Generate, visually expand, optimize, diagnose, and route structured AI image prompts for adult female portraits. Use for lifestyle, curve-focused, fashion, oriental, fantasy, realism, beauty, CCD, low-key cinematic, studio, sport, travel, and e-commerce portrait requests; onboarding or usage help; parameter recommendations; prompt rewrites; image-to-prompt preparation; direct image generation; or identity- and product-preserving edits from authorized reference images. Preserve explicit user parameters and locked reference subjects while creating a coherent photography-directed scene. --- # Female Portrait Director Turn a small set of portrait parameters into a stable, visually directed, copy-ready image prompt for a fictional adult woman. Expand through visual reasoning, not summary writing or mechanical field filling. ## Required loading order 1. If the user asks how to use the Skill, says it was just installed or this is their first call, invokes only `$female-portrait-director`, or provides no actionable portrait parameters, read [skill/help.md](skill/help.md) and return its concise onboarding tutorial. Do not load a Route for a help-only request. 2. Read [skill/skill.md](skill/skill.md) for the canonical workflow. 3. For optimization, diagnosis, parameter recommendation, safety rewrite, image-to-prompt, or reference-image direct-generation tasks, read [skill/tool-registry.md](skill/tool-registry.md) and only the selected file under `skill/tools/`. 4. Read [skill/style-registry.md](skill/style-registry.md). Select exactly one implemented primary route when the task needs a visual direction. Do not invent a placeholder extension route. 5. Read only the selected file under `skill/routes/`. 6. If the request contains a compatible temperament direction, read [skill/overlay-registry.md](skill/overlay-registry.md) and only the selected file under `skill/overlays/`.