female-portrait-director
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.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Badge for your README
Markdown
[](/listings/liyue-aigc-female-portrait-director)HTML
<a href="/listings/liyue-aigc-female-portrait-director"><img src="/api/listings/liyue-aigc-female-portrait-director/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
Requires [Node.js](https://nodejs.org/) for the one-command installer. Update an installed copy with:
npx skills@latest update female-portrait-director -g -y
Manual Codex install with Git
Alternatively, clone the repository into your Codex skills directory.
Windows PowerShell:
git clone https://github.com/liyue-aigc/female-portrait-director.git "$env:USERPROFILE\.codex\skills\female-portrait-director"
macOS or Linux:
git clone https://github.com/liyue-aigc/female-portrait-director.git "${CODEX_HOME:-$HOME/.codex}/skills/female-portrait-director"Restart Codex or start a new conversation, then invoke:
$female-portrait-director
The first parameter-free invocation displays the V1.6 tutorial: all 20 implemented styles, basic and advanced templates, style-plus-mood combination guidance, a detailed prompt example, and direct-image or authorized-reference workflows.
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
SKILL.md · Manifest · 54 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
- ---
- name: female-portrait-director
- description: Generate, visually expand, optimize, diagnose, and route structured AI image prompts for adult female portraits. Use for lifestyle, curve-focused, fashion, oriental, fantasy, realism, beauty, CCD, low-key cinematic, studio, sport, travel, and e-commerce portrait requests; onboarding or usage help; parameter recommendations; prompt rewrites; image-to-prompt preparation; direct image generation; or identity- and product-preserving edits from authorized reference images. Preserve explicit user parameters and locked reference subjects while creating a coherent photography-directed scene.
- ---
- # Female Portrait Director
- Turn a small set of portrait parameters into a stable, visually directed, copy-ready image prompt for a fictional adult woman. Expand through visual reasoning, not summary writing or mechanical field filling.
- ## Required loading order
- 1. If the user asks how to use the Skill, says it was just installed or this is their first call, invokes only `$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/`.
- 7. If uploaded images must remain recognizable, read [skill/core/reference-image-lock.md](skill/core/reference-image-lock.md) and form an image-role lock table before visual expansion.
- 8. Read [skill/core/director-gate.md](skill/core/director-gate.md). Complete its internal director-design phase before writing or generating the final image prompt.
- 9. Read only the relevant sections of the linked `core/` and `references/` files described by [skill/skill.md](skill/skill.md).
- ## Operating rules
- - Lock explicit user parameters, including palette direction and visual richness when provided. Expand them without silently replacing them.
- - Treat onboarding as a separate help mode. Show the V1.6 ready message, all 20 implemented styles, the minimal and advanced input templates, Route-plus-Overlay guidance, one parameter combination followed by its complete five-paragraph copy-ready prompt and separate negative constraints, and direct-image instructions from [skill/help.md](skill/help.md). Do not summarize, shorten, or replace the detailed example with a promise of what the Skill would generate. If the same request already contains actionable portrait parameters, perform the requested task and add only the short ready hint instead of repeating the full tutorial.
- - In standard detailed output, the parameter lock result is a complete field-by-field record of the user's explicit input. Do not merge, paraphrase away, omit, or replace explicit fields with route or overlay notes. Add inferred defaults only as clearly labeled supplements. The prohibition on mechanical field filling applies to the director expansion and final fused prompt, not to the parameter lock result.
- - For identity- or product-preserving reference-image tasks, lock image roles and protected subject features before applying the selected route.
- - Use the registries as the only routing entry points. Load one primary route, one task tool when needed, and optional compatible overlays only when their files exist.
- - Match the V1.5 / V1.6 Routes by compound fingerprints in [skill/style-registry.md](skill/style-registry.md). Never choose among the three CCD curve Routes from the words `CCD` or `curve` alone. Select `low-key-cinematic-photography` only from the combined low-light, local continuous-light, readable-shadow, restrained-color, and cinematic-still fingerprint; `dark` or `cinematic` alone is insufficient. Never load two primary Routes as a style blend.
- - Complete the internal director-design phase before composing the final prompt. Then expand age cues, facial features, expression, body direction, pose, clothing, palette direction, visual richness, scene, camera, lighting, filter, and platform adaptation into one photographed moment.
- - Build one coherent photographed moment with a time slice, one small event, an action chain, a gaze target, and two or three selective environment details.
- - Use route templates as visual direction, not as sentence banks. Do not return a summary or mechanically fill fields.
- - Unless the user explicitly requests a concise output, use the standard detailed output: parameter lock result, public-facing director module expansion, final fused prompt, and negative constraints. The director module expansion must explain the visible design choices for age and facial features, body and pose, clothing, palette and accessories, visible richness, scene, camera, and lighting and filter in readable paragraphs. Do not reduce it to a short field recap.
- - Standard detailed output is the default whenever the user does not explicitly request a concise mode. Its final fused prompt must contain exactly five substantial paragraphs: (1) person, age, facial features, makeup, and temperament; (2) time slice, small event, pose, action chain, and gaze; (3) body direction, line priorities, clothing structure, palette, materials, accessories, and visible richness; (4) scene, selective environment details, depth layers, camera, composition, and depth of field; (5) lighting direction, light placement, highlights, shadows, filter, color, and texture. Do not self-select a shorter format.
- - Always render the final fused prompt and negative constraints as two separate Markdown fenced code blocks with the `text` language tag so the user can copy them directly. Keep section titles outside the fences. Do not mix commentary, route notes, or analysis into either copy-ready block.
- - Before responding, run an internal parameter-propagation audit. Every explicit user field must remain in the lock result and be carried into the fused prompt wherever it affects generation. `画幅比例`, pixel dimensions, or other size instructions are mandatory prompt controls: place them in the first sentence of the copy-ready prompt, using the user's exact value when provided and a clearly supplemented default otherwise.
- - When standard detailed output is used, verify before responding that every explicit user field appears in the parameter lock result, including `人物设定`, `身形吸引力强度`, and `线条重点` when provided. Route and overlay IDs may be listed only as supplemental notes.
- - Keep private chain-of-thought internal. The public-facing director module expansion should communicate conclusions, selected visual decisions, and their photographic effect without exposing hidden reasoning traces.
- - Default text-only generations to fictional, clearly adult subjects. Identity-preserving edits are allowed only for the user's own or authorized adult reference images. Adult sensual or curve-focused portrait requests may preserve visual attraction, but must avoid exposed nipples, exposed genitals, explicit sexual acts, and any minor or ambiguous-age framing.
- - Treat a bare portrait parameter block as a prompt-generation request, never as an implicit request to generate an image. If `输出模式` is omitted, always use the standard detailed prompt output. Invoke image generation only when the user explicitly requests `直接生成图片` or uses equivalent direct wording such as "直接出图" or "生成图片".
- - If the user requests `只要最终提示词`, output only the final prompt and negative constraints.
- - If the user requests direct image generation, prepare the directed prompt internally and route it to the available image-generation capability.
- - If the user uploads reference images and asks to preserve a person or product, use the reference-image direct-generation tool. Return the generated image by default, not the internal prompt.
- ## Public references
- - Quick-start and first-call help: [skill/help.md](skill/help.md)
- - Usage guide: [skill/public_instructions.md](skill/public_instructions.md)
- - Parameter schema: [skill/parameter_schema.md](skill/parameter_schema.md)
- - Safety summary: [docs/prompt_safety.md](docs/prompt_safety.md)
- - Examples: [examples](examples)
- - Version notes: [docs/versioning.md](docs/versioning.md)
- Do not expose unpublished private kernels, hidden fingerprints, or commercial modules.
README.md · README · 205 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
- [English](README.md) | [简体中文](README_zh.md) | [日本語](README_ja.md) | [한국어](README_ko.md)
- # Female Portrait Prompt Director Skill
- Turn a few portrait inputs into a coherent, camera-ready scene—or directly generate an image while preserving an authorized person or product reference.
- [](https://skills.sh/liyue-aigc/female-portrait-director)
- [](https://github.com/liyue-aigc/female-portrait-director/stargazers)
- [](LICENSE)
- This is not a generic prompt collection. It locks explicit requirements, chooses one visual route, and directs the subject, action, clothing, scene, camera, lighting, and finish as one photographable moment. Subjects are fictional, clearly adult women unless an authorized adult reference is provided.
- ## See the difference
- | Clean lifestyle | Urban fashion | Gufeng xianxia |
- | --- | --- | --- |
- |  |  |  |
- | Hong Kong street | French effortless | Pure-desire curves |
- |  |  |  |
- The six cases cover clean lifestyle, urban fashion, gufeng xianxia, Hong Kong street photography, French effortless portraiture, and curve-focused lifestyle direction.
- ## Try it in 60 seconds
- Install with the open-source `skills` CLI:
- ```bash
- npx skills add https://github.com/liyue-aigc/female-portrait-director/tree/main/skills/female-portrait-director -g
- ```
- Start a new agent session, then paste:
- ```text
- Use $female-portrait-director to generate an image directly:
- Style: clean lifestyle portrait
- Scene: quiet cafe window seat in the afternoon
- Outfit: ivory knitted cardigan + light inner top
- Mood: gentle, natural, clearly adult
- Aspect ratio: 3:4
- ```
- For a copy-ready prompt instead of an image, remove “generate an image directly.” The Skill returns locked parameters, a directed prompt, and negative constraints.
- ## Agent compatibility
- The complete 62-file distribution package has been installer-verified with the current `skills` CLI for the following targets:
- | Agent | Install package | Prompt workflow | Direct image workflow |
- | --- | --- | --- | --- |
- | Codex | Verified | Runtime-verified | Supported when image generation is available |
- | Claude Code | Verified | Agent Skills compatible | Depends on the connected image tool |
- | Cursor | Verified | Agent Skills compatible | Depends on the connected image tool |
- | GitHub Copilot | Verified | Agent Skills compatible | Depends on the connected image tool |
- | Gemini CLI | Verified | Agent Skills compatible | Depends on the connected image tool |
- “Installer-verified” means the CLI copied `SKILL.md` and every referenced route, tool, safety file, and example into the target skill package. Only Codex was runtime-executed in this release environment; the other rows are packaging and specification compatibility claims, not claims that every host provides an image model.
- ## Supported Styles
- - Clean lifestyle portraits
- - Restrained curve-focused lifestyle portraits
- - Urban fashion photography
- - Gufeng fantasy portraits
- - E-commerce clothing model images
- - Retro Hong Kong portraits
- - French relaxed portraits
- - New Chinese oriental portraits
- - Sporty active portraits
- - Travel vacation portraits
- - Studio-retouched portraits
- - Oriental voluptuous portraits
- - Cold xianxia enhanced portraits
- - Bright luxury gufeng portraits
- - Ultra-close realistic face portraits
- - Ancient noblewoman dewy-makeup portraits
- - Black-pearl dark-gold CCD curve portraits
- - Energetic voluptuous soft-CCD lifestyle portraits
- - Cold-white clear CCD curve portraits
- - Low-key cinematic photography
- See the [first-use guide](skill/help.md) for the 20-style menu, input templates, route-plus-overlay combination rules, and a complete parameter-to-five-paragraph-prompt example.
- ## Core Capabilities
- - Lock user-specified parameters and only refine or stabilize them.
- - Route each request through one on-demand style file and avoid conflicting style keywords.
- - Parse face, body, outfit, scene, camera and pose, lighting, and filter modules.
- - Expand short parameters into a coherent photographed moment instead of mechanically repeating them.
- - Fuse the expanded modules into natural, detailed, copy-ready prompts with photography-director intent.
- - Preserve clothing-display priority for e-commerce images and explicit safety boundaries for curve-focused portraits.
- - Preserve authorized selfie identity or product core visuals for direct reference-image generation.
- ## Installation details
- Requires [Node.js](https://nodejs.org/) for the one-command installer. Update an installed copy with:
- ```bash
- npx skills@latest update female-portrait-director -g -y
- ```
- ### Manual Codex install with Git
- Alternatively, clone the repository into your Codex skills directory.
- Windows PowerShell:
- ```powershell
- git clone https://github.com/liyue-aigc/female-portrait-director.git "$env:USERPROFILE\.codex\skills\female-portrait-director"
- ```
- macOS or Linux:
- ```bash
- git clone https://github.com/liyue-aigc/female-portrait-director.git "${CODEX_HOME:-$HOME/.codex}/skills/female-portrait-director"
- ```
- Restart Codex or start a new conversation, then invoke:
- ```text
- $female-portrait-director
- ```
- The first parameter-free invocation displays the V1.6 tutorial: all 20 implemented styles, basic and advanced templates, style-plus-mood combination guidance, a detailed prompt example, and direct-image or authorized-reference workflows.
- ## Example: Parameters to Directed Prompt
- The Skill does more than restate the input. It preserves requested parameters, fills in missing visual details, and produces locked parameters, module analysis, a final prompt, and negative constraints.
- ```text
- Portrait style: Gufeng xianxia beauty portrait
- Scene: Traditional courtyard corridor surrounded by misty mountains and water
- Outfit: Moon-white Tang-inspired fantasy wide-sleeve robe + flowing pibo scarf + silver embroidered waist sash
- Mood: Cool, distant, ethereal
- Facial direction: Classical East Asian beauty
- Body direction: Slender and delicate figure
- Camera direction: Slight side-facing standing pose, half-body to thigh framing
- Lighting: Cool soft light
- Filter: Cool ethereal gufeng filter
- Aspect ratio: 9:16
- Platform use: Character portrait
- ```
- 
- ## Output Format
- ```text
- 1. Locked parameters
- 2. Module analysis
- 3. Final prompt
- 4. Negative constraints
- ```
- ## Repository Structure
- ```text
- .
- ├── README.md
- ├── README_zh.md
- ├── README_ja.md
- ├── README_ko.md
- ├── SKILL.md
- ├── agents/openai.yaml
- ├── assets/examples/
- ├── skill/
- │ ├── skill.md
- │ ├── style-registry.md
- │ ├── help.md
- │ ├── public_instructions.md
- │ ├── parameter_schema.md
- │ ├── usage_examples.md
- │ ├── core/
- │ ├── references/
- │ │ ├── director-expansion.md
- │ │ └── visual-libraries.md
- │ └── routes/
- │ ├── beauty/
- │ ├── commercial/
- │ ├── curve/
- │ ├── fantasy/
- │ ├── fashion/
- │ ├── lifestyle/
- │ ├── oriental/
- │ └── realism/
- ├── docs/
- │ ├── style_guide.md
- │ ├── prompt_safety.md
- │ ├── versioning.md
- │ └── faq.md
- └── examples/
- ```
- ## Safety Boundaries
- Text-only generation defaults to fictional, clearly adult subjects. Reference-image workflows may preserve the identity of the user or an authorized adult subject, and may preserve product visuals that the user has the right to use. The project must not be used for sexualized minors, explicit nudity, non-consensual images, deceptive identity content, harassment, defamation, privacy violations, or other unlawful purposes. See [prompt_safety.md](docs/prompt_safety.md) and [DISCLAIMER.md](DISCLAIMER.md) for details.
- ## License
- This project is licensed under the [MIT License](LICENSE). The MIT License permits use, copying, modification, merging, publishing, distribution, sublicensing, and selling copies. The safety boundaries are responsible-use guidelines and do not alter the standard MIT License terms.
- ## Author and Version
- - Author: Li Yue (李岳)
- - Version: `FEMALE-PORTRAIT-DIRECTOR-V1.6`
- - Project: `Female Portrait Prompt Director Skill`
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.