beauty-generator

Guide a user through a compact two-step Chinese option flow for adult female portraits, generate two matched realistic images directly, then optionally create a video-ready character reference sheet from the first image.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "beauty-generator" with this command: npx skills add pddsa/beauty-photo-generator

Beauty Generator

Overview

Use this skill when the user gives a short or fuzzy Chinese prompt for an adult female portrait and wants polished output without manually writing a long image prompt.

Keep the experience product-like:

  • First give a compact core-choice round
  • Then offer one optional detail round
  • Send one short Chinese confirmation
  • Generate two images directly
  • After generation, offer an optional follow-up for a video-ready character reference sheet

Read these files only when needed:

Workflow

1. Scope and safety

  • Only generate adult women.
  • Refuse requests with underage framing, school-age cues, or sexualized youth language.
  • If the user is vague but asks for a sexy result, rewrite it as tasteful high-end fashion portrait language.
  • Keep the result realistic, elegant, and non-explicit.

2. Run the core-choice round first

If the user already gave some traits, keep them and ask only for the missing high-impact choices.

The first round covers:

  • Preset template
  • Face shape
  • Eye shape
  • Hairstyle
  • Vibe
  • Background

Use the short copy from references/conversation_flows.md. Encourage replies with letters, numbers, or short Chinese phrases.

3. Offer one optional detail round

Offer a second round for refinement only once. If the user skips it, use the defaults in references/option_catalog.md.

The detail round covers:

  • Age feel
  • Body tendency
  • Makeup
  • Hair color
  • Expression
  • Lighting mood

4. Resolve conflicts consistently

When user inputs conflict, use this order:

  1. Explicit user text
  2. User's later option choices
  3. Preset defaults

Do not silently replace a clear user requirement with a preset.

5. Assemble the portrait prompt

Build one polished Chinese natural-language prompt. Do not show the full prompt unless the user explicitly asks for it.

The portrait prompt should usually include:

  • Adult identity and the chosen aesthetic direction
  • Face shape, eye shape, hairstyle, hair color, and makeup
  • Vibe, expression, age feel, and body tendency
  • Background and lighting mood
  • Realistic portrait-photography quality targets
  • Clean facial detail, natural skin texture, no text, no watermark

Unless the user asks otherwise, keep the baseline:

  • Default preset: 东方现代写实
  • Half-body close portrait
  • Clear sharp face
  • Natural skin texture
  • Clean high-end background
  • Realistic photography

6. Enforce the portrait usage cap

Right before generating the two portrait images, run:

python .\scripts\usage_gate.py portraits consume

If the returned JSON contains allowed: false, do not generate. Return the exact message from the script.

If the user asks about remaining portrait uses, run:

python .\scripts\usage_gate.py portraits status

7. Generate exactly two portrait images

Use one coherent character design for both images and change only the angle:

  1. 正面微偏左
  2. 侧脸回望

Keep identity, styling, lighting direction, and overall aesthetic aligned across both outputs.

Before generation, send one short Chinese confirmation using the style in references/conversation_flows.md.

8. Offer the video-prep follow-up

Immediately after the two portraits are generated, ask a short follow-up in Chinese:

如果你要继续做视频素材,我可以基于第1张“正面微偏左”继续生成角色设定参考表。回复“需要”即可。

If the user does not say 需要, stop there.

9. Generate the character reference sheet on demand

If the user replies 需要, treat it as a request for a video-ready character reference sheet based on the first portrait image, not as direct video generation.

Before generating the reference sheet, run:

python .\scripts\usage_gate.py reference-sheet consume

If the returned JSON contains allowed: false, do not generate. Return the exact message from the script.

If the user asks about remaining reference-sheet uses, run:

python .\scripts\usage_gate.py reference-sheet status

Then generate one image using the first portrait image as the identity reference plus the fixed art-direction rules in references/reference_sheet_prompt.md.

The generated sheet must:

  • Preserve the same face and identity as the first portrait
  • Use a white pure background
  • Present a professional high-end fashion character reference layout
  • Show four aligned full-body views and multiple detail callouts
  • Stay photorealistic and print-ready

Response style

  • Keep the interaction in Chinese unless the user asks otherwise.
  • Be concise, guided, and product-like.
  • Do not dump long prompts by default.
  • Confirm selections briefly, then generate directly.

作者微信:ddff9294 加好友备注来意。 有公众号,持续输出AI内容 ~

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

保单照妖镜 - 保单权益保障PK擂台

保单照妖镜 - 保单权益保障PK擂台。如果你遇到不知道该如何花钱买更适合自己的保险,看到两家保险产品不知道如何比较两份保单的好坏?选用这个工具是最基础、最简单的PK工具,让你清晰了解两个产品的好坏。 上传两张或以上意外险保单(图片/PDF),自动OCR识别+LLM结构化提取,七维度科学打分对比(含理赔口碑实时搜索...

Registry SourceRecently Updated
General

Keigo Mail Generator

keigo-mail-generator は、日本のビジネスメール作成を標準化するための専用スキルです。LINE、Telegram、Slack などのマルチプラットフォームのユーザーIDを永続的な署名ストレージと紐付け、自動で統合・管理するバックエンド機能を備えています。日本のビジネス環境に最適化された、構成が正...

Registry SourceRecently Updated
General

Miro Management

Manage Miro through the Miro REST API using OAuth 2.0, saved token files, or direct access tokens. Use when the user wants to connect a personal or local Mir...

Registry SourceRecently Updated
General

Family Cultivation Coach

家庭培养协作官。安装后可直接说“我想给孩子建一个每周培养计划”开始使用。当用户提到"孩子课表"、"每周培养计划"、"育儿安排"、"兴趣班课表"、"孩子时间管理"、"家庭培养方案"、"孩子学习计划"等相关词语时,必须触发此技能。 本技能通过5组结构化问题收集孩子画像、家庭约束、培养目标和执行偏好,生成真实可执行的每...

Registry SourceRecently Updated