Token导航 LogoToken导航TokenDH.com
待分类只读github未标认证来源可访问许可证需确认审计通过

avatar-portrait头像肖像

Agent Skill

avatar-portrait 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

559

周安装

24

GitHub Stars

3

下载量

196
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:avatar-portrait(头像肖像)
来源仓库:https://github.com/b-open-io/gemskills
仓库路径:skills/avatar-portrait
安装命令:
npx skills add https://github.com/b-open-io/gemskills --skill avatar-portrait
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/b-open-io/gemskills --skill avatar-portrait

简介

Avatar Portrait 利用 Gemini 图像生成从照片创建风格化头像。

  • 适用于团队 profile 图片、角色 portrait 或特定艺术风格转换。
  • 平衡 likeness 与 style,保留识别度同时应用像素、复古等效果。
  • 安装方式:npx skills add https://github.com/b-open-io/gemskills --skill avatar-portrait
  • 需授权使用 Gemini API,注意版权与隐私合规边界

SKILL.md

Avatar Portrait

Generate stylized avatar portraits from reference photos using Gemini image generation, preserving recognizable likeness while applying a requested visual style.

When to Use

Use this skill when the user asks to:

  • Create avatars from photos
  • Generate team member profile images in a specific style
  • Convert headshots to stylized portraits (pixel, retro, illustrated, modern)
  • Create consistent character portraits that resemble real people

Core Principles

Balance Likeness and Style

The critical challenge is achieving BOTH:

  1. Recognizable likeness - Must look like the source person
  2. Chosen style fidelity - Clear style, not photorealistic unless requested

Common failures:

  • Too photorealistic = ignores requested style
  • Too stylized = loses resemblance to source person

Single Source Input

Use ONLY the subject's photo as input. Never use another person's image as a style reference - this causes face blending and loss of likeness.

Prompt Template

Generate a styled avatar portrait from the reference photo.

## INPUT IMAGE
[path to subject's photo] - USE ONLY THIS IMAGE

## CRITICAL: LIKENESS PRESERVATION
Capture the subject's EXACT features from the photo:
- Face shape and jawline
- Eye shape, spacing, and expression
- Nose shape and size
- Mouth/smile characteristics
- Hair texture, color, and style
- Facial hair pattern and coverage (if applicable)
The result must be RECOGNIZABLE as this specific person.

## STYLE REQUIREMENTS
- Style: [style requested by user, e.g. pixel art, painterly, anime, low-poly]
- Keep style cues consistent across linework, shading, and color treatment
- Stylized but maintains individual features
- NOT photorealistic unless explicitly requested

## APPEARANCE
- [Describe clothing from photo or as specified]
- [Describe expression]
- [Describe any accessories]

## BACKGROUND
- [Describe background style and colors]
- Background style should match the character style

## TECHNICAL
- NO TEXT on the image
- 512x512 output
- Portrait orientation, head and shoulders
- Square format

## OUTPUT
Save to: [output path]

Example: Individual Avatar

For a team member named Dan with a reference photo showing short dark hair, beard, black v-neck:

Generate a styled avatar portrait from the reference photo.

## INPUT IMAGE
/path/to/dan-photo.png - USE ONLY THIS IMAGE

## CRITICAL: LIKENESS PRESERVATION
Capture Dan's EXACT features from the photo:
- His specific face shape and jawline
- His eye shape and expression
- His nose shape
- His smile characteristics
- Short dark hair - exact texture and style from photo
- Full dark beard - exact pattern and coverage
The result must be RECOGNIZABLE as Dan.

## STYLE REQUIREMENTS
- Style: retro 16-bit pixel art
- Visible pixels but NOT a pixelated photo filter
- Clean lines, rich colors, consistent shading
- Stylized but maintains individual features

## APPEARANCE
- Black v-neck shirt
- Warm smile showing teeth
- Friendly, approachable expression

## BACKGROUND
- California sunset cityscape
- Warm oranges, pinks, teals
- Pixel art style matching the character

## TECHNICAL
- NO TEXT on the image
- 512x512 output
- Portrait orientation, head and shoulders

## OUTPUT
Save to: /path/to/output/dan-pixel.png

Context Discipline

Do not read generated avatar images back into context. The script outputs only the file path. Ask the user to visually inspect the result and provide feedback for iteration. To inspect programmatically, optimize the image first (via the optimize-images skill).

Iteration Workflow

  1. First attempt: Generate with detailed prompt
  2. Review: Check both likeness AND style
  3. Adjust if needed:

- If too photorealistic: Emphasize "stylized pixel art character" - If likeness lost: Strengthen feature descriptions from source - If wrong features: Be more specific about what to capture

Common Issues

Face doesn't match source

  • Ensure ONLY the subject's photo is used as input
  • Add more specific feature descriptions
  • Reference exact details visible in the photo

Too photorealistic

  • Emphasize the style family and key style cues
  • Request "stylized" and "illustrated feel"
  • Add explicit anti-photorealism language unless photorealism was requested

Too cartoonish / loses likeness

  • Strengthen the likeness preservation section
  • List specific features to capture
  • Emphasize "RECOGNIZABLE as this person"

Reference Files

For background style references:

  • references/background-styles.md - Common background approaches for avatars

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

33.11%
按下载量换算65

Claude

31.29%
按下载量换算61

Cursor

18.61%
按下载量换算36

Gemini CLI

7.99%
按下载量换算16

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills