Agent skill

Linkfox Aigc Imagegen Brand Gene Extract

by linkfox-ai in linkfox-ai/linkfox-skills

品牌基因样式提取原子技能。根据商品图片与用户品牌基因参数（主色、字体、平台、地区、语言），提取统一的品牌视觉语言（Brand DNA），输出结构化 brandGeneJson 供下游原子技能消费。品牌基因提取、brand gene extract、brand DNA、品牌视觉定义、品牌调性提取、brand style extraction、visual identity…

MITAuto-check passedMedia & Creative

Install Linkfox Aigc Imagegen Brand Gene Extract

skills CLI

$ npx skills add linkfox-ai/linkfox-skills --skill linkfox-aigc-imagegen-brand-gene-extract -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install linkfox-ai/linkfox-skills linkfox-aigc-imagegen-brand-gene-extract --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/linkfox-ai/linkfox-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/linkfox-aigc-imagegen-brand-gene-extract .claude/skills/linkfox-aigc-imagegen-brand-gene-extract && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "linkfox-aigc-imagegen-brand-gene-extract" agent skill from https://github.com/linkfox-ai/linkfox-skills/tree/main/skills/linkfox-aigc-imagegen-brand-gene-extract into .claude/skills/linkfox-aigc-imagegen-brand-gene-extract/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "linkfox-aigc-imagegen-brand-gene-extract", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/linkfox-ai/linkfox-skills/tree/main/skills/linkfox-aigc-imagegen-brand-gene-extract

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add linkfox-ai/linkfox-skills --skill linkfox-aigc-imagegen-brand-gene-extract -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install linkfox-ai/linkfox-skills linkfox-aigc-imagegen-brand-gene-extract --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/linkfox-ai/linkfox-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/linkfox-aigc-imagegen-brand-gene-extract .agents/skills/linkfox-aigc-imagegen-brand-gene-extract && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "linkfox-aigc-imagegen-brand-gene-extract" agent skill from https://github.com/linkfox-ai/linkfox-skills/tree/main/skills/linkfox-aigc-imagegen-brand-gene-extract into .agents/skills/linkfox-aigc-imagegen-brand-gene-extract/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "linkfox-aigc-imagegen-brand-gene-extract", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add linkfox-ai/linkfox-skills --skill linkfox-aigc-imagegen-brand-gene-extract -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install linkfox-ai/linkfox-skills linkfox-aigc-imagegen-brand-gene-extract --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/linkfox-ai/linkfox-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/linkfox-aigc-imagegen-brand-gene-extract .cursor/skills/linkfox-aigc-imagegen-brand-gene-extract && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "linkfox-aigc-imagegen-brand-gene-extract" agent skill from https://github.com/linkfox-ai/linkfox-skills/tree/main/skills/linkfox-aigc-imagegen-brand-gene-extract into .cursor/skills/linkfox-aigc-imagegen-brand-gene-extract/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "linkfox-aigc-imagegen-brand-gene-extract", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/linkfox-ai/linkfox-skills.git --path skills/linkfox-aigc-imagegen-brand-gene-extract

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add linkfox-ai/linkfox-skills --skill linkfox-aigc-imagegen-brand-gene-extract -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install linkfox-ai/linkfox-skills linkfox-aigc-imagegen-brand-gene-extract --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/linkfox-ai/linkfox-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/linkfox-aigc-imagegen-brand-gene-extract .gemini/skills/linkfox-aigc-imagegen-brand-gene-extract && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "linkfox-aigc-imagegen-brand-gene-extract" agent skill from https://github.com/linkfox-ai/linkfox-skills/tree/main/skills/linkfox-aigc-imagegen-brand-gene-extract into .gemini/skills/linkfox-aigc-imagegen-brand-gene-extract/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "linkfox-aigc-imagegen-brand-gene-extract", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install linkfox-ai/linkfox-skills linkfox-aigc-imagegen-brand-gene-extract

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add linkfox-ai/linkfox-skills --skill linkfox-aigc-imagegen-brand-gene-extract -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/linkfox-ai/linkfox-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/linkfox-aigc-imagegen-brand-gene-extract .github/skills/linkfox-aigc-imagegen-brand-gene-extract && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "linkfox-aigc-imagegen-brand-gene-extract" agent skill from https://github.com/linkfox-ai/linkfox-skills/tree/main/skills/linkfox-aigc-imagegen-brand-gene-extract into .github/skills/linkfox-aigc-imagegen-brand-gene-extract/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "linkfox-aigc-imagegen-brand-gene-extract", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add linkfox-ai/linkfox-skills --skill linkfox-aigc-imagegen-brand-gene-extract -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install linkfox-ai/linkfox-skills linkfox-aigc-imagegen-brand-gene-extract --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/linkfox-ai/linkfox-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/linkfox-aigc-imagegen-brand-gene-extract .opencode/skills/linkfox-aigc-imagegen-brand-gene-extract && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "linkfox-aigc-imagegen-brand-gene-extract" agent skill from https://github.com/linkfox-ai/linkfox-skills/tree/main/skills/linkfox-aigc-imagegen-brand-gene-extract into .opencode/skills/linkfox-aigc-imagegen-brand-gene-extract/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "linkfox-aigc-imagegen-brand-gene-extract", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: linkfox-aigc-imagegen-brand-gene-extract
GitHub stars: 107
Token cost: ~2k tokens
SKILL.md length: 507 words
Files: 4 (incl. scripts, references)
Skills in repo: 177
Repo updated: Sep 14, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Works in 5 steps: 解析 brandKey 中各字段值 → 主色决策：brandColor 非空 → 直接采用；为空 → 标记为"自动提取" → 字体决策：fontStyle 非空 → 直接采用；为空 → 标记为"自动提取" → …
Tasks that involve Image generation
SKILL.md covers 适用场景, 不适用, 输入参数 and 流水线步骤, plus 7 more sections
Runs Python scripts from its folder; calls python; needs LINKFOX_AGENT_API_KEY and LINKFOXAGENT_API_KEY

What it does

Linkfox Aigc Imagegen Brand Gene Extract is an agent skill from linkfox-ai/linkfox-skills. 品牌基因样式提取原子技能。根据商品图片与用户品牌基因参数（主色、字体、平台、地区、语言），提取统一的品牌视觉语言（Brand DNA），输出结构化 brandGeneJson 供下游原子技能消费。品牌基因提取、brand gene extract、brand DNA、品牌视觉定义、品牌调性提取、brand style extraction、visual identity extraction。被套图编排层（linkfox-aigc-imagegen-cloth / product 套图编排路径）在步骤三中调用；当用户说"提取品牌基因"、"定义品牌风格"、"brand gene"、"品牌视觉"时触发。

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including scripts and reference files (for example `references/onboarding.md`, `scripts/onboarding.py` and `scripts/save_brand_gene.py`).

It sits in Media & Creative, covering Image generation and Logo and visual identity. The licence is MIT.

When your agent uses it

Tasks that involve Image generation
Tasks that involve Logo and visual identity

Example prompts

“提取品牌基因”
“定义品牌风格”
“brand gene”
“/linkfox-aigc-imagegen-brand-gene-extract”

Requirements

Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

解析 brandKey 中各字段值
主色决策：brandColor 非空 → 直接采用；为空 → 标记为"自动提取"
字体决策：fontStyle 非空 → 直接采用；为空 → 标记为"自动提取"
填充默认值：language 空则默认"英文"；platform 空则默认"亚马逊"；salesRegion 空则默认"美国"
将 images 转为可访问 URL 列表（imageUrlList），供步骤 3 传入 textgen

What it can do on your machine

Read from SKILL.md and the folder at commit 38fef04. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 2 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
- python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
- LINKFOX_AGENT_API_KEY
- LINKFOXAGENT_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Linkfox Aigc Imagegen Brand Gene Extract loads about 2k tokens when it runs, and up to ~2.5k if it reads all its reference files. Until then it costs about 86 tokens; SKILL.md has 507 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~86
When it runs · the whole SKILL.md, loaded when a task matches: ~2k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~2.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from linkfox-ai/linkfox-skills at commit 38fef04, republished under its MIT licence (© linkfox-ai). 507 words, ~1,994 tokens.

Download SKILL.mdSave it as .claude/skills/linkfox-aigc-imagegen-brand-gene-extract/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.

name: linkfox-aigc-imagegen-brand-gene-extract
description: 品牌基因样式提取原子技能。根据商品图片与用户品牌基因参数（主色、字体、平台、地区、语言），提取统一的品牌视觉语言（Brand DNA），输出结构化 brandGeneJson 供下游原子技能消费。品牌基因提取、brand gene extract、brand DNA、品牌视觉定义、品牌调性提取、brand style extraction、visual identity extraction。被套图编排层（linkfox-aigc-imagegen-cloth / product 套图编排路径）在步骤三中调用；当用户说"提取品牌基因"、"定义品牌风格"、"brand gene"、"品牌视觉"时触发。

品牌基因样式提取（Brand Gene Extract）

根据商品图片与用户品牌基因参数，提取统一的品牌视觉语言（Brand DNA），输出结构化 JSON 供下游原子技能消费。

适用场景

场景	说明
套图编排调用	被 `linkfox-aigc-imagegen-cloth` / `linkfox-aigc-imagegen-product`（套图编排路径）在步骤三中调用，为整套图定义统一视觉基因
品牌基因变更	用户修改主色调/字体/平台/地区后重新提取
首次品牌定义	上下文中尚无品牌基因结果时，首次提取

不适用

已有完整 brandGeneJson 且无需变更时（直接复用，不重复调用本 skill）
纯背景替换/抠图/合成等图片编辑操作
非视觉类的品牌故事文案

输入参数

参数	类型	默认	说明
images	list[image]	—	用户上传的商品图片列表（至少 1 张），用于分析商品色彩与气质
brandKey	object	—	用户输入的品牌基因信息（见下方字段说明）

brandKey 字段说明

字段	类型	默认	说明
brandColor	string	""	品牌主色（HEX 值），非空时直接使用，为空时自动提取
fontStyle	string	""	字体风格，非空时直接使用，为空时自动提取
brandName	string	""	品牌名称，用于品牌植入策略
language	string	"英文"	目标市场语言
platform	string	"亚马逊"	发布平台（Amazon/TikTok/Shopee 等）
salesRegion	string	"美国"	销售地区/国家

流水线步骤

步骤 1：参数解析与决策路由

输入：brandKey、images
操作：
1. 解析 brandKey 中各字段值
2. 主色决策：brandColor 非空 → 直接采用；为空 → 标记为"自动提取"
3. 字体决策：fontStyle 非空 → 直接采用；为空 → 标记为"自动提取"
4. 填充默认值：language 空则默认"英文"；platform 空则默认"亚马逊"；salesRegion 空则默认"美国"
5. 将 images 转为可访问 URL 列表（imageUrlList），供步骤 3 传入 textgen
输出：决策路由表（哪些字段用户给定、哪些需自动提取）+ imageUrlList
用途：指导步骤 2 的 prompt 组装

步骤 2：组装品牌视觉基因提取 prompt

输入：步骤 1 的决策路由表、brandKey 全部字段
操作：将以下品牌视觉基因提取指令与 brandKey 参数拼装为完整 prompt，传入步骤 3：

角色：你是顶尖品牌视觉专家和创意总监，基于商品图片与参数，构建一套统一的视觉语言，确保品牌在不同场景下的高度一致性。

A. 统一视觉主题（UNIFIED_VISUAL_THEME）
1. Brand Color（品牌主色）：
  - 定义一个具有"世界观"的核心色，而不仅仅是色板
  - 唯一性：全案只能定义 1 个核心 HEX 色值
  - 来源：必须考虑商品本身的颜色，具备极高审美
  - ⚠️ 黑白灰协议（CRITICAL）：除非商品本身为黑白灰，否则禁止使用黑白灰作为主色，必须输出具体色值（如 #EAF86C）
2. 背景策略（Background Strategy）：必须完整输出以下 4 个子字段，缺一不可，每个都给出具体内容（不得留空、不得只写字段名）：
  - 背景策略-风格定义：根据 salesRegion 做文化本土化的整体环境风格。追求 100% 摄影级写实环境，严禁分层背景图层感，侧重生活方式与情感共鸣。示例："现代北欧极简家居，原木与暖白色调，落地窗自然采光，符合美国中产审美"
  - 背景策略-场景关键词：逗号分隔的具体场景/道具关键词。示例："原木长桌, 亚麻桌布, 绿植, 陶瓷器皿, 晨光"
  - 背景策略-光影：明确的光线方向、色温与氛围（这是必填字段，最易被漏，务必输出）。示例："柔和自然侧光，暖色温 4000K，营造清晨慵懒氛围，轻微长投影增强立体感"
  - Brand Injection（品牌植入）：品牌主色 / Logo / 标识元素如何自然融入场景（这是必填字段，最易被漏，务必输出）。示例："品牌主色作为抱枕/标签点缀色出现，Logo 以低饱和压印形式出现在道具上，不喧宾夺主"
B. 绝对字体锁定（LOCKED_TYPOGRAPHY）
1. 字体风格：从以下库中锁定唯一一种风格：
  - 几何无衬线体：Jost, League Spartan, Montserrat, Manrope, Outfit
  - 硬朗无衬线体：Bebas Neue, Oswald, Barlow Condensed, Anton, Fjalla One
  - 经典优雅衬线体：Bodoni Moda, Playfair Display, Prata, Cormorant Garamond, DM Serif Display
  - 圆润童趣字体：Nunito, Quicksand, Varela Round, Fredoka, Baloo 2
  - 俏皮手写风格: Pacifico, Permanent Marker, Amatic SC, Caveat, Luckiest Guy
2. 颜色策略：
  - 标题色（Heading Color）：必须使用品牌主色或反白色；当标题底部颜色是品牌主色或同色系时，自动触发"灵活反白"；其次考虑使用品牌主色同色系颜色（禁止接近黑色的颜色，颜色不能过深）
  - 正文色（Body Color）：与标题色区分，确保可读性
  - ⚠️ 输出格式注意：颜色策略输出格式为 ["Heading Color"：颜色值] 和 ["Body color"：颜色值]，这是颜色定义而非文本内容
3. 灵活反白权限：当使用深色背景或纯品牌色色块时，授权切换为哑光白（#FFFFFF）文本
4. 排版限制：统一为非斜体（Non-italic），行距适中（standard leading）
输出要求：严格按照下方「输出格式」输出完整 JSON，禁止输出任何解释性文字或代码块标记。
输出：完整的 textgen prompt 字符串
用途：作为步骤 3 的 prompt 输入

步骤 3：调用 linkfox-aigc-textgen 执行视觉推理

输入：步骤 2 的 prompt、步骤 1 的 imageUrlList
操作：按 linkfox-aigc-textgen SKILL.md 的调用方式调用 textgen 执行视觉推理。本步骤产出的内容要回读进上下文做字段提取（步骤 4），不链式拼进下游出图，因此用 textgen 的默认模式（不是 --content-only）：把下列字段写成 JSON 参数文件，经 --stdin 传入运行，再解析 stdout。<textgen根目录> 通过 skill:linkfox-aigc-textgen 解析其 SKILL.md 所在目录的绝对路径取得；<本skill根目录> = 本 SKILL.md 所在目录的绝对路径。
⚠️ 中间参数文件落到会话 data/ 目录。先取目录：
bash
```
DATADIR=$(python <本skill根目录>/scripts/save_brand_gene.py --datadir)
```
⚠️ 构造 brand_gene_params.json 必须用 Write 工具写到 $DATADIR/brand_gene_params.json（prompt 含引号、反斜杠等特殊字符，shell heredoc 内嵌 JSON 易解析失败）。若走命令行生成，只用 python -c 配合 json.dumps，不要手拼 JSON 字符串。
bash
```
python <textgen根目录>/scripts/aigc_textgen.py --stdin < "$DATADIR/brand_gene_params.json"
```
JSON 参数文件包含以下字段：
- prompt：步骤 2 组装的品牌视觉基因提取指令（含「输出格式」要求）
- imageUrls：步骤 1 输出的 imageUrlList
- model：GEM_3_1_PRO（需要视觉理解与复杂推理能力）
- thinkingLevel：high
输出：解析 textgen stdout 得到 content（解析方式按 linkfox-aigc-textgen SKILL.md 的「输出契约」）。
用途：作为步骤 4 的组装原料

Show full SKILL.md (195 more words)Show less

步骤 4：组装 brandGeneJson

输入：步骤 3 解析出的 content（换行可能为 ⏎ 占位符，提取前先还原为换行符）
操作：从该 content 中提取品牌视觉基因各字段，严格按照下方「输出格式」自行组装为 brandGeneJson
缺失字段兜底（强制）：组装后必须逐一核对「输出格式」中的全部字段是否齐全。若模型输出遗漏了某字段（实测最易漏 背景策略-光影 与 Brand Injection（品牌植入）），不得直接交付残缺 JSON，须按以下顺序兜底补齐：
1. 优先从 content 其余文字中归纳推断该字段的合理值；
2. 无可推断内容时，结合已确定的主色 / 风格定义生成一句与整体调性一致的兜底描述（如光影按"自然柔和侧光、暖色温、增强立体感"，品牌植入按"主色作点缀、Logo 低调融入道具"）。最终 brandGeneJson 必须字段齐全，禁止出现缺字段或字段值为空串。
输出：brandGeneJson（长度为 1 的 JSON 列表，字段齐全）
落盘（强制）：组装完成后必须写入会话目录并保留路径供下游复用：
1. 用 Write 工具将 brandGeneJson 写到 $DATADIR/brand_gene_assembled.json（DATADIR 同步骤 3）；或
2. 运行落盘脚本（推荐，自动注册 _meta.json）：
  bash
```
python <本skill根目录>/scripts/save_brand_gene.py "$DATADIR/brand_gene_assembled.json"
```
  stdout 会打印 Saved full response: <绝对路径> (<N> bytes)——将该绝对路径记入上下文，后续 S3 套图编排通过 --brand-gene-file <绝对路径> 或 manifest 的 brand_gene_json 消费。
用途：透传给下游出图链路（linkfox-aigc-imagegen-cloth 的种草图/卖点图/A+图等类型 / linkfox-aigc-imagegen-product 等）作为 brandGeneJson 参数

产物落盘

产物	目录	说明
`brand_gene_params.json`	`<session>/data/`	textgen 入参（步骤 3 中间文件）
`brandGeneJson` 最终结果	`<session>/data/linkfox-aigc-imagegen-brand-gene-extract-<ts>.json`	经 `save_brand_gene.py` 落盘，供套图 S3 与单张 `--brand-gene-file` 复用

路径协议：<cwd>/linkfox/<YYYY-MM-DD>/<session>/data/（<session> 取自 SESSION_ID），与仓库 CLAUDE.md「输出文件位置」一致。

核心规则

A. 主色和字体逻辑

如果 brandColor 有值 → 输出 JSON 中 "brandColor (品牌主色)" 直接用该值
如果 fontStyle 有值 → 输出 JSON 中 "字体风格" 直接用该值
如果哪个值为空 → 该值用核心变量里的规则来自动提取

B. 其他值逻辑

"背景策略-风格定义"、"颜色策略-Heading" 等字段，默认都用核心变量的规则来获取，不受 brandKey 中 brandColor/fontStyle 的透传影响。

输出格式

严格按照以下 JSON 格式输出，输出为长度为 1 的列表：

json

[
  {
    "brandColor": {
      "brandColor (品牌主色)": "颜色名称与HEX值",
      "背景策略-风格定义": "基于 salesRegion 的风格描述",
      "背景策略-场景关键词": "关键词1, 关键词2, ...",
      "背景策略-光影": "光影氛围描述",
      "Brand Injection（品牌植入）": "品牌元素如何植入场景"
    },
    "fontStyle": {
      "字体策略": "选定的字体家族名称",
      "字体风格": "选定的具体字体名称",
      "颜色策略-Heading": "[\"Heading Color\"：颜色值/反白逻辑]",
      "颜色策略-Body/Sub": "[\"Body color\"：颜色值]",
      "灵活反白": "You are authorized to switch to Matte White (#FFFFFF) text whenever using a dark background or a solid brand-color panel.",
      "排版": "Non-italic, standard leading"
    }
  }
]

错误处理

情况	处理
images 为空	停止执行，提示用户上传至少 1 张商品图片
brandKey 完全为空	所有字段按默认值填充（salesRegion=美国、language=英文、platform=亚马逊），主色与字体走自动提取
商品为纯黑白灰且无法提取彩色主色	允许使用黑白灰作为主色（黑白灰协议的唯一豁免条件）

调用方式

本 skill 由套图编排层在步骤三中调用，调用时机：

首次调用：上下文中没有进行过品牌基因样式提取时
重新调用：用户明确要求修改品牌基因（场景 G）时

复用规则：同一上下文中提取结果可复用，无需重复调用。

解决认证和算力问题

发生以下异常情况时，采用 references/onboarding.md 引导解决问题：

异常情况

未配置API Key：环境变量未配置 LINKFOX_AGENT_API_KEY，也未配置 LINKFOXAGENT_API_KEY。
响应401或402状态码
响应提示算力或余额不足：消息含"算力余额不足/计费不足/余额不足/quota exceeded/insufficient balance/套餐到期/需充值/请充值"，或类似含义的内容。

已知局限

品牌主色提取基于 GEM_3_1_PRO 对商品图片的视觉理解，可能与专业设计师判断有偏差
字体风格限定在预设的 5 类 25 款字体中，无法选择库外字体
背景策略的文化本土化依赖 salesRegion 的语义理解，非结构化地域数据库
品牌基因 JSON 必须经 save_brand_gene.py 落盘到会话 data/，不可仅存于对话上下文
依赖 linkfox-aigc-textgen skill 可用；若 textgen 调用失败，品牌基因提取无法完成

Files

SKILL.md and 3 other files (scripts, references) in skills/linkfox-aigc-imagegen-brand-gene-extract of linkfox-ai/linkfox-skills.

SKILL.md
references/onboarding.md
scripts/onboarding.py
scripts/save_brand_gene.py

Open the folder on GitHubat commit 38fef04

Compare with similar skills

Linkfox Aigc Imagegen Brand Gene Extract next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Linkfox Aigc Imagegen Brand Gene Extract compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Linkfox Aigc Imagegen Brand Gene Extract this skilllinkfox-ai/linkfox-skills	107	—	~2k	Automated safety check: Pass	MIT	27 days ago
Logo Generatorop7418/logo-generator-skill	2.2k	—	~1.8k	Automated safety check: Notes	None	5 mo ago
Web Asset Generatoralonw0/web-asset-generator	514	1 repos	~6.6k	Automated safety check: Pass	MIT	8 mo ago
Image Generationonyx-dot-app/onyx	32k	1 repos	~1.7k	Automated safety check: Pass	Custom licence	yesterday
Gemini Image Generatordair-ai/dair-academy-plugins	614	2 repos	~3.5k	Automated safety check: Notes	MIT	2 mo ago
Logo CreatorReScienceLab/opc-skills	1.8k	—	~1.5k	Automated safety check: Pass	Apache-2.0	yesterday

Similar skills

Logo Generator
op7418/logo-generator-skill
Generate professional SVG logos and high-end showcase images.
2.2k GitHub stars~1.8k tokensUpdated 5 mo ago
Media & CreativeAuto-check: notes
Web Asset Generator
alonw0/web-asset-generator
Generate web assets including favicons, app icons (PWA), and social media meta images (Open Graph) for Facebook, Twitter, WhatsApp, and LinkedIn.
514 GitHub starsUsed in 1 repo~6.6k tokens
Media & CreativeAuto-check passed
Image Generation
onyx-dot-app/onyx
Generate or edit raster images (photos, illustrations, textures, sprites, mockups, logos, infographics) using the workspace's configured image-generation provider via onyx-cli image.
32k GitHub starsUsed in 1 repo~1.7k tokens
Media & CreativeAuto-check passed
Gemini Image Generator
dair-ai/dair-academy-plugins
Generates and edits images with Google's Gemini Nano Banana Pro model through the Gemini API, including photo edits and multi-image composition.
614 GitHub starsUsed in 2 repos~3.5k tokens
Media & CreativeAuto-check: notes
Logo Creator
ReScienceLab/opc-skills
Create logos using AI image generation. An agent skill from ReScienceLab/opc-skills.
1.8k GitHub stars~1.5k tokensUpdated yesterday
Media & CreativeAuto-check passed
Image Prompt Reverse
LunarXuan/image-prompt-reverse
Analyze user-provided reference images and reverse-engineer high-fidelity AI image-generation prompts.
467 GitHub stars~678 tokensUpdated 1 mo ago
Media & CreativeAuto-check passed

Questions about Linkfox Aigc Imagegen Brand Gene Extract

What does Linkfox Aigc Imagegen Brand Gene Extract do?

When should I use Linkfox Aigc Imagegen Brand Gene Extract?

Linkfox Aigc Imagegen Brand Gene Extract fits situations like: tasks that involve Image generation; tasks that involve Logo and visual identity.

How do I install Linkfox Aigc Imagegen Brand Gene Extract in Claude Code?

Run `npx skills add linkfox-ai/linkfox-skills --skill linkfox-aigc-imagegen-brand-gene-extract -a claude-code`. Or copy the skill folder (skills/linkfox-aigc-imagegen-brand-gene-extract in linkfox-ai/linkfox-skills) into .claude/skills/linkfox-aigc-imagegen-brand-gene-extract in your project. Claude Code loads it when a task matches its description.

How do I install Linkfox Aigc Imagegen Brand Gene Extract in Codex?

Run `npx skills add linkfox-ai/linkfox-skills --skill linkfox-aigc-imagegen-brand-gene-extract -a codex`. Or copy the skill folder (skills/linkfox-aigc-imagegen-brand-gene-extract in linkfox-ai/linkfox-skills) into .agents/skills/linkfox-aigc-imagegen-brand-gene-extract in your project. Codex loads it when a task matches its description.

Can I use Linkfox Aigc Imagegen Brand Gene Extract in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add linkfox-ai/linkfox-skills --skill linkfox-aigc-imagegen-brand-gene-extract -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/linkfox-aigc-imagegen-brand-gene-extract, .gemini/skills/linkfox-aigc-imagegen-brand-gene-extract, .github/skills/linkfox-aigc-imagegen-brand-gene-extract and .opencode/skills/linkfox-aigc-imagegen-brand-gene-extract in your project.

What does Linkfox Aigc Imagegen Brand Gene Extract need to run?

Going by SKILL.md and its folder, Linkfox Aigc Imagegen Brand Gene Extract needs Python for the scripts in its folder, the command-line tools its instructions call (python) and credentials named LINKFOX_AGENT_API_KEY and LINKFOXAGENT_API_KEY. Our summary lists: Python 3.

Does Linkfox Aigc Imagegen Brand Gene Extract access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Linkfox Aigc Imagegen Brand Gene Extract safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Linkfox Aigc Imagegen Brand Gene Extract use?

Linkfox Aigc Imagegen Brand Gene Extract is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Linkfox Aigc Imagegen Brand Gene Extract use?

About 2k tokens (SKILL.md is roughly 8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 500 tokens, read only when the agent opens those files.

What are the alternatives to Linkfox Aigc Imagegen Brand Gene Extract?

Skills that share tags, products or a category with Linkfox Aigc Imagegen Brand Gene Extract: Logo Generator (op7418/logo-generator-skill, 2.2k stars), Web Asset Generator (alonw0/web-asset-generator, 514 stars), Image Generation (onyx-dot-app/onyx, 32k stars) and Gemini Image Generator (dair-ai/dair-academy-plugins, 614 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Linkfox Aigc Imagegen Brand Gene Extract?

linkfox-ai (a GitHub user) maintains it in linkfox-ai/linkfox-skills, which has 107 GitHub stars. The repository holds 177 skills in this directory. The repository was last updated on September 14, 2026.

Source: linkfox-ai/linkfox-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Linkfox Aigc Imagegen Brand Gene Extract

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

品牌基因样式提取（Brand Gene Extract）

适用场景

不适用

输入参数

brandKey 字段说明

流水线步骤

步骤 1：参数解析与决策路由

步骤 2：组装品牌视觉基因提取 prompt

步骤 3：调用 linkfox-aigc-textgen 执行视觉推理

步骤 4：组装 brandGeneJson

产物落盘

核心规则

A. 主色和字体逻辑

B. 其他值逻辑

输出格式

错误处理

调用方式

解决认证和算力问题

异常情况

已知局限

Files

Compare with similar skills

Similar skills

More from linkfox-ai/linkfox-skills

Related

Questions about Linkfox Aigc Imagegen Brand Gene Extract