Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add linkfox-ai/linkfox-skills --skill linkfox-aigc-imagegen-brand-gene-extractgit clone --depth 1 https://github.com/linkfox-ai/linkfox-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/linkfox-ai/linkfox-skills/linkfox-aigc-imagegen-brand-gene-extract)<a href="https://agentmods.dev/skills/linkfox-ai/linkfox-skills/linkfox-aigc-imagegen-brand-gene-extract"><img src="https://agentmods.dev/badge/skills/linkfox-ai/linkfox-skills/linkfox-aigc-imagegen-brand-gene-extract/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/linkfox-ai/linkfox-skills/linkfox-aigc-imagegen-brand-gene-extract"><img src="https://agentmods.dev/badge/skills/linkfox-ai/linkfox-skills/linkfox-aigc-imagegen-brand-gene-extract.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00164 | $0.04066 |
| Opus 5 | $0.00082 | $0.02033 |
| Sonnet 5 | $0.00033 | $0.00813 |
| Haiku 4.5 | $0.00016 | $0.00407 |
Grade A, and why
linkfox-aigc-imagegen-brand-gene-extract scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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：
- 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
- 解析
- 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）
-
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）
-
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"
- 背景策略-风格定义：根据
-
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 238 lines · 164 tokens per session scan A fab6c6b4d43a
linkfox-aigc-imagegen-brand-gene-extract is a skill published in the GitHub repository linkfox-ai/linkfox-skills (101 stars, last pushed 22d ago), licensed MIT. It adds 164 tokens to every session and 4,066 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.