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-clothgit 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-cloth)<a href="https://agentmods.dev/skills/linkfox-ai/linkfox-skills/linkfox-aigc-imagegen-cloth"><img src="https://agentmods.dev/badge/skills/linkfox-ai/linkfox-skills/linkfox-aigc-imagegen-cloth/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-cloth"><img src="https://agentmods.dev/badge/skills/linkfox-ai/linkfox-skills/linkfox-aigc-imagegen-cloth.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 | $0.00158 | $0.06196 |
| Opus 5 | $0.00079 | $0.03098 |
| Sonnet 5 | $0.00032 | $0.01239 |
| Haiku 4.5 | $0.00016 | $0.00620 |
Grade A, and why
linkfox-aigc-imagegen-cloth 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- linkfox-aigc-imagegen-product — 92% identical, 86 lines differ
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.
服饰图生成
统一入口：服饰 / 模特类商品（上装、下装、连衣裙、外套、鞋帽等）的全类型电商出图能力。单张直出 & 套图编排都从这一个 skill 进入。
入口路由
| 条件 | 路径 | 操作 |
|---|---|---|
| 只要一张特定类型的图（如"做一张模特图"） | 单张直出 | 确定 type → Read 对应 references/types/<type>.md → 执行共享流水线 |
| 要多张 / 多类型 / 套图（如"做一套图""出5张图"） | 套图编排 | Read references/runtime/00-index.md → 按步 Read 01-plan / 02-confirm → 调 scripts/run_collection_pipeline.py 三阶段（plan / dispatch / summary，agent 顺序发 3 个 Bash；dispatch 在 skill 层用 ThreadPoolExecutor 并发跑 scripts/run_one_task.py，agent 自己不并发；禁止 Read maintainer/collection/ 或套图阶段 Read types/*.md） |
类型路由表
| type | 名称 | 与卖点关联 | 是否有画面描述 | 默认比例 | 支线 | 是否走 textgen | 详情 reference |
|---|---|---|---|---|---|---|---|
| WHITE_BG | 白底图（隐形模特） | 否 | 否 | 1:1 | ①静态直出 | 否 | references/types/white-bg.md |
| MODEL_IMAGE | 模特图 | 否 | 是 | 1:1 | ②占位符直出 | 否 | references/types/model-image.md |
| SCENE | 种草图 | 是 | 是 | 1:1 | ③textgen 改写 | 是 | references/types/scene.md |
| SELLING_POINT | 卖点图 | 是 | 是 | 1:1 | ③textgen 改写 | 是 | references/types/selling-point.md |
| PREMIUM_APLUS | 高级A+图 | 是 | 是 | 1464:600 | ③textgen 改写 | 是 | references/types/aplus.md |
| STANDARD_APLUS | 普通A+图 | 是 | 是 | 970:600 | ③textgen 改写 | 是 | references/types/aplus.md |
| PHONE_APLUS | 手机A+图 | 是 | 是 | 600:450 | ③textgen 改写 | 是 | references/types/aplus.md |
| SIZE | 尺码图 | 否 | 是 | 1:1 | 两阶段：①阶段1=③textgen 前置分析 + ②阶段2=占位符直出 | 阶段1是/阶段2否 | references/types/size.md |
确定 type 后，必须 Read 对应的 type reference 文件获取该类型走哪条支线、步骤 2 差异逻辑和运行时模板来源，禁止跳过。
不适用
- 非服饰类实物商品（美妆、数码、家居、食品等）→ 走
linkfox-aigc-imagegen-product系列。 - 纯图片编辑操作（换背景、去水印、换角度等已有明确创意方向的操作）→ 走
linkfox-aigc-imagegen。 - 已有模特图换姿势 / 换动作裂变（模特裂变）→ 不在本范围（业务方上游构造 posePrompt，不读字典）。
- 纯文字生成 →
linkfox-aigc-textgen。 - 视频生成 →
linkfox-aigc-videogen。
共享流水线
所有类型都走同一条 3 步流水线（尺码图为两阶段，见下），步骤 2 的差异由各 type reference 指定走哪条支线。
三条支线（步骤 2 的差异本质）
| 支线 | 机制 | 是否填占位符 | 是否调 textgen | 是否过敏感词 | 适用类型 |
|---|---|---|---|---|---|
| ① 静态直出 | 用 scripts/build_imagegen_prompt.py --type WHITE_BG 从 white-bg.md 动态提取静态正文作为最终 prompt |
否 | 否 | 否 | WHITE_BG |
| ② 占位符直出 | 模板填占位符后直接出图（用 scripts/build_imagegen_prompt.py） |
是 | 否 | MODEL_IMAGE 否 / SIZE 阶段2 末尾追加规避指令 | MODEL_IMAGE、SIZE 阶段2 |
| ③ textgen 改写 | 模板填占位符 → linkfox-aigc-textgen 改写出最终 prompt（用 scripts/build_textgen_params.py） |
是 | 是 | SCENE 否 / 卖点·A+ 是 / SIZE 阶段1 否 | SCENE、SELLING_POINT、*_APLUS、SIZE 阶段1 |
What ships with it
41 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.
- references/maintainer/collection/data-fields.md 2.5 KB
- references/maintainer/collection/README.md 525 B
- references/maintainer/collection/S0-scene-routing.md 11 KB
- references/maintainer/collection/S1-content-reasoning.md 9.8 KB
- references/maintainer/collection/S2-plan-confirm.md 4.6 KB
- references/maintainer/collection/S3-dispatch.md 7.0 KB
- references/maintainer/collection/workflow.md 2.6 KB
- references/onboarding.md 2.0 KB
- references/runtime/00-index.md 2.4 KB
- references/runtime/01-plan.md 1.9 KB
- references/runtime/02-confirm.md 5.7 KB
- references/runtime/03-deliver.md 17 KB
- references/types/aplus.md 4.4 KB
- references/types/model-image.md 4.8 KB
- references/types/scene.md 4.7 KB
- references/types/selling-point.md 4.4 KB
- references/types/size.md 7.2 KB
- references/types/white-bg.md 6.7 KB
- scripts/build_imagegen_prompt.py 9.9 KB runs code
- scripts/build_textgen_params.py 10 KB runs code
- scripts/collection_pipeline/__init__.py 0 B runs code
- scripts/collection_pipeline/brand_gene.py 3.0 KB runs code
- scripts/collection_pipeline/config.py 2.2 KB runs code
- scripts/collection_pipeline/plan.py 7.1 KB runs code
- scripts/collection_pipeline/runner.py 4.5 KB runs code
- scripts/collection_pipeline/single_task.py 18 KB runs code
- scripts/collection_pipeline/summary.py 4.8 KB runs code
- scripts/collection_pipeline/templates/brand-gene-extract.txt 1.3 KB
- scripts/collection_pipeline/templates/s1-reasoning-cloth.txt 1.5 KB
- scripts/collection_pipeline/templates/s1-reasoning-product.txt 1.0 KB
- scripts/collection_pipeline/utils.py 29 KB runs code
- scripts/onboarding.py 24 KB runs code
- scripts/run_collection_pipeline.py 444 B runs code
- scripts/run_one_task.py 1.3 KB runs code
- scripts/save_image_plan.py 11 KB runs code
- scripts/templates/model-image.txt 4.1 KB
- scripts/templates/scene.txt 5.8 KB
- scripts/templates/selling-point-aplus.txt 13 KB
- scripts/templates/size-common.txt 6.0 KB
- scripts/templates/size-pre-analysis.txt 2.7 KB
- scripts/templates/size-three-column.txt 7.3 KB
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 · 158 tokens per session scan A 454830ecd336
linkfox-aigc-imagegen-cloth is a skill published in the GitHub repository linkfox-ai/linkfox-skills (101 stars, last pushed 21d ago), licensed MIT. It adds 158 tokens to every session and 6,196 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
beat-sync-reel
Generates Instagram Reels where product image cuts are synced to audio beats. Accepts audio as a local file, URL, or search query. Uses librosa for beat detection, FFmpeg Ken Burns for scene animation, and Pillow for text overlays. No AI video generation — fully free, fast, and scalable.
ecom-details-image
A planning tool for e-commerce product visuals, including main-image concepts, scene ideas, detail-page directions, and prompts for image-generation systems.
byted-livesaas-master
A control tool for managing business livestreams, including rooms, comments, viewers, product cards, coupons, and live-session settings.
byted-ind-ecom-product-video-prompt
A structured prompt-writing guide for creating e-commerce product videos with Seedance 2.0. It turns one or more product images into a product showcase script using scene settings, timed shots, and output constraints.
tiktok-shop-branding
Brand building and positioning on TikTok Shop. Brand identity development, content pillars, community engagement, brand storytelling, and authenticity strategies. Use when the user asks about TikTok branding, brand building, brand identity, or brand positioning on TikTok.
amazon-listing-images
Amazon product listing image strategy and optimization. Comprehensive shot planning, infographic design, lifestyle photography, mobile optimization, and conversion-focused visual content. Use when the user asks about Amazon images, product photography, visual optimization, or listing conversion.