Borrowing it
Nothing to install: this file belongs to Peiiii/nextclaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Peiiii/nextclaw/master/.agents/skills/nextclaw-product-visual-assets/SKILL.mdgit clone --depth 1 https://github.com/Peiiii/nextclawWrote 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/peiiii/nextclaw/nextclaw-product-visual-assets)<a href="https://agentmods.dev/skills/peiiii/nextclaw/nextclaw-product-visual-assets"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/nextclaw-product-visual-assets/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/peiiii/nextclaw/nextclaw-product-visual-assets"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/nextclaw-product-visual-assets.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 | $0.00115 | $0.01782 |
| Opus 5 | $0.00057 | $0.00891 |
| Sonnet 5 | $0.00023 | $0.00356 |
| Haiku 4.5 | $0.00012 | $0.00178 |
Grade A, and why
nextclaw-product-visual-assets 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 yesterday.
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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NextClaw 产品视觉资产
目标
让对外视觉既能准确证明真实产品价值，又形成值得传播的完成品。skill 负责选择证据、艺术方向、生成编排和验收；确定性脚本负责截图、同步或渲染。开始前先读取 Wiki 中的用户内容边界，隔离内部过程、隐私、调试状态和不成熟结论。
选择一个模式
- 产品截图与外部资产：更新稳定界面、精选真实任务、README/landing 镜像、二维码或指标图时，读取 产品截图与外部资产。
- 整页宣传工作室：把新功能、主题、版本或真实场景做成精美的单文件 HTML showcase/campaign 页面时，执行下方流程。
- AI 辅助单张视觉：只需一张概念主图或截图包装时，使用
imagegen；真实 UI 仍由原始截图承担证据，概念图不得冒充产品界面。
Stable/major 版本传播图在选图或生成后、绑定 release review 前，读取 版本传播图质量门。
只选择当前任务需要的模式，不批量读取其它参考。
整页宣传工作室
主产物是一件完整 HTML 宣传作品：开场判断、渠道文案预览、传播卡片、真实证据和设计说明共同组成同一套叙事。X、官网、README 或社区帖只是可选渠道模块，不是页面本身的全部目的。
-
冻结命题与内容骨架：用一句话写清用户应记住什么，再列 1–3 个可核查 claim。为每个模块声明它在故事中的任务、提供的信息增量、用户看完应带走的结论，以及承载结论的证据或解释；回答不了这四项的模块直接删除或重写，禁止用漂亮背景包装空内容。命题应服务 NextClaw 作为长期个人智能搭档或个人操作层的真实价值，不能只写“更高级、更震撼”。
-
截图计划：先决定 claim 需要“完整窗口”“完整功能面板”还是“完整图 + 有来源的细节图”，再选择或重新采集素材。每张事实素材都要在
capture中声明主体、完整性、裁切来源和隐私检查；不能先拿现成图再随意找一个位置塞进去。读取 宣传页内容与证据合同。 -
裁切决策：完整证据保持原始画面；局部图必须声明来源完整图和归一化
cropRegion，只能用于解释细节。没有完整图时不得生成事实卡片。 -
选择区块原型：先读取 宣传页区块布局原型目录，根据内容角色、信息数量、顺序关系和媒体形状筛选最多三个候选，并在
layoutDecision中记录最终选择与理由。再在 card 的evidence中明确单图、连续多图或“完整图 + 细节图”，固定使用contain并继承源图比例。读取 宣传页构图与留白合同，约束文字、截图、主动留白、安全区和多图关系；截图自身成为圆角卡片，不默认再套窗口壳。 -
确定艺术方向：从产品本身提取颜色、材质、留白和字体气质。需要生成/编辑背景、使用参考图或准备提示词时，读取 宣传页艺术方向与生图提示词，并使用
imagegen。AI 只生成背景、纹理、装饰或明确标注的概念视觉，不伪造产品 UI。 -
编排整页：先按内容推进确定模块数量，再决定构图。默认包含开场判断、可选渠道预览、2–4 张传播卡片、证据映射和简短设计说明；按传播目标增删，不强行保留 X 帖子，也不为凑满卡片保留只有一句泛化口号的模块。背景只提供氛围、分区和视线引导，不算内容。
-
生成：复制并修改样例 brief，然后运行：
node scripts/render-promo-page.mjs --brief <brief.json> --out <preview.html>模板位于
assets/promo-page-template.html。渲染器会把本地图片嵌入 HTML，并阻断缺少布局决策、原型与实现不相容、claim 与截图不匹配、事实卡片缺少完整截图或试图用全幅裁切冒充产品证据的页面。 -
验收：打开页面检查桌面和窄屏；逐条核对“选图—裁切—比例—拼接—可读性”，确认每个事实 claim 都能在完整截图中找到、截图关键对象足够大、多图顺序有意义，并排除私人信息、失败态、加载态、旧版本误导或 AI 伪造 UI。交付前必须执行构图参考中的“五星挑刺法”，并在最终回复中公开每个模块的五个问题、分数、模块指数、全局排序和未解决项；不能因为结果达到交付线就省略问题。用户说“挑毛病”“按之前的方法审”或“五星挑刺”时，直接召回同一方法。纯审美由用户确认，内容代表性由执行者先证明。
What ships with it
12 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.
- agents/openai.yaml 325 B
- assets/promo-page-island-atmosphere-reference.webp 83 KB
- assets/promo-page-island-theme-brief.example.json 4.4 KB
- assets/promo-page-island-workspace-reference.png 3303 KB
- assets/promo-page-template.html 19 KB
- references/product-screenshot-and-external-assets.md 5.2 KB
- references/promo-page-art-direction-and-image-prompts.md 3.6 KB
- references/promo-page-composition-and-spacing.md 16 KB
- references/promo-page-content-evidence.md 6.3 KB
- references/promo-page-layout-archetypes.md 7.9 KB
- references/release-visual-quality.md 2.1 KB
- scripts/render-promo-page.mjs 19 KB runs code
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.
- yesterday Changed d646ff60a0f2
- 7d ago Changed · +2 lines f1f87c423801
- 12d ago First seen · 56 lines · 115 tokens per session scan A 9c9702a59d9f
nextclaw-product-visual-assets is a skill published in the GitHub repository Peiiii/nextclaw (256 stars, last pushed today), licensed MIT. It adds 115 tokens to every session and 1,782 once invoked, about $0.0006 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
algorithmic-art
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
infographic
A guide for creating infographics with only HTML and CSS. Infographics present structured information visually, such as timelines, comparisons, funnels and organisation charts.
slack-gif-creator
Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack.".
mermaid-diagram
A guide for writing Mermaid code for structured diagrams. Mermaid is a text format that can describe diagrams such as flowcharts, architecture diagrams and timelines.
skin-creator
Create and apply a two-asset LobsterAI visual skin from the user's style description. Use only when the AI Skin Designer kit supplies the structured skinpack workflow marker; do not use for ordinary theme or image requests.