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 ChenShuo2004/cs-skills --skill cs-xiaohuang-skillgit clone --depth 1 https://github.com/ChenShuo2004/cs-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/chenshuo2004/cs-skills/cs-xiaohuang-skill)<a href="https://agentmods.dev/skills/chenshuo2004/cs-skills/cs-xiaohuang-skill"><img src="https://agentmods.dev/badge/skills/chenshuo2004/cs-skills/cs-xiaohuang-skill/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/chenshuo2004/cs-skills/cs-xiaohuang-skill"><img src="https://agentmods.dev/badge/skills/chenshuo2004/cs-skills/cs-xiaohuang-skill.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 | $0.00153 | $0.01933 |
| Opus 5 | $0.00077 | $0.00966 |
| Sonnet 5 | $0.00031 | $0.00387 |
| Haiku 4.5 | $0.00015 | $0.00193 |
Grade A, and why
cs-xiaohuang-skill 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 11d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
小黄 IP 与正文配图
小黄就是“有温度”的固定品牌角色。这个 skill 是它的唯一入口:既把中文内容的判断、变化、关系或隐喻画成正文配图,也稳定生成、编辑和延展小黄的品牌 IP 资产。
始终遵守:可以换动作、场景、媒介和画法;不可以换掉角色身份。
先读参考
所有生图、编辑或角色评估任务都必须查看 assets/reference-xiaohuang.png;它是唯一的身份锚点。再按任务读取,避免一次加载无关内容:
- 身份、标准图、修复、三视图或一致性检查:
references/character-dna.md。 - 2D/3D、黑白、动作表情、多形态、联名或风格迁移:
references/media-and-variants.md。 - 品牌 IP 生成或编辑:
references/ip-prompt-templates.md。 - 正文配图:
references/style-dna.md、references/xiaohuang-ip.md、references/composition-patterns.md、references/prompt-template.md。 - 交付前:
references/qa-checklist.md。
两种工作模式
1. 正文配图
- 配图规划:分析文章怎么配图、哪些段落值得配图时,先输出 shot list,不生成图片。
- 直接生成:为每个认知锚点单独调用
image_gen;不要把多张配图拼成一张。 - 局部编辑:只改标题、错字、标注或指定元素;保持其余构图、比例与风格不变。
2. 品牌 IP 延展
- 角色延展:标准图、动作、表情、三视图、表情包、场景植入和品牌海报插画。
- 媒介转换:保持角色身份,将 2D 转为 3D、线稿、软胶、树脂或用户指定媒介。
- 风格迁移与联名:只迁移视觉语言;与其他角色共创时,双方身份必须分别可辨。
- 身份修复:按 DNA 修复错误轮廓、爱心天线、面部或四肢,而非重新设计角色。
正文配图工作流
- 消化内容。 读取用户提供的文章、笔记、链接、Markdown、Notion 内容、截图或单个观点;区分核心观点、认知转折、可视化关系和不需要配图的段落。
- 选择认知锚点。 不要平均配图。优先选择能帮助理解的判断、前后变化、输入输出、分流、瓶颈、反馈、角色状态或核心隐喻。
- 先做配图策略。 在未明确要求生成时,给出 3~6 张 shot list;短内容可为 1~3 张,长文通常不超过 8 张。每张包含:插入位置、核心意思、构图类型、小黄的动作、主要物件与建议标注词。
- 发明新的隐喻。 将抽象概念转换成可见动作和低科技物件;每次从当前文章重新设计画面,不复用之前的案例构图。
- 逐张生成。 每张图只表达一个结构。使用
references/prompt-template.md组合提示词,并让小黄承担解释概念的关键动作。 - 检查与迭代。 按
references/qa-checklist.md检查。中文错字多时,减少标注后重生成;元素过多时,删到只剩一个动作与少量物件。 - 保存交付。 当用户在 workspace 中工作时,将成图保存至
assets/<article-slug>-illustrations/,按01-topic.png、02-topic.png递增命名;不覆盖原图,除非用户明确要求。
品牌 IP 延展工作流
- 锁定输入角色。 明确区分身份参考、风格参考、场景参考和编辑目标;不要把所有输入图都当成编辑目标。
- 写出不变量与变量。 不变量是轮廓逻辑、爱心天线、面部比例、细四肢与暖色体系;变量是动作、表情、场景、构图、媒介、光线和画法。
- 选择任务结构。 先决定是角色延展、媒介转换、风格迁移、联名共创还是身份修复;多版本必须改变结构,不只换材质。
- 单资产生成或编辑。 用户明确要求生成时直接调用可用生图工具;每个独立资产单独生成,局部问题只做单一目标编辑。
- 检查与迭代。 按 QA 清单检查。两个及以上身份锚点失败时重新设计;只有一个局部失败时固定不变量后局部修复。
- 保存交付。 保存到用户指定目录;未指定时使用清晰、可排序的文件名,且不覆盖旧资产。报告用途、媒介、路径、最稳版本与仍存风险。
统一硬规则
- 角色 DNA 优先于画风。小黄必须保持暖黄不规则种子形身体、空心爱心天线、黑色竖椭圆眼、小弧线嘴、腮红和细黑四肢;不得变成梨子、鸡蛋、水滴、动物或通用黄色吉祥物。
- 正文配图默认 16:9 横版、暖白底、黑色轻手绘线条和充足留白;一张只解释一个关系,标注最多 6 处,小黄必须承担关键动作。
- 品牌 IP 默认使用暖白背景与克制的 2D 手绘蜡笔 / 油画棒 / 彩铅质感;只有用户要求时才切换到 3D、黑白或其他媒介。
- 不复制他人 IP、受保护角色或旧图构图。风格迁移只迁移线条、材质、色彩和氛围;联名时不得合并轮廓或交换身份标志。
- 不用于复杂架构图、可编辑矢量图、PPT 式信息图或 ChatCut 视频策划。品牌角色主导的插画、场景图和海报资产属于本 skill 范围。
What ships with it
23 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 367 B
- assets/examples/01-cognitive-anchor.png 1809 KB
- assets/examples/02-one-idea.png 1668 KB
- assets/examples/03-relation-reveal.png 1727 KB
- assets/examples/04-negative-space.png 2001 KB
- assets/examples/05-metaphor-translation.png 1886 KB
- assets/examples/06-concise-labels.png 1895 KB
- assets/examples/07-quality-check.png 1976 KB
- assets/examples/ip/00-character-system.png 415 KB
- assets/examples/ip/01-standard-2d.png 1356 KB
- assets/examples/ip/02-light-the-lamp.png 1399 KB
- assets/examples/ip/03-soft-vinyl-3d.png 1306 KB
- assets/examples/ip/04-shape-directions.png 1103 KB
- assets/reference-xiaohuang.png 406 KB
- README.md 3.9 KB
- references/character-dna.md 2.4 KB
- references/composition-patterns.md 1.1 KB
- references/ip-prompt-templates.md 4.1 KB
- references/media-and-variants.md 2.1 KB
- references/prompt-template.md 2.2 KB
- references/qa-checklist.md 2.2 KB
- references/style-dna.md 1.3 KB
- references/xiaohuang-ip.md 1.1 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.
- 11d ago First seen · 80 lines · 153 tokens per session scan A be4b4df8cae8
cs-xiaohuang-skill is a skill published in the GitHub repository ChenShuo2004/cs-skills (142 stars, last pushed 8d ago), licensed MIT. It adds 153 tokens to every session and 1,933 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
html-ppt-zhangzara-retro-zine
A neighborhood zine on the disappearing corner shops — portraits, voices, and what a block loses when they close. Built as a decision-grade story deck for community, local readers.
html-ppt-zhangzara-studio
A photography studio's portfolio-and-rate deck — the signature work, the process, and the packages that win the brief. Built as a decision-grade design craft deck for prospective clients.
motion-frames
A single-frame motion-design composition with looping CSS animations — rotating type ring, animated globe, ticking timer, parallax labels. Renders as a hero video poster you can hand straight to HyperFrames or any keyframe-based exporter. Use when the brief asks for "motion design", "animated hero", "loop", "video…
webgl-halftone-drift
A self-contained WebGL2 hero: a flowing field screened through a rotated halftone dot grid into a duotone print aesthetic; move the cursor to bend the drift.
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.
motion-graphics
A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…