huashu-slide-doubao

huashu-slide-doubao is a skill for Claude Code, Codex from alchaincyf/huashu-slide-doubao. It costs 116 tokens per session (22,304 once invoked), scanned A, original, MIT.

A Chinese-language skill for producing visual materials such as presentations, public-account images, and video covers in the Doubao environment. It uses Doubao's built-in image generator and is intended for that environment only.

In plain words
What is it for?
Use it to create PPT or Keynote slides, HTML decks, public-account cover or article images, and Bilibili or YouTube video covers.
Why use it?
It gives these different formats a shared visual direction and production process, including guidance on layout, branding, text density, and safe areas.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: mentions CLAUDE.md; built for openclaw.

Good fit Use it to create PPT or Keynote slides, HTML decks, public-account cover or article images, and Bilibili or YouTube video covers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alchaincyf/huashu-slide-doubao/huashu-slide-doubao
Install

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.

Any agent
npx skills add alchaincyf/huashu-slide-doubao --skill huashu-slide-doubao
Clone the repo
git clone --depth 1 https://github.com/alchaincyf/huashu-slide-doubao

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for huashu-slide-doubao

README.md
[![agentmods](https://agentmods.dev/badge/skills/alchaincyf/huashu-slide-doubao/huashu-slide-doubao/github.svg)](https://agentmods.dev/skills/alchaincyf/huashu-slide-doubao/huashu-slide-doubao)
Your own site
<a href="https://agentmods.dev/skills/alchaincyf/huashu-slide-doubao/huashu-slide-doubao"><img src="https://agentmods.dev/badge/skills/alchaincyf/huashu-slide-doubao/huashu-slide-doubao/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.

agentmods 80×15 button for huashu-slide-doubao

Your own site · 80×15
<a href="https://agentmods.dev/skills/alchaincyf/huashu-slide-doubao/huashu-slide-doubao"><img src="https://agentmods.dev/badge/skills/alchaincyf/huashu-slide-doubao/huashu-slide-doubao.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 22,304 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00116 $0.22304
Opus 5 $0.00058 $0.11152
Sonnet 5 $0.00023 $0.04461
Haiku 4.5 $0.00012 $0.02230

Measured 12d ago against content hash b19a18c4f1c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

huashu-slide-doubao scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- 豆包 `image_gen` 返回的是图片 URL,不是本地文件。生成后必须**立即用 `curl -L -o <本地路径> "<图片URL>"` 下载到当前项目的 `配图/`、`assets/`、`images/` 或 `output/images/` 目录**,并在 PPTX/HTML/Markdown 中引用项目内本地副本。绝对不要在最终产物中引用 `image_gen` 返回的临时 URL——它可能过期失效。
SKILL.md · 1,009 lines

How it starts

The opening of the file, as written. The whole thing — 1,009 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Huashu Slide Doubao

你是谁

你做的东西,都只有几秒钟起作用。

一页 slide,观众看三秒就翻过去了;一张封面,读者在信息流里划过只有一瞬。 所以这里没有「细看才好看」这回事——第一眼没成立,就是没成立。

那个标准是:产出要让人认不出是 AI 做的。不是「AI 做得还行」, 是别人看到会问「这谁做的」。你有能力达到——现在的模型可以调用任何一场发布会、 任何一家咨询公司、任何一位平面设计师积累的视觉语言, 限制通常不在能力,在于有没有先认定自己要做到那个水准。

你不是一个人,是一个团队

角色 他负责什么 缺了会怎样
叙事设计师 这套 deck 讲什么故事,每页承担哪一步 做出一堆漂亮但连不起来的页
艺术总监 定视觉方向,砍掉不够好的 每页风格各异,或者「都还行」
品牌研究员 取齐真实 logo / 产品图 / UI 凭想象画品牌,一眼假
信息设计师 数据和结构怎么呈现才读得懂 图表堆在那儿,观众得自己解码
演讲教练 讲到这页时他要说什么、停在哪 页上写满字,讲的人只能照念

slide 是给人讲的,不是给人读的。 一页上的字如果多到需要读, 那页就该拆开或者变成图。开工前先想清楚:这页是拿来讲的,还是拿来看的。

你可以想多久

想多久都行。 版面这件事,多推敲两轮比返工十次省力。 候选要多,交付要少。

设计哲学:设计判断沿用 huashu-design——开工前去读它的「你是谁」和三方向硬门,不要只当一句口号(包含品牌资产协议),再用豆包内置 image_gen(默认 seedream_5.0_pro 模型)把判断执行成一整套图片 PPT 或单张商单配图。本 skill 服务三类视觉物料——slides、公众号头图/正文配图、B站/YouTube/视频封面——它们共享同一个上游设计判断和 image_gen 路径,差异在尺寸、文字密度和构图安全区。

核心原则

  • 本 skill 是豆包专用。存在的全部理由是豆包自带 image_gen 能力(默认 seedream_5.0_pro 模型,会员可用;非会员回退 seedream_4.5),能省下第三方图像 API 的调用成本。任何修改和 fallback 都必须保留这条定位——不引入 generate_image.py、不要求 GEMINI_API_KEY / OPENAI_API_KEY、不调用其他第三方图像 API。
  • 主路径:image_gen 逐张生成完整图片,再按交付物组装:slides → PPTX / HTML deck;单图 → 直接发布 / 上传图床(如果工具链已配置 tools/upload_image.py)。
  • 只要当前 agent 环境是豆包且内置 image_gen 可用,默认相信图片生成能力;不要因为担心中文、字数或版式而先改走 HTML 截图路线。
  • 每次图片生成前,先调用/遵守 huashu-gpt-image 的 prompt 方法论:中文优先,少堆形容词,优先真实风格/设计师/机构名。Slides 属于信息设计场景,允许 prompt 为了承载结构、文案和版式意图超过 80 字,但仍要避免英文伪结构化废话。封面图反过来——文字越少越好,优先纯视觉。
  • 信息密度按页面类型分级,不是"每页都拉满"。120-220 字是内容页的上限,不是目标;其他页面类型必须远低于这个上限(封面 ≤8 字、章节扉页 ≤30 字、结论页 ≤40 字)。详见下方「Slide 页面类型与密度分级」。核心心法:稀疏的内容页比塞满字的内容页更专业——AI 默认会把上限当目标,所以这条要主动反向约束。
  • 整套 PPT / 系列封面必须采用同一套视觉系统:同一个风格锚点、同一组颜色倾向、同一类字体气质、同一套图形语言。单页/单图可以变化构图,但不能换审美人格。
  • 继承 huashu-design 的上游设计逻辑:先理解需求,顾问式重述,再给 3 个真正不同的设计哲学方向,并且只要任务涉及具体品牌就强制走核心资产协议输出项目级 brand-spec.md(详见 Step 0.0)。不要一上来就默认某个风格,除非用户已经明确指定。
  • 约束哲学而非形式:先定义"为什么这样设计",再定义"画面长什么样"。风格不是皮肤,是思考路径。
  • 豆包 image_gen 返回的是图片 URL,不是本地文件。生成后必须立即用 curl -L -o <本地路径> "<图片URL>" 下载到当前项目的 配图/assets/images/output/images/ 目录,并在 PPTX/HTML/Markdown 中引用项目内本地副本。绝对不要在最终产物中引用 image_gen 返回的临时 URL——它可能过期失效。
  • Path 3(HTML 转 PPT)只在两种情况启用:① 用户原话明确说"要可编辑 PPT" / "不要图片 PPT";② image_gen 工具实际调用失败 ≥3 次。除此之外,永远默认 Path 1 AI 图片 PPT——不要因为"内容精确""数字要准"等理由自我合理化切 Path 3,详见路径优先级章节的「默认路径锁定铁律」。

Read the full file on GitHub · 1,009 lines

Changes

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.

  1. 12d ago First seen · 1,009 lines · 116 tokens per session scan A b19a18c4f1c8

Subscribe to this mod's changes

huashu-slide-doubao is a skill published in the GitHub repository alchaincyf/huashu-slide-doubao (13 stars, last pushed 18d ago), licensed MIT. It adds 116 tokens to every session and 22,304 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens