Xiaohu IP Studio Agent Skill

Generates contextual in-article illustrations and diagrams starring consistent IP characters for in-depth Chinese technical and analytical…

Context cost
63.3k tokensestimated from the bundle, loaded when it triggers
Bundle
61 files · 273.8 kB3 scripts among them — read before you run
Licence
MITthe author’s own terms
Last change
—v0.1.0
Servers it uses
Noneruns standalone

What it does

开源中文配图技能 + IP 角色库。用"挑认知锚点 → 现编隐喻 → 反 PPT 自检"的方法,为中文深度文/方法拆解生成由固定角色出演的正文配图(不是通用插画,不是样式库选风格)。自带 31 个原创 IP 角色(手绘线稿 15 + 谐音梗 meme 16),配图时按文章调性选一个角色出演,也可自建角色。当用户说"配图""正文配图""IP 配图""给这篇配图""隐喻配图""选个角色配图""配图 shot list"时使用。

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

content

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md20.8 kB · preview
--- name: xiaohu-ip-studio version: 0.1.0 ---
7# 小互 IP Studio · 开源配图引擎
8
9> 把"中文深度文配图方法论" + "可扩展 IP 角色库"打包的开源配图技能。**方法论恒定,角色与画风是参数。** 血统/致谢见 CREDITS.md。
10>
11> **本文件是流程骨架 + 指针,不复述方法。** 每个概念有唯一真源 reference;骨架点到为止,卡住了再翻对应文件——不必前置通读。
12
13## 核心定位
14
15为中文**深度文 / 方法拆解 / 产品解读**生成**由固定 IP 角色出演**的正文配图。目标**不是**:商业插画、PPT 信息图、样式库随机选风格、可爱卡通。目标**是**:把文章里一个关键判断 / 流程 / 状态 / 隐喻,变成一张有记忆点、一眼怪但一秒懂的解释图,由你选定的角色出演。
16
17## 装好先配置生图(必须一次)
18
19自带生图脚本 scripts/generate.py,但**需要你填自己的图像 API key**(不内置任何密钥):
20
21```bash
22python3 scripts/illo.py init # 引导填 key,写入 ~/.config/xiaohu-ip-studio/config.yaml(mode 600)
23python3 scripts/illo.py doctor # 自检:key / 依赖 / 角色库是否就绪
24```
25
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md1,175 words
Files61
LicenceMIT
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈70
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
63,255
on trigger
The instruction body and 60 supporting files, read only when the skill fires.
31.7%
of a 200k window
Ten skills this size would not fit in the window together.
050k100k150k200k context window

63.3k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

61 files, 273.8 kB on disk. Mostly text — the instructions the model reads — with 3 scripts in it that your client would run only if the instructions tell it to. 68 files of its source are not in the download — listed after these, with why.

  • SKILL.md20.8 kB
  • CREDITS.md3.5 kB
  • LICENSE1.1 kB
  • NOTICE1.0 kB
  • README.en.md14.3 kB
  • README.md13.7 kB
  • config.example.yaml0.6 kB

Not in the download

Not carried is a type a skill download does not hold. Take them from its source.

  • .gitignorenot carried
  • _archived-symbols-20260617/achong/refs/achong-锚点.pngnot carried
  • _archived-symbols-20260617/lengjiao/refs/lengjiao-锚点.pngnot carried
  • _archived-symbols-20260617/shuangzi/refs/shuangzi-锚点.pngnot carried
  • _archived-symbols-20260617/xiaoxing/refs/xiaoxing-锚点.pngnot carried
  • assets/article/01-lineup-all.jpgnot carried
  • assets/article/02-feature-review.pngnot carried
What is not in it

A skill installs nothing and depends on nothing: it is a folder your client reads. This one carries 3 scripts beside the text, so the download is 61 files — not the whole of its source: 68 files are left out. They are listed under the files, with why. The MIT licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Xiaohu IP Studio · 63.3k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/xiaohu-ip-studio/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/xiaohu-ip-studio" ] && { [ ! -e .claude/skills/xiaohu-ip-studio ] || { mv .claude/skills/xiaohu-ip-studio "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/xiaohu-ip-studio" .claude/skills/ && echo "Installed .claude/skills/xiaohu-ip-studio"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add xiaohuailabs/xiaohu-ip-studio

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/xiaohu-ip-studio/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/xiaohu-ip-studio/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/xiaohu-ip-studio" ] && { [ ! -e ~/.claude/skills/xiaohu-ip-studio ] || { mv ~/.claude/skills/xiaohu-ip-studio "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/xiaohu-ip-studio" ~/.claude/skills/ && echo "Installed ~/.claude/skills/xiaohu-ip-studio" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/xiaohu-ip-studio/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where. Not in this download: 68 files of its source (the full list, and why). Take them from its source.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Version0.1.0
Publishedno release date on file
PriceFree
Referencexiaohuailabs/xiaohu-ip-studio

Versions

v0.1.0 is what is on the shelf; no release here carries a date. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

v0.1.0
  • No earlier releases have been published to the marketplace.
Pinning

The install command always fetches the release that is current the day you run it — v0.1.0 today — and cannot ask for an earlier one. The copy on your disk does not change until you run it again.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Who wrote it

XI
xiaohuailabs

Publishes on mcprush.

0 servers listed1 skill listednot claimed
Profile
Publisher
Servers0
Claim this skill