Lark Slides for Claude Agent Skill

Creates, edits, and manages professional Lark and Feishu presentations using AI-driven layout planning and template integration.

Context cost
304.2k tokensestimated from the bundle; more than a 200k window holds
Bundle
50 files · 1605.1 kB7 scripts among them — read before you run
Licence
MITthe author’s own terms
Last change
—v1.0.0
Servers it uses
Noneruns standalone

What it does

飞书幻灯片:创建和编辑幻灯片。创建演示文稿、读取幻灯片内容、管理幻灯片页面(创建、删除、读取、局部替换)。当用户需要创建或编辑幻灯片、读取或修改单个页面时使用。当用户给出 doubao.com 的 /slides/ URL/token 时,也应直接使用本 skill,不要因为域名不是飞书而回退到 WebFetch;路由依据是 URL 路径模式和 token,而不是域名。不负责:云文档内容编辑(走 lark-doc)、云文档里的独立画板对象(走 lark-whiteboard)、上传或下载普通文件(走 lark-drive)。

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.md27.8 kB · preview
--- name: lark-slides version: 1.0.0 metadata: requires: bins: ["lark-cli"] cliHelp: "lark-cli slides --help" ---
11# slides (v1)
12
13> 本技能文档较长,务必使用 Read 工具阅读两次,必须阅读完整全文。
14
15## 权威经验
16
17**权威经验是全局硬约束和高频易错点,必须牢记并严格遵守。**
18
19- 你有充足的时间完成这个 PPT,质量永远比速度重要。
20- PPT 的尺寸是 960x540,必须严格确保主体内容在页面边界内。
21- !!!禁止交付无图产物!!! 必须使用大量图片增强视觉效果!!! 禁止重复使用同一张图!!!
22- 封面页的主视觉必须是 <img>(来自生图工具或搜图工具),不要使用 <shape> 或 <icon> 拼出封面视觉。
23- 禁止用 <shape> 和 <line> 拟形具体物项,必须使用生图工具生成的 <img>。
24- 禁止在 headline 或 title 下方放置用于分隔或装饰的 rect 或 <line>。
25- 禁止在任何页面内部使用无意义的装饰线条或色块条带,页面任何一边都不要使用贴边窄条。
26- 生图工具的指令参数必须以“不要出现任何文字和颜色色号”结尾,避免生成的图片上出现干扰文字。
27- 禁止使用 emoji 图标,任何位置都不能出现。
28- 字号必须显式设置 <content> 的 fontSize 属性,不要依赖 textType 的默认字号兜底,这些兜底值明显偏大。
29- 大数字、字号大或字数多的 <content> 必须设置 wrap="true" autoFit="normal-auto-fit" 属性自动换行和缩排,避免文字溢出。
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md1,317 words
Files50
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.

≈100
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
304,100
on trigger
The instruction body and 49 supporting files, read only when the skill fires.
1.5×
a 200k window
It does not fit in the window: loaded whole, it would need more room than the model has.
050k100k150k200k context window

304.2k tokens, estimated from the bundle at four bytes to the token — more than the whole window, so it cannot all be held at once: the model reads SKILL.md when the skill fires and the other files only as the instructions call for them. 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

50 files, 1605.1 kB on disk. Mostly text — the instructions the model reads — with 7 scripts in it that your client would run only if the instructions tell it to.

  • SKILL.md27.8 kB
  • references/asset-planning.md7.7 kB
  • references/iconpark-index.json0.2 kB
  • references/iconpark.md0.2 kB
  • references/lark-slides-add-slide.md0.2 kB
  • references/lark-slides-create.md0.2 kB
  • references/lark-slides-delete-slide.md0.2 kB
  • references/lark-slides-edit-workflows.md0.2 kB
  • references/lark-slides-history.md0.2 kB
  • references/lark-slides-media-upload.md0.2 kB
  • references/lark-slides-pptx-template-workflows.md0.2 kB
  • references/lark-slides-replace-slide.md0.2 kB
  • references/lark-slides-screenshot.md0.2 kB
  • references/lark-slides-xml-presentation-slide-get.md0.3 kB
  • references/lark-slides-xml-presentation-slide-replace.md0.3 kB
  • references/lark-slides-xml-presentations-get.md0.2 kB
  • references/planning-layer.md14.7 kB
  • references/slides_chart_demo.xml0.2 kB
  • references/slides_xml_schema_definition.xml0.2 kB
  • references/troubleshooting.md0.2 kB
  • references/validation-checklist.md0.2 kB
  • references/visual-planning.md14.4 kB
  • references/xml-schema-quick-ref.md0.2 kB
  • scripts/iconpark_tool.py12.4 kB
  • scripts/iconpark_tool_test.py7.9 kB
  • scripts/sxsd_validator.py39.6 kB
  • scripts/xml_lint.py120.1 kB
  • scripts/xml_lint_test.py207.4 kB
  • scripts/xml_text_overlap_lint.py0.5 kB
  • scripts/xml_text_overlap_lint_test.py0.4 kB
  • references/cli/lark-slides-add-slide.md4.9 kB
  • references/cli/lark-slides-create.md9.0 kB
  • references/cli/lark-slides-delete-slide.md2.7 kB
  • references/cli/lark-slides-history.md6.8 kB
  • references/cli/lark-slides-media-upload.md4.7 kB
  • references/cli/lark-slides-replace-slide.md13.8 kB
  • references/cli/lark-slides-screenshot.md5.6 kB
  • references/cli/lark-slides-update-slide.md9.5 kB
  • references/cli/lark-slides-xml-presentation-slide-get.md0.2 kB
  • references/cli/lark-slides-xml-presentation-slide-replace.md0.8 kB
  • references/cli/lark-slides-xml-presentations-get.md1.9 kB
  • references/workflow/error-handling.md5.3 kB
  • references/workflow/slides-editing.md8.1 kB
  • references/workflow/template-editing.md3.9 kB
  • references/workflow/validation-xml.md9.8 kB
  • references/xml/iconpark-index.json746.9 kB
  • references/xml/iconpark.md2.2 kB
  • references/xml/slides_chart_demo.xml60.6 kB
  • references/xml/slides_xml_schema_definition.xml233.4 kB
  • references/xml/xml-schema-quick-ref.md18.1 kB
What is not in it

A skill installs nothing and depends on nothing: it is a folder your client reads. This one carries 7 scripts beside the text, so the bundle is 50 files you can review in full before installing. 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.

# Lark Slides for Claude · 304.2k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/lark-slides-for-claude/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/lark-slides-for-claude" ] && { [ ! -e .claude/skills/lark-slides-for-claude ] || { mv .claude/skills/lark-slides-for-claude "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/lark-slides-for-claude" .claude/skills/ && echo "Installed .claude/skills/lark-slides-for-claude"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add larksuite/lark-slides-for-claude

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/lark-slides-for-claude/ 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/lark-slides-for-claude/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/lark-slides-for-claude" ] && { [ ! -e ~/.claude/skills/lark-slides-for-claude ] || { mv ~/.claude/skills/lark-slides-for-claude "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/lark-slides-for-claude" ~/.claude/skills/ && echo "Installed ~/.claude/skills/lark-slides-for-claude" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/lark-slides-for-claude/ 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. It appears as lark-slides in Gemini CLI, Codex, Copilot and Grok (its own name); Claude Code lists it by the folder name, lark-slides-for-claude.

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
Version1.0.0
Publishedno release date on file
PriceFree
Referencelarksuite/lark-slides-for-claude

Versions

v1.0.0 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.

v1.0.0
  • 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 — v1.0.0 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

LA
larksuite

Publishes on mcprush.

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