lark-doc

larksuite/cli · Agent Skill

Manages Lark document content (Docx/Wiki), including reading, creating, editing, inserting/downloading images, and operating mind notes.

Jump to install ↓

Overview

Publisher	larksuiteOrganization
Repository	larksuite/cli ↗
Skill folder	`lark-shared`
Stars	17,066
Bundled files	1
License	MIT
Last updated	August 30, 2026
Links	Skill source ↗ · Repository ↗

Mozgi check

What we found in the skill files. Details come with a subscription.

Security

low risk · no obvious risks found — the full report shows the details

Compatibility

instructions only — works with most agents

Similar skills

36 similar skills found

Also with subscription

Installation

A skill is a folder with a SKILL.md file. Pick your agent and run the commands in a terminal (macOS, Linux or Git Bash on Windows) from your project root.

Copy the prompt into Claude, Codex or another assistant: it will review the skill and install it for you.

Install the “lark-doc” skill from mozgi.io (https://mozgi.io/skills/lark-doc/) for me.

1. Download the archive: https://mozgi.io/skills/lark-doc/download
   If it fails, take the skill folder from the source: https://github.com/larksuite/cli/tree/main/skills/lark-shared
2. Read SKILL.md and the other files. Check the skill is safe: no hidden commands, no sending data elsewhere, no scripts doing something other than described. If anything looks suspicious, stop and tell me.
3. Put the “lark-doc” folder into your agent's skills folder: .claude/skills/ for Claude Code, .agents/skills/ for Codex, .cursor/skills/ for Cursor, .gemini/skills/ for Gemini CLI. Inside the project if we are in one, otherwise in the home folder (~/.claude/skills/ etc.).
4. Make sure <skills folder>/lark-doc/SKILL.md exists.
5. Briefly tell me what this skill does and offer to try it on my task.

If you cannot do a step yourself, tell me what to click or type.

git clone --depth 1 --branch main https://github.com/larksuite/cli.git /tmp/cli
mkdir -p .claude/skills
cp -r /tmp/cli/skills/lark-shared .claude/skills/lark-shared

Restart Claude Code — the skill appears in the list; call it manually with /lark-doc. For all projects use ~/.claude/skills.

git clone --depth 1 --branch main https://github.com/larksuite/cli.git /tmp/cli
mkdir -p .agents/skills
cp -r /tmp/cli/skills/lark-shared .agents/skills/lark-shared

Codex looks for skills in .agents/skills from the current folder up to the repo root; call one with /skills or $lark-doc. For all projects use ~/.agents/skills.

git clone --depth 1 --branch main https://github.com/larksuite/cli.git /tmp/cli
mkdir -p .cursor/skills
cp -r /tmp/cli/skills/lark-shared .cursor/skills/lark-shared

Cursor picks the skill up on start; call it with “/” in Agent chat. Cursor also reads .claude/skills and .agents/skills. For all projects use ~/.cursor/skills.

git clone --depth 1 --branch main https://github.com/larksuite/cli.git /tmp/cli
mkdir -p .gemini/skills
cp -r /tmp/cli/skills/lark-shared .gemini/skills/lark-shared

Gemini CLI offers to activate the skill when a task matches — you approve it. For all projects use ~/.gemini/skills.

Review the source files

1 file Download Zip

Read SKILL.md and any companion files before deciding whether to install. Click a file to preview it.

SKILL.md contents

Original author text · read-only

lark-cli 共享规则

所有 lark-* skill 共享的底座：身份、认证、输出契约与高风险操作。

通用准则

1. 调用前先确认用法：执行前读对应 reference 或跑 --help，别猜 flag 盲调。

2. 身份决定你代表谁操作：--as user 代表用户本人（能看到、也能操作其日历、云空间/云盘/云存储等个人资源），--as bot 代表应用自己，应用级操作，只能访问bot自己的资源，bot 查用户资源会返回空成功而非报错。动手前先搞清楚身份identity。身份模型和权限管理 → lark-shared-identity-and-permissions.md ↗。

3. 授权 / 配置类 URL 必须配二维码：当命令输出 verification_url、verification_uri_complete、console_url 等 URL 字段时，必须用 lark-cli auth qrcode 生成并在回复中展示，URL 在前二维码在后；优先生成 PNG（--output），仅当用户明确要求时才使用 ASCII（--ascii）。URL 原样转发——不编解码、不加标点、不重拼 query，二维码和链接请一起展示给用户。

4. --format json（默认）下，判断成功用 ok == true（或进程退出码 0），不要用 code == 0：成功信封没有顶层 code / msg 字段，code 只出现在错误信封的 error 内。按 OpenAPI 老格式 {"code": 0, "msg": "ok"}判断会把所有成功调用误判为失败——封装写入类命令时尤其危险。JSON 输出契约 → lark-shared-output-contract.md ↗。

安全规则

1. 禁止输出密钥（appSecret、accessToken等）到终端明文。

2. 写入/删除操作前必须确认用户意图。

3. 目标命令支持 --dry-run 时，用 --dry-run 预览危险请求。

4. 退出码 10 是高风险确认门禁（risk: "high-risk-write"），不是错误：停下 → 向用户确认（展示 action、risk 和关键参数）→ 取得用户显式同意后，将 hint 指出的确认 flag 追加到你原始 argv 的末尾后重试；绝不静默加确认 flag 绕过 → lark-shared-high-risk-approval.md ↗。

5. 文件路径只接受相对路径：--file、--output、--output-dir、@file 等路径参数只接受 cwd 下的相对路径，传绝对路径会报 unsafe file path。数据输入（@file、大 JSON）优先用 stdin 传入，避免路径和转义问题。

Reference 强触发索引

命中任一触发条件时，MUST 在执行下一步前读取对应 reference。命中多条时按表中顺序读取，同一reference只读取一次。

| 强触发条件（命中任一即必读） | Reference |

|---|---|

| 查看自己是谁(user/bot)、获取当前身份详细字段信息、身份诊断、--as选择逻辑、身份延续、登录态、认证、scope、授权和权限管理、missing_scopes 或 console_url、Agent 准备发起或完成 auth login | lark-shared-identity-and-permissions.md ↗ |

| 需要依赖 JSON 输出契约判断成功 / 失败、读取 stdout / stderr，或为命令编写脚本与封装 | lark-shared-output-contract.md ↗ |

| 准备执行high-risk-write(高风险操作)、判断命令风险等级、遇到退出码 exit 10、confirmation_required、确认后重试 | lark-shared-high-risk-approval.md ↗ |

| 首次使用CLI需运行 lark-cli config init 完成应用配置、或 CLI 明确提示 config init --new | lark-shared-config-init.md ↗ |

| 用户询问 notice、CLI版本更新、或输出含 _notice（升级 / skills 落后 / 废弃命令提示）| lark-shared-update-notice.md ↗ |

Frequently asked questions

What does the lark-doc skill do?

Manages Lark document content (Docx/Wiki), including reading, creating, editing, inserting/downloading images, and operating mind notes.

How do I install lark-doc?

Open the “Installation” block on this page and pick your agent — Claude Code, Codex, Cursor or Gemini CLI — for ready-made commands that copy the skill folder to the right place. Or copy the prompt from the “Via assistant” tab and let the assistant review and install the skill.

Which AI models work with lark-doc?

Skills are plain Markdown instructions (the Agent Skills format), so lark-doc works with any agent that reads SKILL.md: Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and more. The model loads the instructions only when a task matches the skill's description.

Is lark-doc free?

The skill is published openly by larksuite under the MIT license. The skill itself costs nothing — you only pay your AI provider for the tokens you use.

Is it safe to install skills?

A skill is a set of instructions your agent will follow, so read SKILL.md and its companion files before installing. Scripts in the skill folder only run if your agent runs them — keep an eye on what it does and do not grant unnecessary permissions.

How is a skill different from an MCP server or a plugin?

An MCP server or plugin gives the model new tools — code that runs and returns a result. A skill gives it knowledge and process: how to approach a task, which steps to follow and what good output looks like. It needs no server or API key.

Related skills

All skills →

nano-pdf Edit PDF files using natural-language instructions via the nano-pdf CLI. openclaw390k

nutrient-document-processing Process, convert, OCR, extract, redact, sign, and fill documents using the Nutrient DWS API. Supports PDF, DOCX, XLSX, PPTX, HTML, and images. affaan-m258k

grill-with-docs Refines plans and designs through detailed interviews, simultaneously generating documentation (ADRs, glossary). mattpocock256k

pptx-author Automatically generates PowerPoint presentations (.pptx) using the python-pptx library. Ideal for creating reports and documents. NousResearch243k

powerpoint Creates, reads, and edits PowerPoint (.pptx) presentations using the python-pptx library, enabling offline file manipulation. NousResearch243k

pdf Work with PDFs: read and extract text and tables; create, merge, split, rotate; fill forms, encrypt, watermark, extract images, and OCR scanned documents. anthropics176k