lark-docx2md

lark-docx2md is a skill for Claude Code, Codex from Byte-n/larkDocx2md. It costs 68 tokens per session (894 once invoked), scanned A, original, ISC.

A skill for downloading Feishu Wiki documents and spreadsheets as local Markdown files. Feishu is a collaboration platform; Wiki pages are documents and Sheets are spreadsheets.

In plain words
What is it for?
For downloading Feishu wiki, document, or spreadsheet links, reading selected sections or whole sheets, and passing the resulting Markdown to another task.
Why use it?
It provides a defined way to import Feishu content for reading, archiving, analysis, or later processing, including selecting a particular document section when requested.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit For downloading Feishu wiki, document, or spreadsheet links, reading selected sections or whole sheets, and passing the resulting Markdown to another task.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/byte-n/larkdocx2md/lark-docx2md
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 Byte-n/larkDocx2md --skill lark-docx2md
Clone the repo
git clone --depth 1 https://github.com/Byte-n/larkDocx2md

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 lark-docx2md

README.md
[![agentmods](https://agentmods.dev/badge/skills/byte-n/larkdocx2md/lark-docx2md/github.svg)](https://agentmods.dev/skills/byte-n/larkdocx2md/lark-docx2md)
Your own site
<a href="https://agentmods.dev/skills/byte-n/larkdocx2md/lark-docx2md"><img src="https://agentmods.dev/badge/skills/byte-n/larkdocx2md/lark-docx2md/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 lark-docx2md

Your own site · 80×15
<a href="https://agentmods.dev/skills/byte-n/larkdocx2md/lark-docx2md"><img src="https://agentmods.dev/badge/skills/byte-n/larkdocx2md/lark-docx2md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 894 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 4 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 35
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 52
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 62
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 68
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
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 $0.00068 $0.00894
Opus 5 $0.00034 $0.00447
Sonnet 5 $0.00014 $0.00179
Haiku 4.5 $0.00007 $0.00089

Measured 9d ago against content hash 1846f2046586, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

lark-docx2md 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 9d 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.

skills/lark-docx2md/SKILL.md · 78 lines

What it actually says

lark-docx2md

将飞书文档或电子表格 URL 转换为本地 Markdown 文件。

适用范围

  • 适用链接类型:https://*.feishu.cn/{wiki,docx,docs,sheets}/...(含 ?sheet=xxx)。
  • 适用任务类型:读取、导入、归档、分析、抽取飞书文档内容,并提供给后续实现或生成任务使用。
  • wiki/docx/docs:支持整篇读取与按标题/章节定向读取。
  • sheets:默认按整表读取,不做标题筛选。
  • 不适用于:非飞书链接、纯本地文件解析、需要直接写回飞书文档的场景。

工作流程

第一步:识别链接类型(必须先做)

  • 若 URL 含 /sheets/:判定为电子表格。
  • 若 URL 含 /wiki//docx//docs/:判定为文档。

第二步:按类型分支处理

A. 电子表格(/sheets/

电子表格不做标题识别,直接下载整表:

npx -y lark-docx2md@latest dl --agent local --url "<url>"
B. 文档(/wiki//docx//docs/
  1. 先从用户请求中识别 title

    1. 显式关键词「标题/章节/小节/部分/节选/只要/其中的」+ 名词短语。
    2. 成对引号 "" '' “” ‘’ 「」 《》 包裹的短文本。
    3. 介词结构:X 中的 YX 里的 YX 那一段关于 X 的内容
    4. 多级路径:A 下/中/里的 BA > BA/BA → B → 取为有序路径 [A, B, ...]

    抽到的标题文本:去首尾空白与包裹引号;保留原文大小写、标点、空格、中英文;不翻译/改写/补全。

  2. 如果成功识别到 title,则需要进一步获取 <blockId>

npx -y lark-docx2md@latest get-titles --agent local --url "<url>"

根据 get-titles 输出的所有标题信息,匹配 title 获取对应的 <blockId>。若没有明确的匹配项或存在多个匹配项,则必须让用户参与决策。

  1. 根据识别结果查询:

<blockId>

npx -y lark-docx2md@latest dl --agent local --filter-title-block-id "<blockId>" --url "<url>"

<blockId>

npx -y lark-docx2md@latest dl --agent local --url "<url>"

读取结果

dl 的 stdout 解析 Markdown 绝对路径并读取该文件;同时必须读取其中引用的所有图片(含画板内图片,路径形如 static/xxx.png)。

重要事项

  • dl 必须带 --agent localget-titles 必须带 --agent local
Files

What ships with it

1 file 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.

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. 9d ago First seen · 78 lines · 68 tokens per session scan A 1846f2046586

Subscribe to this mod's changes

lark-docx2md is a skill published in the GitHub repository Byte-n/larkDocx2md (31 stars, last pushed 25d ago), licensed ISC. It adds 68 tokens to every session and 894 once invoked, about $0.0003 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.