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.
npx skills add ddpie/lark-mcp-on-agentcore --skill lark-docgit clone --depth 1 https://github.com/ddpie/lark-mcp-on-agentcoreWrote 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.
[](https://agentmods.dev/skills/ddpie/lark-mcp-on-agentcore/lark-doc)<a href="https://agentmods.dev/skills/ddpie/lark-mcp-on-agentcore/lark-doc"><img src="https://agentmods.dev/badge/skills/ddpie/lark-mcp-on-agentcore/lark-doc/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.
<a href="https://agentmods.dev/skills/ddpie/lark-mcp-on-agentcore/lark-doc"><img src="https://agentmods.dev/badge/skills/ddpie/lark-mcp-on-agentcore/lark-doc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00162 | $0.02452 |
| Opus 5 | $0.00081 | $0.01226 |
| Sonnet 5 | $0.00032 | $0.00490 |
| Haiku 4.5 | $0.00016 | $0.00245 |
Grade A, and why
lark-doc 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
docs
认证由 MCP server 自动处理,无需手动配置。
# 常用示例
lark_docs_fetch(doc="文档URL或token;若 URL 存在 #share-... 锚点,优先使用锚点方式读取,不要全文拉取")
lark_docs_create(content='<title>标题</title><p>内容</p>')
lark_docs_update(doc="文档URL或token", command="append", content='<p>内容</p>')
前置条件 — 执行操作前必读
CRITICAL — 执行对应操作前,MUST 先调用以下技能参考,缺一不可:
- 读取文档(
lark_docs_fetch) → 必读lark_get_skill(domain="doc", section="fetch")(scope/detail选择、局部读取策略、<fragment>/<excerpt>输出结构) - 创建或编辑文档内容 → 必读
lark_get_skill(domain="doc", section="xml")(XML 语法规则,仅当用户明确要求 Markdown 时改读lark_get_skill(domain="doc", section="md"))和必读lark_get_skill(domain="doc", section="style/lark-doc-style")(写作原则:默认段落、按体裁、组件克制);从零创建时加读lark_get_skill(domain="doc", section="style/lark-doc-create-workflow");编辑已有文档时加读lark_get_skill(domain="doc", section="update")和lark_get_skill(domain="doc", section="style/lark-doc-update-workflow")
未读完以上参考就执行相应操作会导致参数选择错误或格式错误。
格式选择规则(全局):
- 创建 / 导入场景(
lark_docs_create,或lark_docs_update的command="append"/"overwrite"整段写入):XML 和 Markdown 都可以。用户提供.md本地文件、或明确说"导入 Markdown"时,直接用 Markdown;否则默认 XML。- 精准编辑场景(
lark_docs_update的str_replace/block_insert_after/block_replace/block_delete/block_move_after等局部精修指令):优先使用 XML(doc_format="xml",即默认值)。XML 能稳定表达 block 结构和样式,局部精修更可控;不要因为 Markdown 更简单就自行切换。
快速决策
- 用户要复制文档 / 创建文档副本 / 另存为副本时,切到
lark_get_skill(domain="drive"),按其中的复制指引通过lark_invoke(tool_name="lark_drive_files_copy", ...)完成;不要用lark_docs_fetch+lark_docs_create重建正文,也不要走lark_drive_export/lark_drive_import。 - 先判定任务路径:找文档 / 导入导出走
lark_get_skill(domain="drive");只读 / 摘要用lark_docs_fetch默认simple;明确旧文本 → 新文本直接str_replace;只有 block 链接、评论锚点、插入 / 替换 / 删除 / 移动才局部 fetchwith-ids;保真改写已有内容才读full - block 直达链接格式:
文档基础 URL#block_id;没有 block_id 时局部 fetchwith-ids - 连续执行多个文档写操作时,必须按
lark_get_skill(domain="doc", section="update")的「Block ID 生命周期」判断旧 block ID 是否还能复用;overwrite/block_replace/block_delete后不要复用受影响的旧 ID,插入 / 复制后要重新 fetch 才能拿到新 block ID - 用户需要在文档内创建、复制或移动资源块(画板、电子表格、多维表格等)时,必须先读取
lark_get_skill(domain="doc", section="xml")的「三、资源块」章节 - 写文档时,由内容和用户意图决定表达形式;流程、架构、路线图、关键指标等信息可以使用画板,但不要默认把重要信息都画板化
- 新增或更新画板时,按
lark_get_skill(domain="doc", section="whiteboard")选型;Mermaid 可由主 Agent 直接插入,SVG / 复杂图 / 已有画板更新按其中流程隔离到 SubAgent - 用户说"看一下文档里的图片/附件/素材""预览素材" → 用
lark_docs_media_preview - 用户明确说"下载素材" → 用
lark_docs_media_download - 用户想把文档回滚到某个
revision_id或某一时刻 → 先读lark_get_skill(domain="doc", section="history"),按其中流程操作 - 用户明确说"下载/更新/删除文档封面图" → 用
lark_docs_resource_download/lark_docs_resource_update/lark_docs_resource_delete(type="cover"),详见lark_get_skill(domain="doc", section="resource-cover") lark_docs_resource_*目前仅支持 Docx 封面资源;其他图片、附件或素材请走lark_docs_media_*- 如果目标是画板/whiteboard/画板缩略图 → 只能用
lark_docs_media_download(type="whiteboard")(不要用lark_docs_media_preview) - 用户明确要操作思维笔记时;已有思维笔记,走思维笔记链路
lark_get_skill(domain="doc", section="mindnote");新建思维笔记,走lark_get_skill(domain="doc", section="whiteboard") - 拿到 spreadsheet URL/token 后 → 切到
lark-sheets做对象内部操作 - 用户需要统计文档的总字数 / 总字符数(word count / character count)时,先读取
lark_get_skill(domain="doc", section="word-stat"),并按其中流程调用lark_exec_script(script="lark-doc/scripts/doc_word_stat.py", ...);统计口径以该脚本为准,不要改用其他方式自行计算。 - 用户说"给文档加评论""查看评论""回复评论""给评论加/删除表情 reaction" → 切到
lark-drive处理 - 文档内容中出现嵌入的
<sheet>、<bitable>或<cite file-type="sheets|bitable">标签时 → 必须主动提取 token 并切到对应技能下钻读取内部数据,不能只呈现标签本身
What ships with it
18 files 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.
- references/lark-doc-create.md 4.9 KB
- references/lark-doc-fetch.md 8.5 KB
- references/lark-doc-history.md 5.4 KB
- references/lark-doc-md.md 4.3 KB
- references/lark-doc-media-download.md 1.9 KB
- references/lark-doc-media-insert.md 6.5 KB
- references/lark-doc-media-preview.md 1.4 KB
- references/lark-doc-mindnote.md 5.6 KB
- references/lark-doc-resource-cover.md 4.0 KB
- references/lark-doc-update.md 12 KB
- references/lark-doc-whiteboard.md 7.8 KB
- references/lark-doc-word-stat.md 4.3 KB
- references/lark-doc-xml-extended-blocks.md 1.5 KB
- references/lark-doc-xml.md 9.5 KB
- references/style/lark-doc-create-workflow.md 4.7 KB
- references/style/lark-doc-style.md 6.0 KB
- references/style/lark-doc-update-workflow.md 4.5 KB
- scripts/doc_word_stat.py 39 KB runs code
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.
- 9d ago First seen · 79 lines · 162 tokens per session scan A 4a3b0d63cdba
lark-doc is a skill published in the GitHub repository ddpie/lark-mcp-on-agentcore (8 stars, last pushed 11d ago), licensed MIT. It adds 162 tokens to every session and 2,452 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
larksnap-fetch
A bridge for downloading Feishu/Lark documents or ordinary webpages into local files, with options such as Markdown, HTML, or PDF. Feishu, also called Lark, is a workplace collaboration platform.
lark-cli
A command-line tool for working with Lark, also called Feishu, a workplace collaboration platform. It covers services such as calendars, meetings, documents, spreadsheets, messaging, tasks, approvals, and shared files.
lark-wiki-migration
A Feishu wiki migration tool copies all document pages from one Feishu knowledge base to another. Feishu is a workplace collaboration platform, and a wiki is an organized collection of linked documents.
documents
Read and write Lark documents - get content as markdown or blocks, create new documents, append content (text, headings, lists, code), list folders. Use when user asks about a Lark doc, wants to read/create/edit a document, or mentions a document URL/ID.
sheets
Read and query Lark Sheets (spreadsheets) - list sheets in a spreadsheet, read cell data. Use when user asks about a spreadsheet, wants to read data from a Lark sheet, or mentions a spreadsheet URL/ID.
minutes
Access Lark Minutes recordings - get metadata, export transcripts, download audio/video. Use when user asks about meeting recordings, transcripts, or minutes.