Remote OpenClaw
Menu
SkillsMCPPluginsFree guideDigestSubmit MCPSkillPluginMCPMCP, plugin, or skillAdvertise
Remote OpenClaw
SkillsMCPPluginsFree guideDigestSubmit MCPSkillPluginMCPMCP, plugin, or skillAdvertise

Featured

Reach 56,000+ AI builders from just $0.50 a click

You only pay for clicks, never impressions - and it's far cheaper than Google Ads, with no monthly lock-in.

Advertise from $0.50/click →
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
CLN.Work — Stop prompting, start hiring AI employees logoCLN.Work — Stop prompting, start hiring AI employees

Turn your Claude agents into a real team — onboard them, assign tasks, and manage them like staff.

Hire AI employees →
Deploy your OpenClaw agent in 60 seconds, live 24/7 — 10% off with code ZACAARON10 logoDeploy your OpenClaw agent in 60 seconds, live 24/7 — 10% off with code ZACAARON10

Launch OpenClaw on Hostinger in about 60 seconds and keep it live 24/7. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Deploy your Hermes agent in 60 seconds, live 24/7 — 10% off with code ZACAARON10 logoDeploy your Hermes agent in 60 seconds, live 24/7 — 10% off with code ZACAARON10

Launch Hermes on Hostinger in about 60 seconds, connect Telegram & Discord, and keep it live 24/7. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Reach 56,000+ AI builders from just $0.50 a click

You only pay for clicks, never impressions - and it's far cheaper than Google Ads, with no monthly lock-in.

Advertise from $0.50/click →
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
CLN.Work — Stop prompting, start hiring AI employees logoCLN.Work — Stop prompting, start hiring AI employees

Turn your Claude agents into a real team — onboard them, assign tasks, and manage them like staff.

Hire AI employees →
Deploy your OpenClaw agent in 60 seconds, live 24/7 — 10% off with code ZACAARON10 logoDeploy your OpenClaw agent in 60 seconds, live 24/7 — 10% off with code ZACAARON10

Launch OpenClaw on Hostinger in about 60 seconds and keep it live 24/7. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Deploy your Hermes agent in 60 seconds, live 24/7 — 10% off with code ZACAARON10 logoDeploy your Hermes agent in 60 seconds, live 24/7 — 10% off with code ZACAARON10

Launch Hermes on Hostinger in about 60 seconds, connect Telegram & Discord, and keep it live 24/7. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Reach 56,000+ AI builders from just $0.50 a click

You only pay for clicks, never impressions - and it's far cheaper than Google Ads, with no monthly lock-in.

Advertise from $0.50/click →
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
CLN.Work — Stop prompting, start hiring AI employees logoCLN.Work — Stop prompting, start hiring AI employees

Turn your Claude agents into a real team — onboard them, assign tasks, and manage them like staff.

Hire AI employees →
Deploy your OpenClaw agent in 60 seconds, live 24/7 — 10% off with code ZACAARON10 logoDeploy your OpenClaw agent in 60 seconds, live 24/7 — 10% off with code ZACAARON10

Launch OpenClaw on Hostinger in about 60 seconds and keep it live 24/7. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Deploy your Hermes agent in 60 seconds, live 24/7 — 10% off with code ZACAARON10 logoDeploy your Hermes agent in 60 seconds, live 24/7 — 10% off with code ZACAARON10

Launch Hermes on Hostinger in about 60 seconds, connect Telegram & Discord, and keep it live 24/7. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Skills/larksuite/cli/lark-drive
lark-drive logo

lark-drive

larksuite/cli
232K installs14K stars
Run it on Hostinger →up to 70% off + an extra 10% with code ZACAARON10Free API →

Installation

npx skills add https://github.com/larksuite/cli --skill lark-drive

Summary

飞书云空间:管理云空间中的文件和文件夹。上传和下载文件、创建文件夹、复制/移动/删除文件、查看文件元数据、管理文档评论、管理文档权限、订阅用户评论变更事件、修改文件标题(docx、sheet、bitable、file、folder、wiki);也负责把本地 Word/Markdown/Excel/CSV 以及 Base 快照(.base)导入为飞书在线云文档(docx、sheet、bitable)。当用户需要上传或下载文件、整理云空间目录、查看文件详情、管理评论、管理文档权限、修改文件标题、订阅用户评论变更事件,或要把本地文件导入成新版文档、电子表格、多维表格/Base 时使用。

SKILL.md

drive (v1)

CRITICAL — 开始前 MUST 先用 Read 工具读取 ../lark-shared/SKILL.md,其中包含认证、权限处理

导入分流规则: 如果用户要把本地 Excel / CSV / .base 快照导入成 Base / 多维表格 / bitable,必须优先使用 lark-cli drive +import --type bitable。不要先切到 lark-base;lark-base 只负责导入完成后的表内操作。

快速决策

  • 用户要搜文档 / Wiki / 电子表格 / 多维表格 / 云空间对象,优先使用 lark-cli drive +search。自然语言里"最近我编辑过的"、"我创建的"、"最近一周我打开过的 xxx"、"某人创建的 docx" 等直接映射到扁平 flag,避免手写嵌套 JSON。老的 docs +search 进入维护期、后续会下线,不要新增对它的依赖。
  • 用户要把本地 .xlsx / .csv / .base 导入成 Base / 多维表格 / bitable,第一步必须使用 lark-cli drive +import --type bitable。
  • 用户要把本地 .md / .docx / .doc / .txt / .html 导入成在线文档,使用 lark-cli drive +import --type docx。
  • 用户要在 Drive 里上传、创建、读取、局部 patch 或覆盖更新原生 .md 文件(不是导入成 docx),切到 lark-markdown。
  • 用户要查看、下载、回滚或删除文件的历史版本,使用 drive +version-history、drive +version-get、drive +version-revert、drive +version-delete;这组命令同时支持 --as user 和 --as bot,自动化场景优先 --as bot。
  • 用户要把本地 .xlsx / .xls / .csv 导入成电子表格,使用 lark-cli drive +import --type sheet。
  • 用户要在云空间里新建文件夹,优先使用 lark-cli drive +create-folder。
  • 用户要把本地文件上传到知识库 / 文档库里的某个 wiki 节点下时,仍然使用 lark-cli drive +upload --wiki-token <wiki_token>;不要误切到 wiki 域命令。
  • lark-base 只负责导入完成后的 Base 内部操作(表、字段、记录、视图),不要在“本地文件 -> Base”这一步提前切到 lark-base。

修改标题

  • 使用 drive files patch 命令,通过new_title字段可以修改标题,支持 docx、sheet、bitable、file、wiki、folder 类型

核心概念

文档类型与 Token

飞书开放平台中,不同类型的文档有不同的 URL 格式和 Token 处理方式。在进行文档操作(如添加评论、下载文件等)时,必须先获取正确的 file_token。

文档 URL 格式与 Token 处理

URL 格式示例Token 类型处理方式
/docx/https://example.larksuite.com/docx/doxcnxxxxxxxxxfile_tokenURL 路径中的 token 直接作为 file_token 使用
/doc/https://example.larksuite.com/doc/doccnxxxxxxxxxfile_tokenURL 路径中的 token 直接作为 file_token 使用
/wiki/https://example.larksuite.com/wiki/wikcnxxxxxxxxxwiki_token⚠️ 不能直接使用,需要先查询获取真实的 obj_token
/sheets/https://example.larksuite.com/sheets/shtcnxxxxxxxxxfile_tokenURL 路径中的 token 直接作为 file_token 使用
/drive/folder/https://example.larksuite.com/drive/folder/fldcnxxxxfolder_tokenURL 路径中的 token 作为文件夹 token 使用

Wiki 链接特殊处理(关键!)

知识库链接(/wiki/TOKEN)背后可能是云文档、电子表格、多维表格等不同类型的文档。不能直接假设 URL 中的 token 就是 file_token,必须先查询实际类型和真实 token。

处理流程
  1. 使用 wiki.spaces.get_node 查询节点信息
   lark-cli wiki spaces get_node --params '{"token":"wiki_token"}'
  1. 从返回结果中提取关键信息
  • node.obj_type:文档类型(docx/doc/sheet/bitable/slides/file/mindnote)
  • node.obj_token:真实的文档 token(用于后续操作)
  • node.title:文档标题
  1. 根据 obj_type 使用对应的 API
obj_type说明使用的 API
docx新版云文档drive file.comments.、docx.
doc旧版云文档drive file.comments.*
sheet电子表格sheets.*
bitable多维表格bitable.*
slides幻灯片drive.*
file文件drive.*
mindnote思维导图drive.*
查询示例
# 查询 wiki 节点
lark-cli wiki spaces get_node --params '{"token":"wiki_token"}'

返回结果示例:

{
  "node": {
    "obj_type": "docx",
    "obj_token": "xxxx",
    "title": "标题",
    "node_type": "origin",
    "space_id": "12345678910"
  }
}

资源关系

Wiki Space (知识空间)
└── Wiki Node (知识库节点)
    ├── obj_type: docx (新版文档)
    │   └── obj_token (真实文档 token)
    ├── obj_type: doc (旧版文档)
    │   └── obj_token (真实文档 token)
    ├── obj_type: sheet (电子表格)
    │   └── obj_token (真实文档 token)
    ├── obj_type: bitable (多维表格)
    │   └── obj_token (真实文档 token)
    └── obj_type: file/slides/mindnote
        └── obj_token (真实文档 token)

Drive Folder (云空间文件夹)
└── File (文件/文档)
    └── file_token (直接使用)

常见操作 Token 需求

操作需要的 Token说明
读取文档内容file_token / 通过 docs +fetch --api-version v2 自动处理docs +fetch --api-version v2 支持直接传入 URL
添加局部评论(划词评论)file_token传 --block-id 时,drive +add-comment 会创建局部评论;docx 支持文本定位或 block_id,slides 仅支持 block_id,且都支持最终解析到对应类型的 wiki URL
添加全文评论file_token不传 --block-id 时,drive +add-comment 默认创建全文评论;支持 docx、旧版 doc URL,以及最终解析为 doc/docx 的 wiki URL
下载文件file_token从文件 URL 中直接提取
上传文件folder_token / wiki_node_token目标位置的 token
列出文档评论file_token同添加评论

评论能力边界(关键!)

  • drive +add-comment 支持两种模式。
  • 全文评论:未传 --block-id 时默认启用,也可显式传 --full-comment;支持 docx、旧版 doc URL,以及最终解析为 doc/docx 的 wiki URL。
  • 局部评论:传 --block-id 时启用;仅支持 docx,以及最终解析为 docx 的 wiki URL。block ID 可通过 docs +fetch --api-version v2 --detail with-ids 获取。
  • drive +add-comment 的 --content 需要传 reply_elements JSON 数组字符串,例如 --content '[{"type":"text","text":"正文"}]'。
  • slides 评论要求显式传 --block-id <slide-block-type>!<xml-id>;CLI 会将其拆分后写入 anchor.block_id 和 anchor.slide_block_type。其中 <xml-id> 是 PPT XML 协议中的元素 id;不支持 --selection-with-ellipsis 和 --full-comment。
  • 评论写入内容(添加评论、回复评论、编辑回复)里的文本不能直接出现 <、>;提交前必须先转义:< -> &lt;,> -> &gt;。
  • 使用 drive +add-comment 时,shortcut 会对 type=text 的文本元素自动做上述转义兜底;如果直接调用 drive file.comments create_v2、drive file.comment.replys create、drive file.comment.replys update,则需要在请求里自行传入已转义的内容。
  • 如果 wiki 解析后不是 doc/docx/sheet/slides,不要用 +add-comment。
  • 如果需要更底层地直接调用评论 V2 协议,再走原生 API:先执行 lark-cli schema drive.file.comments.create_v2,再执行 lark-cli drive file.comments create_v2 ...。全文评论省略 anchor,局部评论传 anchor.block_id。

评论查询与统计口径(关键!)

强制规则:drive file.comments list 默认必须传 is_solved:false,即仅查询未解决评论。即使用户说“所有评论”“全部评论”“把评论都列出来”,只要没有明确提到要包含已解决评论,仍然按默认口径查询未解决评论。仅当用户明确要求包含已解决评论时,才可省略 is_solved 参数。

正确示例:

# 默认查询:仅未解决评论(推荐)
lark-cli drive file.comments list --params '{"file_token": "xxx", "file_type": "docx", "is_solved": false}'

# 查询所有评论(用户未明确要求包含已解决评论)
lark-cli drive file.comments list --params '{"file_token": "xxx", "file_type": "docx", "is_solved": false}'

# 包含已解决评论(需用户明确要求)
lark-cli drive file.comments list --params '{"file_token": "xxx", "file_type": "docx"}'

错误示例:

# 不推荐:用户未明确要求但查询所有评论
lark-cli drive file.comments list --params '{"file_token": "xxx", "file_type": "docx"}'
  • 查询文档评论时,使用 drive file.comments list。
  • drive file.comments list 返回的 items 应理解为"评论卡片"列表,每个 item 对应用户界面里看到的一张评论卡片,而不是平铺的互动消息列表。
  • 服务端语义上,创建第一条评论时会同时创建该卡片里的第一条 reply;因此真正承载正文的是每个 item.reply_list.replies,其中第一条 reply 在用户视角下就是这张卡片里的"评论本身"。
  • 当用户要统计"评论数"或"评论卡片数"时,统计 items 的长度即可;如果是全量统计,则对所有评论分页返回的 items 长度累加。
  • 当用户要统计"回复数"时,按用户视角应排除每张评论卡片里的首条评论,统计口径是所有 item.reply_list.replies 的长度之和减去 items 的长度。
  • 当用户要统计"总互动数"时,统计所有 item.reply_list.replies 的长度之和即可;这个口径包含每张评论卡片里的首条评论。
  • 如果某个 item.has_more=true,说明该评论卡片下还有更多回复未包含在当前返回中;此时需要继续调用 drive file.comment.replys list 拉全后,再做全量回复数 / 总互动数统计。

评论业务特性与引导(关键!)

评论排序引导
  • 一个文档通常有多个评论,评论按 create_time(创建时间)排序。
  • 重要:只有当用户明确提到"最新评论"、"最后评论"、"最早评论"时,才需要根据 create_time 进行排序:
  • 必须先获取所有评论(处理分页拉完所有数据),不能只获取一页就排序
  • "最新评论" / "最后评论":按 create_time 降序排列,取第一条
  • "最早评论":按 create_time 升序排列,取第一条
  • 如果用户只说"第一条评论",直接使用 drive file.comments list 返回的第一条即可,不需要额外排序。
评论回复限制
  • 添加评论回复前先检查是否存在以下限制
  • 全文评论不支持回复:is_whole=true 的评论(全文评论)无法添加回复,遇到此类评论应提示用户"全文评论不支持回复"。
  • 已解决评论不支持回复:is_solved=true 的评论无法添加回复,遇到此类评论应提示用户"该评论已被解决,无法回复"。
  • 注意:当用户要回复某条评论但该评论因上述限制不能回复时,只提示不能回复即可,不要自动帮用户找其他可以回复的评论,避免不符合用户预期。
批量查询与列表查询的选择
  • 使用 drive file.comments batch_query 是已知评论 ID 后的批量查询,需要传入具体的评论 ID 列表。
  • 使用 drive file.comments list 用于分页获取评论列表,适合统计评论总数、遍历所有评论,或获取"最新/最后 N 条评论"等场景。
Reaction / 表情场景
  • 遇到评论 / 回复上的 reaction(表情、各表情数量、谁点了什么、添加/删除表情)相关问题时,先阅读 lark-drive-reactions.md 了解如何使用。

典型错误与解决方案

错误信息原因解决方案
not exist使用了错误的 token检查 token 类型,wiki 链接必须先查询获取 obj_token
permission denied没有相关操作权限引导用户检查当前身份对文档/文件是否有相应操作权限;如果需要,可以授予相应权限
invalid file_typefile_type 参数错误根据 obj_type 传入正确的 file_type(docx/doc/sheet/slides)
permission.public.patch 错误码引导

调用 lark-cli drive permission.public patch 更新文档公开权限失败时,如果返回以下错误码,按表格给用户明确下一步。不要把这些错误简单归类为缺少 scope;它们通常表示租户、对外分享或文档密级策略拦截。

错误码含义给用户的引导
91009对外分享被租户安全策略管控,当前用户无法开启提示用户:对外分享能力被租户安全策略统一管控,无法通过 API 或当前用户直接开启;需要联系租户管理员调整组织级对外分享策略。
91010文档对外分享未打开提示用户:当前文档尚未打开对外分享,请先在文档权限设置中打开对外分享,再重试 permission.public.patch。
91011对外分享被文档密级管控提示用户:对外分享被密级策略拦截,需要打开目标文档,在文档内发起密级豁免或进行密级降级后再重试;回复中必须给出目标文档 URL。
91012权限设置被文档密级管控提示用户:该权限设置被密级策略拦截,需要打开目标文档,在文档内发起密级豁免或进行密级降级后再重试;回复中必须给出目标文档 URL。

当用户最初提供的是文档 URL,遇到 91011 或 91012 时直接把该 URL 原样返回给用户作为操作入口;如果上下文只有 token,需要先尽量通过已有上下文、搜索结果或元数据恢复目标文档 URL,再给出可点击的文档 URL。

授权当前应用访问文档

当需要将文档权限授予当前应用(bot)自身时,先通过 bot info 接口获取应用的 open_id,再调用权限接口授权:

# 1. 获取当前应用的 open_id
lark-cli api GET /open-apis/bot/v3/info --as bot
# 从返回值中取 bot.open_id

# 2. 授权当前应用访问文档
lark-cli drive permission.members create \
  --params '{"token":"<doc_token>","type":"<resource_type>"}' \
  --data '{"member_type":"openid","member_id":"<bot_open_id>","perm":"view","type":"user"}'

注意:此方式仅适用于需要授权给当前应用的场景。授权给其他用户时,直接使用对方的 open_id 即可,无需调用 bot info 接口。

<resource_type> 可选值:doc、docx、sheet、bitable、file、folder、wiki、slides。

Shortcuts(推荐优先使用)

Shortcut 是对常用操作的高级封装(lark-cli drive +<verb> [flags])。有 Shortcut 的操作优先使用。

Shortcut说明
+searchSearch Lark docs, Wiki, and spreadsheet files with flat filter flags (preferred over docs +search). Natural-language-friendly: --edited-since, --mine, --doc-types, etc.
+uploadUpload a local file to a Drive folder or wiki node
+create-folderCreate a Drive folder, optionally under a parent folder, with bot auto-grant support
+downloadDownload a file from Drive to local
+statusCompare a local directory with a Drive folder by exact SHA-256 hash by default, or use --quick for a best-effort modified-time diff that skips remote downloads; reports new_local / new_remote / modified / unchanged plus detection=exact or detection=quick. Duplicate remote rel_path conflicts fail fast with error.type=duplicate_remote_path and list every conflicting entry; do not proceed as if one was chosen. --local-dir 必须是 cwd 内的相对路径,越界路径 CLI 会直接拒绝;目标在 cwd 外时引导用户切换 agent 工作目录,不要私自 cd 绕过。
+pullFile-level Drive → local mirror. Duplicate remote rel_path conflicts fail by default; for duplicate files, rename downloads all copies with stable hashed suffixes, while newest / oldest pick one. --if-exists supports overwrite / smart / skip (smart is a best-effort modified-time incremental mode for repeat syncs). --delete-local requires --yes, only removes regular files, and is skipped after item failures. --local-dir must stay inside cwd.
+syncTwo-way local ↔ Drive sync. Reuses +status diff buckets, pulls new_remote, pushes new_local, and resolves modified via `--on-conflict=remote-winslocal-winskeep-bothask. --quick enables best-effort modified-time diffing (timestamp mismatches can still trigger real pull/push actions), --on-duplicate-remote supports failnewestoldest`, and the command is intentionally non-destructive (no delete on either side).
+create-shortcutCreate a shortcut to an existing Drive file in another folder
+add-commentAdd a comment to doc/docx/sheet/slides, also supports wiki URL resolving to doc/docx/sheet/slides
+exportExport a doc/docx/sheet/bitable to a local file with limited polling; supports --file-name for local naming
+export-downloadDownload an exported file by file_token
+importImport a local file to Drive as a cloud document (docx, sheet, bitable)
+version-historyList historical versions of a file with only_tag=true and cursor-based pagination
+version-getDownload a specific historical version of a file
+version-revertRevert a file to a specific historical version
+version-deleteDelete a specific historical version of a file
+moveMove a file or folder to another location in Drive
+deleteDelete a Drive file or folder with limited polling for folder deletes
+pushFile-level local → Drive mirror. Duplicate remote rel_path conflicts fail by default; newest / oldest only apply to duplicate files when you explicitly want to target one remote file. --if-exists supports skip / smart / overwrite (smart skips files whose remote modified_time is already up to date, but falls through to the same overwrite path when the remote is older, so it inherits overwrite's rollout caveat). --delete-remote requires --yes. --local-dir must stay inside cwd.
+task_resultPoll async task result for import, export, move, or delete operations
+apply-permissionApply to the document owner for view/edit access (user-only; 5/day per document)

API Resources

lark-cli schema drive.<resource>.<method>   # 调用 API 前必须先查看参数结构
lark-cli drive <resource> <method> [flags] # 调用 API

重要:使用原生 API 时,必须先运行 schema 查看 --data / --params 参数结构,不要猜测字段格式。

files

  • copy — 复制文件
  • create_folder — 新建文件夹
  • list — 获取文件夹下的清单
  • patch — 修改文件标题

file.comments

  • batch_query — 批量获取评论
  • create_v2 — 添加全文/局部(划词)评论
  • list — 分页获取文档评论
  • patch — 解决/恢复 评论

file.comment.replys

  • create — 添加回复
  • delete — 删除回复
  • list — 获取回复
  • update — 更新回复

permission.members

  • auth —
  • create — 增加协作者权限
  • transfer_owner —

metas

  • batch_query — 获取文档元数据

user

  • remove_subscription — 取消订阅用户、应用维度事件
  • subscription — 订阅用户、应用维度事件(本次开放评论添加事件)
  • subscription_status — 查询用户、应用对指定事件的订阅状态

file.statistics

  • get — 获取文件统计信息

file.view_records

  • list — 获取文档的访问者记录

file.comment.reply.reactions

  • update_reaction — 添加/删除 reaction

权限表

方法所需 scope
files.copydocs:document:copy
files.create_folderspace:folder:create
files.listspace:document:retrieve
files.patchdocx:document:write_only
file.comments.batch_querydocs:document.comment:read
file.comments.create_v2docs:document.comment:create
file.comments.listdocs:document.comment:read
file.comments.patchdocs:document.comment:update
file.comment.replys.createdocs:document.comment:create
file.comment.replys.deletedocs:document.comment:delete
file.comment.replys.listdocs:document.comment:read
file.comment.replys.updatedocs:document.comment:update
permission.members.authdocs:permission.member:auth
permission.members.createdocs:permission.member:create
permission.members.transfer_ownerdocs:permission.member:transfer
permission.public.getdocs:permission.setting:read
permission.public.patchdocs:permission.setting:write_only
metas.batch_querydrive:drive.metadata:readonly
user.remove_subscriptiondocs:event:subscribe
user.subscriptiondocs:event:subscribe
user.subscription_statusdocs:event:subscribe
file.statistics.getdrive:drive.metadata:readonly
file.view_records.listdrive:file:view_record:readonly
file.comment.reply.reactions.update_reactiondocs:document.comment:create

Score

0–100
78/ 100

Grade

B

Popularity30/30

231,628 installs — top-tier adoption.

Completeness27/30

Documented: full SKILL.md body, description, one-line install. Missing: category/license metadata.

Trust15/25

Community skill with a public GitHub source repository you can review.

Freshness6/15

No update timestamp is tracked for this skill in our catalog.

Scored automatically from popularity, completeness, trust, and freshness — computed only from data in our catalog, never fabricated.

Proud of your score? Add this badge to your README.

Paste a snippet into your GitHub README. The badge updates automatically and links back to this page.

Lark Drive skill score badge previewScore badge

Markdown

[![Lark Drive skill](https://www.remoteopenclaw.com/skills/larksuite/cli/lark-drive/badges/score.svg)](https://www.remoteopenclaw.com/skills/larksuite/cli/lark-drive)

HTML

<a href="https://www.remoteopenclaw.com/skills/larksuite/cli/lark-drive"><img src="https://www.remoteopenclaw.com/skills/larksuite/cli/lark-drive/badges/score.svg" alt="Lark Drive skill"/></a>

Lark Drive FAQ

How do I install the Lark Drive skill?

Run “npx skills add https://github.com/larksuite/cli --skill lark-drive” in your terminal. The skill is added to your agent's skills directory and picked up automatically on the next run — no restart or extra configuration needed.

What does the Lark Drive skill do?

飞书云空间:管理云空间中的文件和文件夹。上传和下载文件、创建文件夹、复制/移动/删除文件、查看文件元数据、管理文档评论、管理文档权限、订阅用户评论变更事件、修改文件标题(docx、sheet、bitable、file、folder、wiki);也负责把本地 Word/Markdown/Excel/CSV 以及 Base 快照(.base)导入为飞书在线云文档(docx、sheet、bitable)。当用户需要上传或下载文件、整理云空间目录、查看文件详情、管理评论、管理文档权限、修改文件标题、订阅用户评论变更事件,或要把本地文件导入成新版文档、电子表格、多维表格/Base 时使用。 The full SKILL.md on this page shows the exact instructions the skill gives your agent.

Is the Lark Drive skill free?

Yes. Lark Drive is a free, open-source skill published from larksuite/cli. As with any third-party skill, review the source repository before installing it into an agent with sensitive access.

Does Lark Drive work with Claude Code and OpenClaw?

Yes. Skills use the portable SKILL.md format, so Lark Drive works with Claude Code, OpenClaw, Codex, Hermes, and any other agent that reads SKILL.md skills.

Featured

Reach 56,000+ AI builders from just $0.50 a click

You only pay for clicks, never impressions - and it's far cheaper than Google Ads, with no monthly lock-in.

Advertise from $0.50/click →
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
CLN.Work — Stop prompting, start hiring AI employees logoCLN.Work — Stop prompting, start hiring AI employees

Turn your Claude agents into a real team — onboard them, assign tasks, and manage them like staff.

Hire AI employees →
Deploy your OpenClaw agent in 60 seconds, live 24/7 — 10% off with code ZACAARON10 logoDeploy your OpenClaw agent in 60 seconds, live 24/7 — 10% off with code ZACAARON10

Launch OpenClaw on Hostinger in about 60 seconds and keep it live 24/7. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Deploy your Hermes agent in 60 seconds, live 24/7 — 10% off with code ZACAARON10 logoDeploy your Hermes agent in 60 seconds, live 24/7 — 10% off with code ZACAARON10

Launch Hermes on Hostinger in about 60 seconds, connect Telegram & Discord, and keep it live 24/7. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Reach 56,000+ AI builders from just $0.50 a click

You only pay for clicks, never impressions - and it's far cheaper than Google Ads, with no monthly lock-in.

Advertise from $0.50/click →
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
CLN.Work — Stop prompting, start hiring AI employees logoCLN.Work — Stop prompting, start hiring AI employees

Turn your Claude agents into a real team — onboard them, assign tasks, and manage them like staff.

Hire AI employees →
Deploy your OpenClaw agent in 60 seconds, live 24/7 — 10% off with code ZACAARON10 logoDeploy your OpenClaw agent in 60 seconds, live 24/7 — 10% off with code ZACAARON10

Launch OpenClaw on Hostinger in about 60 seconds and keep it live 24/7. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Deploy your Hermes agent in 60 seconds, live 24/7 — 10% off with code ZACAARON10 logoDeploy your Hermes agent in 60 seconds, live 24/7 — 10% off with code ZACAARON10

Launch Hermes on Hostinger in about 60 seconds, connect Telegram & Discord, and keep it live 24/7. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Reach 56,000+ AI builders from just $0.50 a click

You only pay for clicks, never impressions - and it's far cheaper than Google Ads, with no monthly lock-in.

Advertise from $0.50/click →
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
CLN.Work — Stop prompting, start hiring AI employees logoCLN.Work — Stop prompting, start hiring AI employees

Turn your Claude agents into a real team — onboard them, assign tasks, and manage them like staff.

Hire AI employees →
Deploy your OpenClaw agent in 60 seconds, live 24/7 — 10% off with code ZACAARON10 logoDeploy your OpenClaw agent in 60 seconds, live 24/7 — 10% off with code ZACAARON10

Launch OpenClaw on Hostinger in about 60 seconds and keep it live 24/7. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Deploy your Hermes agent in 60 seconds, live 24/7 — 10% off with code ZACAARON10 logoDeploy your Hermes agent in 60 seconds, live 24/7 — 10% off with code ZACAARON10

Launch Hermes on Hostinger in about 60 seconds, connect Telegram & Discord, and keep it live 24/7. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
View on GitHub

Recommended skills

Browse all →
lark-doc logo

lark-doc

larksuite/cli

373K installsInstall
lark-base logo

lark-base

larksuite/cli

372K installsInstall
lark-im logo

lark-im

larksuite/cli

371K installsInstall
lark-shared logo

lark-shared

larksuite/cli

371K installsInstall
lark-wiki logo

lark-wiki

larksuite/cli

370K installsInstall
lark-whiteboard logo

lark-whiteboard

larksuite/cli

370K installsInstall

Browse

Skills by category

Frontend250Git198Data154Testing120Design105Docs103Security96Automation87Backend76Devops37Productivity29Mcp23

Related guides

Hand-picked reading to help you choose, install, and use agent skills.

GuideBest Openclaw Skills 2026GuideHow To Evaluate Openclaw Skill Before InstallingGuideOpenclaw Skills Complete Guide

Remote OpenClaw

AI agent skills directory, marketplace, and workflow hub for OpenClaw, Hermes Agent, Claude Code, Codex, and MCP-powered operator stacks.

The Agent Stack: weekly agent tooling digest, free.

Explore

  • Home
  • Skills Directory
  • Claude Code Skills
  • Codex Skills
  • MCP Clients
  • Marketplace
  • Hermes Ecosystem
  • Free guide
  • Learn
  • Blog
  • The Agent Stack (Digest)

More

  • Submit a Tool
  • Advertise
  • Playbook
  • Free Tools
  • API
  • Shipping
  • Contact
  • Terms
  • Privacy

Know a company that should advertise here? Refer them and earn 10% — up to $300 per referral.

© 2026 Remote OpenClaw
Fazier badgeFeatured on Twelve ToolsFeatured on Wired BusinessRemote OpenClaw - Featured on AI Agents DirectoryListed on Turbo0