Markitdown
ImCa0/just-laws
Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.
飞书云空间(云盘/云存储):管理 Drive 文件和文件夹,包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、评论/权限/订阅、标题、版本、飞书文档密级标签(secure labels)和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题,或导入 Word/Markdown/Excel/CSV/PPTX/.base 为…
$ npx skills add rongxinzy/RongxinAI --skill lark-drive -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install rongxinzy/RongxinAI lark-drive --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/rongxinzy/RongxinAI.git skills-src && mkdir -p .claude/skills && cp -r skills-src/MCPs/feishu/skills/lark-drive .claude/skills/lark-drive && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "lark-drive" agent skill from https://github.com/rongxinzy/RongxinAI/tree/main/MCPs/feishu/skills/lark-drive into .claude/skills/lark-drive/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lark-drive", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/rongxinzy/RongxinAI/tree/main/MCPs/feishu/skills/lark-driveType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add rongxinzy/RongxinAI --skill lark-drive -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install rongxinzy/RongxinAI lark-drive --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rongxinzy/RongxinAI.git skills-src && mkdir -p .agents/skills && cp -r skills-src/MCPs/feishu/skills/lark-drive .agents/skills/lark-drive && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "lark-drive" agent skill from https://github.com/rongxinzy/RongxinAI/tree/main/MCPs/feishu/skills/lark-drive into .agents/skills/lark-drive/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lark-drive", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add rongxinzy/RongxinAI --skill lark-drive -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install rongxinzy/RongxinAI lark-drive --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rongxinzy/RongxinAI.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/MCPs/feishu/skills/lark-drive .cursor/skills/lark-drive && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "lark-drive" agent skill from https://github.com/rongxinzy/RongxinAI/tree/main/MCPs/feishu/skills/lark-drive into .cursor/skills/lark-drive/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lark-drive", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/rongxinzy/RongxinAI.git --path MCPs/feishu/skills/lark-drive--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add rongxinzy/RongxinAI --skill lark-drive -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install rongxinzy/RongxinAI lark-drive --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rongxinzy/RongxinAI.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/MCPs/feishu/skills/lark-drive .gemini/skills/lark-drive && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "lark-drive" agent skill from https://github.com/rongxinzy/RongxinAI/tree/main/MCPs/feishu/skills/lark-drive into .gemini/skills/lark-drive/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lark-drive", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install rongxinzy/RongxinAI lark-driveInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add rongxinzy/RongxinAI --skill lark-drive -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/rongxinzy/RongxinAI.git skills-src && mkdir -p .github/skills && cp -r skills-src/MCPs/feishu/skills/lark-drive .github/skills/lark-drive && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "lark-drive" agent skill from https://github.com/rongxinzy/RongxinAI/tree/main/MCPs/feishu/skills/lark-drive into .github/skills/lark-drive/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lark-drive", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add rongxinzy/RongxinAI --skill lark-drive -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install rongxinzy/RongxinAI lark-drive --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rongxinzy/RongxinAI.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/MCPs/feishu/skills/lark-drive .opencode/skills/lark-drive && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "lark-drive" agent skill from https://github.com/rongxinzy/RongxinAI/tree/main/MCPs/feishu/skills/lark-drive into .opencode/skills/lark-drive/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lark-drive", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
lark-drive飞书云空间(云盘/云存储):管理 Drive 文件和文件夹,包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、评论/权限/订阅、标题、版本、飞书文档密级标签(secure labels)和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题,或导入 Word/Markdown/Excel/CSV/PPTX/.base 为…
Lark Drive is an agent skill from rongxinzy/RongxinAI. 飞书云空间(云盘/云存储):管理 Drive 文件和文件夹,包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、评论/权限/订阅、标题、版本、飞书文档密级标签(secure labels)和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题,或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用;doubao.com 云空间 URL/token 也按资源路径和 token 路由,不回退 WebFetch。不负责:文档内容编辑(走 lark-doc)、表格/Base 表内数据操作(走 lark-sheets/lark-base)、知识空间节点/成员管理(走 lark-wiki)、原生 Markdown 文件读写/patch/diff(走 lark-markdown)。
Its SKILL.md is about 4.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 48 other files, including reference files (for example `references/lark-drive-add-comment.md`, `references/lark-drive-apply-permission.md` and `references/lark-drive-comment-location.md`).
It sits in Documents & Office, covering Messaging and chat bots, Word documents and Excel spreadsheets. It works with Microsoft Word, Microsoft Excel and Microsoft PowerPoint. The repository describes itself as: An all-in-one local AI Agent workspace with a fully self-developed stack. The licence is AGPL-3.0.
Read from SKILL.md and the folder at commit 9c64865. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
From the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
xxx.feishu.cnFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
DOC_TOKENFOLDER_TOKENFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Lark Drive loads about 4.5k tokens when it runs, and up to ~110k if it reads all its reference files. Until then it costs about 106 tokens; SKILL.md has 1,130 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from rongxinzy/RongxinAI at commit 9c64865, republished under its AGPL-3.0 licence (© rongxinzy). 1,130 words, ~4,468 tokens.
.claude/skills/lark-drive/SKILL.md (or your agent's skills folder). This skill also uses 47 other files; get the full folder from GitHub.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
术语说明: 飞书云空间也常被称为"云盘"、"云存储"、"网盘"或"我的空间",这些说法通常指的是同一个产品,是飞书官方的云端文件存储与管理中心。
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。
副本分流规则: 如果用户要复制在线文档、创建文档副本、把文档复制到另一个文件夹,必须使用
lark-cli drive files copy。不要用drive +export下载后再drive +import上传,也不要用docs +fetch+docs +create重建正文;导出/导入只用于本地文件转换或离线产物。
lark-wiki,使用 lark-cli wiki +move-to-drive;不要把 Wiki token 直接交给 drive +move。这是会改变文档归属和权限继承的写操作,执行前确认源节点与目标位置。lark-cli drive files copy。先用 lark-cli schema drive.files.copy --format json 确认参数;如果来源是 wiki URL/token,先用 lark-cli drive +inspect 获取底层 token 和 type,不要把 wiki token 直接当 file_token。params.file_token 传源文档 token,data.folder_token 传目标文件夹 token,data.name 传副本名称,data.type 传源文件类型(如 docx / sheet / bitable / slides)。示例:lark-cli drive files copy --params '{"file_token":"<DOC_TOKEN>"}' --data '{"folder_token":"<FOLDER_TOKEN>","name":"<COPY_NAME>","type":"docx"}'。如返回 confirmation_required,按 lark-shared 高风险审批协议向用户确认后,在原命令末尾追加 --yes 重试。lark-cli drive +inspect --url '<url>' 进行识别;具体用法、失败处理和边界见 references/lark-drive-inspect.md。references/lark-drive-workflow.md,再按其中 Workflow Registry 进入 permission_governance workflow。references/lark-drive-secure-label.md;这是 Drive 文件治理能力。references/lark-drive-workflow.md,再按其中 Workflow Registry 进入 permission_governance workflow。references/lark-drive-workflow.md,再按其中 Workflow Registry 进入 topic_move_collector workflow。该 workflow 负责搜索召回、内容验证、相关性分类、移动计划、写前确认和结果验证;禁止直接从 drive +search 或 drive +move 开始。references/lark-drive-workflow.md,再按其中 Workflow Registry 进入 knowledge_organize workflow。默认只生成方案;创建目录、移动资源、申请权限都必须单独确认。topic_move_collector;对已知文件夹、文档库或知识库做目录盘点和结构重组,进入 knowledge_organize;只移动一个已明确资源时仍使用原子移动命令。lark-cli drive +search。自然语言里"最近我编辑过的"、"我创建的"(→ --created-by-me,原始创建者语义)、"我负责/owner 的"(→ --mine,owner 语义)、"最近一周我打开过的 xxx"、"某人 owner 的 docx" 等直接映射到扁平 flag,避免手写嵌套 JSON。lark-cli drive +list-comments --url '<url>',不要优先手写 drive file.comments list;支持妙搭 apps 的 /page/<token> URL;具体使用方式先阅读 references/lark-drive-list-comments.md。apps(file_type=apps),裸 token 调 shortcut 时传 --type apps。file_type=docx)的文档支持通过 drive +list-comments --need-relation 返回评论位置,其他类型会静默忽略该参数;具体用法需要先阅读 references/lark-drive-comment-location.md 了解。.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。.md / .docx / .doc / .txt / .html 导入成在线文档,使用 lark-cli drive +import --type docx。.pptx 导入成飞书幻灯片,使用 lark-cli drive +import --type slides;当前 PPTX 导入上限是 500MB。drive +import 且目标是同一个位置(同一 --folder-token、默认根目录,或同一 --target-token)时,必须串行执行;不要并发导入到同一位置,服务端可能返回并发冲突错误。.md 文件(不是导入成 docx),切到 lark-markdown。.md 文件的历史版本差异,或比较远端 Markdown 与本地草稿,切到 lark-markdown 的 lark-cli markdown +diff;需要版本号时先用 drive +version-history。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。.xlsx / .xls / .csv 导入成电子表格,使用 lark-cli drive +import --type sheet。lark-cli drive +create-folder。lark-cli drive +preview。lark-cli drive +cover;先 --list-only 看规格,再选 --spec 下载。lark-cli drive +export --url '<文档 URL>' --file-extension <格式>;详细参数、Wiki token 和错误码处理见 references/lark-drive-export.md。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。lark-cli drive +inspect 解包;+inspect 失败后不要自动切到别的写接口继续尝试,先按错误提示处理权限、scope 或链接问题。drive +inspect / drive +upload 遇到 not found、permission denied、missing scope 时,默认停止重试;只有 rate limit 或临时网络错误才适合有限重试。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。
| URL 格式 | 示例 | Token 类型 | 处理方式 |
|---|---|---|---|
/docx/ | https://example.larksuite.com/docx/doxcnxxxxxxxxx | file_token | URL 路径中的 token 直接作为 file_token 使用 |
/doc/ | https://example.larksuite.com/doc/doccnxxxxxxxxx | file_token | URL 路径中的 token 直接作为 file_token 使用 |
/wiki/ | https://example.larksuite.com/wiki/wikcnxxxxxxxxx | wiki_token | 不能直接当底层 file_token;优先用 drive +inspect 解包获取 obj_token |
/sheets/ | https://example.larksuite.com/sheets/shtcnxxxxxxxxx | file_token | URL 路径中的 token 直接作为 file_token 使用 |
/page/ | https://example.feishu.cn/page/N1BWmMrqndT5ZcamAIBcnvDLnOf/ | apps token | 妙搭 apps 类型;用于评论列表时直接作为 file_token,file_type=apps |
/drive/folder/ | https://example.larksuite.com/drive/folder/fldcnxxxx | folder_token | URL 路径中的 token 作为文件夹 token 使用 |
lark-cli drive +inspect --url 'https://xxx.feishu.cn/wiki/wikcnXXX'知识库链接背后可能是 docx、sheet、bitable、slides、file 等不同对象。后续要做评论、下载、导出或内容读取时,优先用 drive +inspect 拿到 type、token、title、url;完整手动解析和跨 skill 路由见共享文档 lark-wiki-token-routing.md。不要只根据 /wiki/<token> 猜底层类型。
| 操作 | 需要的 Token | 说明 |
|---|---|---|
| 读取文档内容 | file_token / 通过 docs +fetch 自动处理 | docs +fetch 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,sheet 使用 <sheetId>!<cell>,slides 使用 <slide-block-type>!<xml-id>;Base 只有记录局部评论,定位为 file_token(base_token) + --block-id <table-id>!<record-id>!<view-id> |
| 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、白名单扩展名的 Drive file,以及最终解析为 doc/docx/file 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 | URL 或 file_token | 优先使用 drive +list-comments --url '<url>';wiki URL/token 会自动解析到底层真实 token/type;妙搭 apps URL 使用 /page/<token> |
+add-comment:review / 审阅 / 校对场景默认尽量创建局部评论,不要把多个可定位问题合并为一条全文评论。+list-comments:推荐传 --url,支持 wiki 自动解包;参数细节见 reference。lark-drive-comments-guide.md。file_type=docx,再读 lark-drive-comment-location.md,并使用 drive +list-comments --need-relation;其他文档类型会静默忽略该参数。lark-drive-reactions.md;只有用户明确需要 reaction 信息时才带 need_reaction=true。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。<、>;提交前必须先转义:< -> <,> -> >。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。--type bitable / --type base 或 /base/、/bitable/、wiki Base 链接;bitable 和 Base 是同一概念,bitable 是内部代号、Base 是产品名,裸 token 推荐传 bitable,base 仅作为兼容别名兜底。--block-id <table-id>!<record-id>!<view-id>,其中 table/record/view ID 通常分别以 tbl/rec/vew 开头。view_id 只决定被提及时点击通知打开哪个视图,不影响评论挂载点;只要在同一记录上都能看到评论,但必须传,否则通知无法确定跳转视图。ID 可通过 lark-base 获取。doc/docx/file/sheet/slides/bitable/base,不要用 +add-comment。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;docx/sheet/slides 局部评论传 anchor.block_id,Base 记录局部评论传 anchor.block_id(table_id)、anchor.base_record_id、anchor.base_view_id。drive.file.comments.* / drive.file.comment.replys.* 评论 Base 文档时,file_type 填 bitable,不要填 base。| 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_type | file_type 参数错误 | 根据 obj_type 传入正确的 file_type(docx/doc/sheet/slides/bitable/apps) |
232140101 / 232140100 / 233523001(常见于 drive +import 的 job_error_msg) | 同一位置下存在并发导入 / 创建操作 | 批量导入到同一文件夹、根目录或同一 --target-token 时改为串行执行;每个失败项每次重试前等待几秒,总共最多重试 3 次,仍失败就停止并报告冲突 |
permission.public.patch 的 91009 / 91010 / 91011 / 91012 错误时,先读 lark-drive-permission-guide.md。+apply-permission。lark-shared 处理;不要把租户安全策略、对外分享、密级拦截简单归类为缺 scope。lark-doc。lark-sheets。lark-base。lark-wiki;上传本地文件到 wiki 节点仍用 drive +upload --wiki-token。lark-markdown;把 Markdown 导入成在线 docx 才用 drive +import --type docx。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 |
|---|---|
+search | 搜索文档、Wiki、表格、文件夹等云空间对象;支持 --edited-since、--created-by-me、--mine、--doc-types 等扁平 flag;区分 original creator 与 owner 语义。 |
+upload | 上传本地文件到 Drive 文件夹或 wiki 节点;修改/重写/更新已有文件时优先覆盖上传,而不是直接上传一个新文件。 |
+create-folder | 新建 Drive 文件夹,支持父文件夹与 bot 创建后自动授权。 |
+download | 下载 Drive 文件到本地。 |
+preview | 查看或下载文件的 PDF / HTML / 文本 / 图片等预览产物。 |
+cover | 查看或下载文件封面图规格。 |
+status | 比较本地目录与 Drive 文件夹差异;默认按 SHA-256 精确比较,--quick 使用修改时间近似比较。 |
+pull | 从 Drive 拉取文件到本地目录,支持重复远端路径处理和增量模式。 |
+sync | 双向同步本地目录与 Drive 文件夹:拉取 new_remote、推送 new_local,modified 按 --on-conflict=remote-wins|local-wins|keep-both|ask 处理;--quick 用修改时间近似比较;--on-duplicate-remote 支持 fail / newest / oldest;只同步 type=file,跳过在线文档和 shortcut,且不会删除两端多余文件。 |
+push | 将本地目录推送到 Drive 文件夹,支持 skip / smart / overwrite 与确认后删除远端。 |
+create-shortcut | 在另一个文件夹里创建现有 Drive 文件的快捷方式。 |
+add-comment | 给 doc/docx/file/sheet/slides/base(bitable) 添加评论,也支持解析到这些类型的 wiki URL;评论统计、回复和 reaction 细则见 lark-drive-comments-guide.md。 |
+list-comments | 获取 doc/docx/sheet/file/slides/base(bitable)/apps 评论列表;优先传 URL,支持 wiki 自动解包和妙搭 /page/<token> URL。 |
+export | 将 doc/docx/sheet/bitable/slides 导出为本地文件。 |
+export-download | 根据导出产物的 file_token 下载文件。 |
+import | 将本地文件导入为飞书在线文档、表格、多维表格或幻灯片。 |
+version-history | 查看文件历史版本。 |
+version-get | 下载指定历史版本。 |
+version-revert | 回滚到指定历史版本。 |
+version-delete | 删除指定历史版本。 |
+move | 移动 Drive 文件或文件夹;Wiki 层级移动走 lark-wiki。 |
+delete | 删除 Drive 文件或文件夹,文件夹删除会轮询异步任务。 |
+task_result | 查询 import/export/move/delete 等异步任务结果。 |
+inspect | 检视 URL 的类型、标题和 canonical token;wiki URL 会自动解包到底层文档。 |
+apply-permission | 以 user 身份向文档 owner 申请访问权限。 |
+member-add | 添加一个或最多 10 个 Drive 文档、文件、文件夹或 wiki 节点协作者/授权成员;封装 Drive permission member create/batch_create,真实写入需要 --yes。 |
+secure-label-list | 列出当前用户可用的密级标签。 |
+secure-label-update | 更新 Drive 文件或文档的密级标签。 |
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。高频原生命令: 读取 Drive 文件夹清单时使用
drive files list,使用前先读references/lark-drive-files-list.md,按模板通过--params传参并手动处理分页;不要把--page-all输出直接交给 JSON 解析脚本。
copy — 复制文件;在线文档创建副本的首选能力,完整参数见上方“快速决策”,不要用 drive +export / drive +import 绕行复制create_folder — 新建文件夹list — 获取文件夹下的清单;使用前阅读 references/lark-drive-files-list.mdpatch — 修改文件标题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create — 添加回复delete — 删除回复list — 获取回复update — 更新回复auth — create — 增加协作者权限transfer_owner —batch_query — 获取文档元数据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get — 获取文件统计信息lark-cli drive file.statistics get --file-token <token> --file-type <type> --format json;--params JSON 也支持,适合批量拼装或 raw 参数场景。list — 获取文档的访问者记录lark-cli drive file.view_records list --file-token <docx_token> --file-type docx --page-size <N> --viewer-id-type open_id --format json;--params JSON 也支持,适合批量拼装、分页续跑或 raw 参数场景。update_reaction — 添加/删除 reactionget — 获取当前用户的容量信息,包含各业务使用量、租户配额是否超限、用户配额、所在部门配额--as user,不要使用默认的 bot 身份quota_detail_id 传当前用户的 user_id© rongxinzy, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 47 other files (references) in MCPs/feishu/skills/lark-drive of rongxinzy/RongxinAI.
Open the folder on GitHubat commit 9c64865
We found 3 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 3 other GitHub owners. This page covers the copy in rongxinzy/RongxinAI, which our catalogue first saw on October 7, 2026.
Lark Drive next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Lark Drive this skillrongxinzy/RongxinAI | 154 | 3 repos | ~4.5k | Automated safety check: Pass | AGPL-3.0 | |
| MarkitdownImCa0/just-laws | 781 | 14 repos | ~3.2k | Automated safety check: Notes | MIT | |
| Docx4jplutext/docx4j | 2.4k | — | ~2.5k | Automated safety check: Pass | None | |
| Cyber Pptcrazyykhllc-bit/CyberPPT | 1.8k | — | ~10k | Automated safety check: Pass | MIT | |
| PDFzai-org/ZCode | 7.7k | — | ~18k | Automated safety check: Notes | Proprietary | |
| Markitshift-labs-ai/markit | 1.3k | — | ~299 | Automated safety check: Pass | MIT |
ImCa0/just-laws
Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.
plutext/docx4j
A skill your agent uses when writing Java code that creates, reads or edits Word (.docx), PowerPoint (.pptx) or Excel (.xlsx) files with docx4j — including generating documents, editing existing…
crazyykhllc-bit/CyberPPT
当用户需要把 DOCX、PDF、TXT、XLSX、研究报告、业务材料或原始数据转成高密度、可编辑、咨询风格 PPTX 时使用;也适用于需要 SCR 论证、视觉风格探索、详细图表和渲染质检的 PPT。
zai-org/ZCode
Professional PDF toolkit covering four production workflows: reports, creative visuals, academic LaTeX, and existing PDF processing.
shift-labs-ai/markit
Convert files and URLs to Markdown. An agent skill from shift-labs-ai/markit.
jimmc414/Kosmos
Convert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing.
rongxinzy/RongxinAI
SaaS financial health advisor. An agent skill from rongxinzy/RongxinAI.
rongxinzy/RongxinAI
Reduce voluntary and involuntary churn through cancel flow design, save offers, exit surveys, and dunning sequences.
rongxinzy/RongxinAI
The only skill for creating a new PowerPoint deck. An agent skill from rongxinzy/RongxinAI.
rongxinzy/RongxinAI
ZhiYuan Agent expert package lifecycle manager for the pi engine.
rongxinzy/RongxinAI
Professional Ziwei Doushu consultation skill with an offline calculation engine.
rongxinzy/RongxinAI
飞书邮箱:Use when user mentions 起草邮件、写邮件、草稿、发送/回复/转发邮件、查阅邮件、看邮件、搜索邮件、邮件文件夹、邮件标签、邮件联系人、监听新邮件、邮件收信规则等;use for mail/email intent only.
Categories
飞书云空间(云盘/云存储):管理 Drive 文件和文件夹,包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、评论/权限/订阅、标题、版本、飞书文档密级标签(secure labels)和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题,或导入 Word/Markdown/Excel/CSV/PPTX/.base 为…. Lark Drive is an agent skill from rongxinzy/RongxinAI.
Lark Drive fits situations like: tasks that involve Messaging and chat bots; tasks that involve Word documents; tasks that involve Excel spreadsheets.
Run `npx skills add rongxinzy/RongxinAI --skill lark-drive -a claude-code`. Or copy the skill folder (MCPs/feishu/skills/lark-drive in rongxinzy/RongxinAI) into .claude/skills/lark-drive in your project. Claude Code loads it when a task matches its description.
Run `npx skills add rongxinzy/RongxinAI --skill lark-drive -a codex`. Or copy the skill folder (MCPs/feishu/skills/lark-drive in rongxinzy/RongxinAI) into .agents/skills/lark-drive in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add rongxinzy/RongxinAI --skill lark-drive -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/lark-drive, .gemini/skills/lark-drive, .github/skills/lark-drive and .opencode/skills/lark-drive in your project.
Going by SKILL.md and its folder, Lark Drive needs credentials named DOC_TOKEN and FOLDER_TOKEN. Our summary lists: A credential in DOC_TOKEN; A credential in FOLDER_TOKEN.
SKILL.md names 1 domain. In commands or code: xxx.feishu.cn; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Lark Drive is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.5k tokens (SKILL.md is roughly 18k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 106k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Lark Drive: Markitdown (ImCa0/just-laws, 781 stars), Docx4j (plutext/docx4j, 2.4k stars), Cyber Ppt (crazyykhllc-bit/CyberPPT, 1.8k stars) and PDF (zai-org/ZCode, 7.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
rongxinzy (a GitHub organization) maintains it in rongxinzy/RongxinAI, which has 154 GitHub stars. The repository holds 94 skills in this directory. The repository was last updated on October 10, 2026.
Source: rongxinzy/RongxinAI on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.