ASD

Lark Im

Mensajería instantánea de Feishu/Lark: enviar y responder mensajes, buscar historial, gestionar miembros de grupo, subir/descargar archivos, reacciones, avisos urgentes y tarjetas interactivas con sus callbacks.

Estrellas
16.4k

en todo el repo

Actividad
93

0–100, la ruta de este skill

Actualizado
hace 7 días

último commit aquí

Commits
34

últimos 90 días

Contexto
5.3k tok

146 tok en reposo

Paquete
59 archivos

289 KB

Instalar

Funciona con cualquier agente que lea SKILL.md

npx -y skills add larksuite/cli --skill lark-im --agent claude-code

Se instala solo en este repositorio.

Qué hace

  • Envía, responde, busca y descarga mensajes, archivos e imágenes en chats de Feishu/Lark
  • Gestiona miembros, administradores y ajustes de grupos de chat
  • Envía tarjetas interactivas y escucha callbacks de botones (card.action.trigger)
  • Gestiona reacciones, marcadores (flags), pins y accesos rápidos del feed
  • Envía avisos urgentes por app, SMS o llamada telefónica

Úsalo cuando

  • El usuario necesita enviar, buscar o revisar mensajes y archivos de chat
  • Se requiere crear o gestionar grupos, miembros o etiquetas de grupo
  • Hay que enviar o procesar tarjetas interactivas y sus callbacks
  • Se necesita gestionar accesos rápidos del feed o marcadores de mensajes

No lo uses cuando

    Qué lo activa

    Di cualquiera de estas frases y el agente debería cargar este skill.

    • Envía un mensaje de texto a este grupo de Lark
    • Busca los mensajes que mencionan 'presupuesto' en el chat de ventas
    • Crea una tarjeta interactiva y envíala al chat
    • Descarga el archivo adjunto del último mensaje del grupo

    SKILL.md

    En inglés

    im (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

    Core Concepts

    • Message: A single message in a chat, identified by message_id (om_xxx). Supports types: text, post, image, file, audio, video, sticker, interactive (card), share_chat, share_user, merge_forward, etc.
    • Chat: A group chat or P2P conversation, identified by chat_id (oc_xxx).
    • Thread: A reply thread under a message, identified by thread_id (om_xxx or omt_xxx).
    • Reaction: An emoji reaction on a message.
    • Flag: A bookmark on a message or thread.
    • Feed Shortcut: A chat pinned to the current user's feed sidebar, identified by feed_card_id (an oc_xxx open_chat_id for CHAT type).
    • Feed Group: A tag that groups feed cards in the feed list, identified by feed_group_id (ofg_xxx). Members are feed cards, each identified by feed_id + feed_type. Two types: normal (members managed explicitly) and rule (members auto-derived from rules).

    Resource Relationships

    Chat (oc_xxx)
    ├── Message (om_xxx)
    │   ├── Thread (reply thread)
    │   ├── Reaction (emoji)
    │   └── Resource (image / file / video / audio)
    └── Member (user / bot)
    

    Important Notes

    Identity and Token Mapping

    • --as user means user identity and uses user_access_token. Calls run as the authorized end user, so permissions depend on both the app scopes and that user's own access to the target chat/message/resource.
    • --as bot means bot identity and uses tenant_access_token. Calls run as the app bot, so behavior depends on the bot's membership, app visibility, availability range, and bot-specific scopes.
    • If an IM API says it supports both user and bot, the token type changes who the operator is. The same API can succeed with one identity and fail with the other because owner/admin status, chat membership, tenant boundary, or app availability are checked against the current caller.

    Sender Name Resolution

    When fetching messages (+chat-messages-list, +threads-messages-list, +messages-mget, +messages-search), the CLI shows a display name for both user and bot senders:

    • Server-provided name: the read APIs return sender_name (plus the full-i18n sender_i18n_names map) on each message sender; the CLI surfaces it as the sender's name for users and bots alike. No name lookup and no extra permission are needed — no contact scope and no application:bot.basic_info:read.
    • Fallback to id: when the server does not provide a name, the sender is shown by its id and the command still exits 0. There is no contact-directory fallback.

    The raw sender_name is not duplicated in output (its value is in name); the full sender_i18n_names map (all locales) is preserved for consumers that need a specific language, alongside an optional open_bot_id (ou_) for bot senders aligned with the message-receive event channel. System messages (msg_type: system) have no sender name — that is normal, not an error.

    Default message enrichment (reactions / update_time)

    The four message-pulling shortcuts (+messages-mget, +chat-messages-list, +messages-search, +threads-messages-list) automatically attach a reactions block and (for edited messages) update_time to each returned message — no separate im.reactions.batch_query call is needed. Pass --no-reactions to opt out. For the full contract (output shape, the im:message.reactions:read scope requirement, and the "missing field ≠ fetch failure" data rules), read references/lark-im-message-enrichment.md.

    Opt-in resource auto-download (--download-resources)

    +chat-messages-list, +messages-mget, and +threads-messages-list accept --download-resources to save eligible attachments into ./lark-im-resources/ and add a resources array to each message. It is off by default; stickers are not downloadable. A failed attachment is reported on that resource without aborting the message pull. Use +messages-resources-download for one attachment. See references/lark-im-message-enrichment.md for the output contract.

    Card Messages (Interactive)

    Before sending or replying with any interactive card (+messages-send / +messages-reply), you MUST read references/card/lark-im-card-create.md and follow its workflow. The card JSON passed to --msg-type interactive --content must be the output of that workflow — never hand-write or copy a card payload.

    Card messages (interactive type) are not yet supported for compact conversion in event subscriptions. The raw event data will be returned instead, with a hint printed to stderr.

    interactive cards support callback events (card.action.trigger) — see references/lark-im-card-action-reply.md.

    Audio Messages

    --audio sends a voice message and supports only Opus audio files, for example .opus files or Ogg Opus (.ogg) files. For mp3, wav, or other non-Opus audio, either convert to .opus first and keep using --audio, or send the original file as an attachment with --file.

    Sending Doc Content as a Message

    When sending content fetched from a Lark doc as a message, fetch the doc with --doc-format im-markdown, then send it as a message using the --markdown format. The fetched content is already in markdown; in any content-forwarding scenario, keep the fetched original text and send it in the --markdown format. Note: if the doc contains a cite tag with type="user", keep it as-is and do not strip the tag.

    Flag Types

    Flags support two layers:

    • Message-layer flag: (ItemTypeDefault, FlagTypeMessage) — regular message bookmark
    • Feed-layer flag: (ItemTypeThread/ItemTypeMsgThread, FlagTypeFeed) — thread as feed-layer bookmark

    Item types for feed-layer flags:

    • ItemTypeThread (4) = thread in a topic-style chat
    • ItemTypeMsgThread (11) = thread in a regular chat

    Feed Shortcut

    Feed shortcuts add chats to the current user's feed sidebar. They are distinct from flags:

    • Flag = bookmark on a message/thread, scoped to the user's bookmark list.
    • Feed shortcut = entry in the user's feed sidebar (currently only chats).

    Key limits:

    • Only CHAT-type (feed_card_id is oc_xxx) is exposed via OpenAPI; doc/app/subscription shortcuts exist internally but are not yet whitelisted.
    • All three operations (create/remove/list) are user-identity only — they sign with user_access_token.
    • Batch size is 10 per call for create/remove; list is a one-page wrapper with opaque page_token pagination.

    Shortcuts(推荐优先使用)

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

    Shortcut 说明
    +chat-create Create a group chat or topic chat; user/bot; --chat-mode group
    +chat-list List chats the current user/bot is a member of; defaults to groups; pass --types=p2p,group to include p2p single chats (user-only); user/bot; supports sorting, auto-pagination, --exclude-muted (user-only)
    +chat-members-list List members of a chat; returns separate users[] / bots[] buckets; callable as user or bot; --member-types filters which kinds to return; --page-all pagination; surfaces truncations[] when the server caps a bucket
    +chat-messages-list List messages in a chat or P2P conversation; user/bot; accepts --chat-id or --user-id, resolves P2P chat_id, supports time range, --order asc/desc sorting, auto-pagination
    +chat-search Search visible group chats by --query keyword and/or --member-ids; user/bot; e.g. look up chat_id by group name; supports type filters, sorting, auto-pagination, and --exclude-muted (user identity only)
    +chat-update Update group chat name or description; user/bot; updates a chat's name or description
    +messages-mget Batch get messages by IDs; user/bot; fetches up to 50 om_ message IDs, formats sender names, expands thread replies
    +messages-reply Reply to a message (supports thread replies); user/bot; supports text/markdown/post/media replies, reply-in-thread, idempotency key
    +messages-resources-download Download an image or file attached to a message; user/bot
    +messages-search Search messages across chats (supports keyword, sender, time range filters) with user or bot identity; filters by chat/sender/attachment/time, supports auto-pagination via --page-all / --page-limit, enriches results via batched mget and chats batch_query
    +messages-send Send a message to a chat or direct message; user/bot; sends to chat-id or user-id with text/markdown/post/media, supports idempotency key
    +threads-messages-list List messages in a thread; user/bot; accepts om_/omt_ input, resolves message IDs to thread_id, supports --order asc/desc sorting, auto-pagination
    +flag-create Create a bookmark on a message; user-only; defaults to message-layer flag; use --flag-type feed for feed-layer flag (item_type auto-detected from chat mode)
    +flag-cancel Cancel (remove) a bookmark. When no --flag-type is given, best-effort double-cancel: removes message layer and (when chat_type is determinable) feed layer
    +flag-list List bookmarks; user-only; auto-enriches feed-type thread entries with message content; --page-all is capped by --page-limit (default 20, max 1000), and has_more=true means the result is incomplete
    +feed-shortcut-create Add chats to the user's feed shortcuts; user-only; oc_xxx chat IDs only; batch up to 10 per call; --head/--tail controls insertion order; partial failures return an ok:false ledger
    +feed-shortcut-remove Remove chats from the user's feed shortcuts; user-only; batch up to 10 per call; removing an absent shortcut is idempotent success; real per-item failures return an ok:false ledger
    +feed-shortcut-list List one page of the user's feed shortcuts; user-only; omit --page-token for the first page; default output enriches CHAT entries under detail; pass --no-detail to skip the extra lookup and im:chat:read scope
    +feed-group-list List the caller's feed groups (tags); user-only; supports --page-all auto-pagination
    +feed-group-list-item List feed cards in a feed group (tag); user-only; enriches each item with chat_name resolved from feed_id; supports --page-all auto-pagination
    +feed-group-query-item Look up specific feed cards in a feed group (tag) by ID; user-only; enriches each item with chat_name resolved from feed_id

    API Resources

    lark-cli schema im.<resource>.<method>   # 调用 API 前必须先查看参数结构
    lark-cli im <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。

    chats

    • create — 创建群。Identity: bot only (tenant_access_token).
    • get — 获取群信息。Identity: supports user and bot; the caller must be in the target chat to get full details, and must belong to the same tenant for internal chats.
    • link — 获取群分享链接。Identity: supports user and bot; the caller must be in the target chat, must be an owner or admin when chat sharing is restricted to owners/admins, and must belong to the same tenant for internal chats.
    • update — 更新群信息。Identity: supports user and bot.

    chat.members

    • create — 将用户或机器人拉入群聊。Identity: supports user and bot; the caller must be in the target chat; for bot calls, added users must be within the app's availability; for internal chats the operator must belong to the same tenant; if only owners/admins can add members, the caller must be an owner/admin, or a chat-creator bot with im:chat:operate_as_owner.
    • delete — 将用户或机器人移出群聊。Identity: supports user and bot; only group owner, admin, or creator bot can remove others; max 50 users or 5 bots per request.

    chat.user_setting

    • batch_query — 批量查询当前用户在群内的个人偏好设置 (e.g. is_muted mutes normal messages, is_mute_at_all mutes @all messages); up to 10 chats per request. Identity: user only (user_access_token); the caller must be in each target chat.
    • batch_update — 批量更新当前用户在群内的个人偏好设置 (e.g. is_muted mutes normal messages, is_mute_at_all mutes @all messages); up to 10 chats per request. Identity: user only (user_access_token); the caller must be in each target chat.

    chat.nickname

    • get — 获取自己的群昵称。Get your own nickname in the chat (self-only). Identity: user only (user_access_token); returns an empty string when no nickname is set.
    • update — 设置自己的群昵称。Set or update your own nickname in the chat (self-only). Identity: user only (user_access_token); nickname must be a non-empty string (max 300 bytes). Use DELETE to clear it.
    • delete — 清空自己的群昵称。Clear your own nickname in the chat (self-only). Identity: user only (user_access_token).

    chat.managers

    • add_managers — 指定群管理员。Identity: supports user and bot; only the group owner can add managers; max 10 managers per chat (20 for super-large chats), and at most 5 bots per request.
    • delete_managers — 删除群管理员。Identity: supports user and bot; only the group owner can remove managers; max 50 users or 5 bots per request.

    chat.moderation

    • get — 获取群成员发言权限。Identity: supports user and bot; the caller must be in the target chat and belong to the same tenant.
    • update — 更新群发言权限。Identity: supports user and bot; only the group owner (or creator bot with im:chat:operate_as_owner) can update; the caller must be in the chat.

    messages

    • delete — 撤回消息。Identity: supports user and bot; for bot calls, the bot must be in the chat to revoke group messages; to revoke another user's group message, the bot must be the owner, an admin, or the creator; for user P2P recalls, the target user must be within the bot's availability.
    • forward — 转发消息。Identity: supports user and bot.
    • merge_forward — 合并转发消息。Identity: bot only (tenant_access_token).
    • read_users — 查询消息已读信息。Identity: bot only (tenant_access_token); the bot must be in the chat, and can only query read status for messages it sent within the last 7 days.
    • urgent_app — 发送应用内加急。Identity: bot only (tenant_access_token); the bot must be the message sender and must be in the conversation that contains the message.
    • urgent_phone — 发送电话加急。Identity: bot only (tenant_access_token); the bot must be the message sender and must be in the conversation that contains the message.
    • urgent_sms — 发送短信加急。Identity: bot only (tenant_access_token); the bot must be the message sender and must be in the conversation that contains the message.

    reactions

    • batch_query — 批量获取消息表情。Identity: supports user and bot.Must-read
    • create — 添加消息表情回复。Identity: supports user and bot; the caller must be in the conversation that contains the message.Must-read
    • delete — 删除消息表情回复。Identity: supports user and bot; the caller must be in the conversation that contains the message, and can only delete reactions added by itself.Must-read
    • list — 获取消息表情回复。Identity: supports user and bot; the caller must be in the conversation that contains the message.Must-read

    threads

    • forward — 转发话题。Identity: supports user and bot.

    images

    • create — 上传图片。Identity: bot only (tenant_access_token).

    pins

    • create — Pin 消息。Identity: supports user and bot.
    • delete — 移除 Pin 消息。Identity: supports user and bot.
    • list — 获取群内 Pin 消息。Identity: supports user and bot.

    feed.groups

    • batch_add_item — Batch add feed cards to a feed group. Identity: user only (user_access_token).Must-read
    • batch_query — Batch query feed groups. Identity: user only (user_access_token).Must-read
    • batch_remove_item — Batch remove feed cards from a feed group. Identity: user only (user_access_token).Must-read
    • create — Create a feed group. Identity: user only (user_access_token).Must-read
    • delete — Delete a feed group. Identity: user only (user_access_token).Must-read
    • update — Update a feed group. Identity: user only (user_access_token).Must-read

    权限表

    方法 所需 scope
    chats.create im:chat:create
    chats.get im:chat:read
    chats.link im:chat:read
    chats.update im:chat:update
    chat.members.create im:chat.members:write_only
    chat.members.delete im:chat.members:write_only
    chat.members.get im:chat.members:read
    +chat-members-list im:chat.members:read
    chat.user_setting.batch_query im:chat.user_setting:read
    chat.user_setting.batch_update im:chat.user_setting:write
    chat.managers.add_managers im:chat.managers:write_only
    chat.managers.delete_managers im:chat.managers:write_only
    chat.moderation.get im:chat.moderation:read
    chat.moderation.update im:chat:moderation:write_only
    messages.delete im:message:recall
    messages.forward im:message
    messages.merge_forward im:message
    messages.read_users im:message:readonly
    messages.urgent_app im:message.urgent
    messages.urgent_phone im:message.urgent:phone
    messages.urgent_sms im:message.urgent:sms
    reactions.batch_query im:message.reactions:read
    reactions.create im:message.reactions:write_only
    reactions.delete im:message.reactions:write_only
    reactions.list im:message.reactions:read
    threads.forward im:message
    images.create im:resource
    pins.create im:message.pins:write_only
    pins.delete im:message.pins:write_only
    pins.list im:message.pins:read
    feed.groups.batch_add_item im:feed_group_v1:write
    feed.groups.batch_query im:feed_group_v1:read
    feed.groups.batch_remove_item im:feed_group_v1:write
    feed.groups.create im:feed_group_v1:write
    feed.groups.delete im:feed_group_v1:write
    feed.groups.update im:feed_group_v1:write

    Reproducido de larksuite/cli bajo licencia MIT. Leer esta página en markdown.

    Archivos

    59 archivos en el paquete. Solo se lee SKILL.md al activarse — las referencias se cargan si el skill decide que las necesita.

    Antes de instalar

    Requiere el binario lark-cli y haber leído primero ../lark-shared/SKILL.md para autenticación y permisos.

    Detalles

    Creador
    larksuite
    Categoría
    Automatización
    Licencia
    MIT
    Recursos incluidos
    referencias
    Repositorio
    larksuite/cli
    Código fuente
    Ver SKILL.md

    Más de larksuite/cli

    Este repo incluye 28 skills. Si instalas uno, normalmente ya tienes los demás.

    Operaciones sobre documentos en la nube de Lark (Docx/Wiki): leer, crear y editar documentos, insertar o descargar imágenes/adjuntos, y gestionar notas mentales.

    Costo de contexto al activarse
    1k tok
    Tamaño del paquete
    44 archivos
    Última actualización
    hace 3 días
    documentos

    飞书幻灯片: crea y edita presentaciones, lee contenido de slides, gestiona páginas (crear, eliminar, leer, reemplazo parcial). No cubre documentos, pizarras ni archivos generales.

    Costo de contexto al activarse
    7k tok
    Tamaño del paquete
    50 archivos
    Última actualización
    hace 3 días
    documentos

    Drive de Feishu/Lark: gestiona archivos y carpetas (subir/descargar, copiar/mover/eliminar, metadatos, permisos, comentarios, versiones, etiquetas de confidencialidad) e importa archivos locales como docx/sheet/bitable/slides.

    Costo de contexto al activarse
    6.3k tok
    Tamaño del paquete
    61 archivos
    Última actualización
    hace 3 días
    documentos

    Operaciones en Lark Base (multitabla): tablas, campos, registros, vistas, fórmulas/lookup, formularios, dashboards, workflows y roles; se usa ante Base/多维表格/bitable o enlaces /base/.

    Costo de contexto al activarse
    6.2k tok
    Tamaño del paquete
    30 archivos
    Última actualización
    anteayer
    bases de datos

    Desarrollo y hosting de apps Miaoda/Spark: creación, desarrollo local o en la nube, diseño creativo, integraciones de IA/Feishu, logs, métricas, variables de entorno, colaboradores, roles y triggers.

    Costo de contexto al activarse
    6.2k tok
    Tamaño del paquete
    55 archivos
    Última actualización
    hace 3 días
    herramientas desarrollo

    Base de conocimiento de Feishu: gestiona espacios wiki, miembros de espacios y nodos de documentos; crea, consulta, mueve y organiza documentos y accesos directos dentro de la wiki.

    Costo de contexto al activarse
    3.2k tok
    Tamaño del paquete
    14 archivos
    Última actualización
    hace 3 días
    documentos

    Skills relacionados

    Úsalo cuando enfrentes 2 o más tareas independientes que puedan trabajarse sin estado compartido ni dependencias secuenciales.

    Costo de contexto al activarse
    1.5k tok
    Tamaño del paquete
    1 archivo
    Última actualización
    el mes pasado
    automatizacion

    Úsalo al ejecutar planes de implementación con tareas independientes dentro de la sesión actual.

    Costo de contexto al activarse
    8.1k tok
    Tamaño del paquete
    7 archivos
    Última actualización
    anteayer
    automatizacion

    Interrógame sobre las specs de los workflows que quiero construir, dentro de este workspace.

    Costo de contexto al activarse
    640 tok
    Tamaño del paquete
    2 archivos
    Última actualización
    hace 16 días
    automatizacion