跪拜 Guibai
← All articles
Artificial Intelligence · Hacking · OpenAI

Feishu CLI Gives AI Agents Hands to Operate Your Entire Office Suite

By 周一同学Zelina ·
Read original on juejin.cn ↗ Google Translate ↗ Alt translation

Most AI-in-the-workplace demos stop at generating text; this integration closes the loop by letting the agent execute the final step inside the tools teams already use. For any developer or team running on Feishu/Lark, it eliminates the manual copy-paste tax on routine ops—spreadsheet formatting, report assembly, meeting scheduling—and shifts the bottleneck from tool operation to clear thinking.

Summary

The Feishu CLI (lark-cli) bridges the gap between AI chat and actual work by giving language models direct control over Feishu's office tools. Instead of copying AI-generated text into documents or manually updating spreadsheets, a developer can install the CLI inside an agent like Codex and issue plain-English commands that create cloud docs, populate multidimensional tables, configure automations, generate slide decks, draw vector diagrams on whiteboards, and send personalized messages to colleagues.

A walkthrough covers eight practical scenarios: drafting and reviewing documents with inline comments, building project trackers with automated deadline reminders, cross-table aggregation for weekly reports, generating onboarding slide decks and fashion ordering fair presentations, converting Mermaid diagrams into editable whiteboard flowcharts, running JS-driven high-density infographics like radar charts and product roadmaps, batch-sending individualized notifications, and extracting action items from meeting minutes into Feishu Tasks.

The tool covers 100+ skills under an MIT license and requires only Node.js and a few CLI commands to set up. A restart of the agent host is mandatory for skills to load, and OAuth authorization determines whether the AI can read personal data like calendars and private messages.

Takeaways
Feishu CLI is an MIT-licensed open-source tool that exposes 100+ office operations across 11 domains as command-line actions an AI agent can invoke.
Installation requires Node.js 16+, a global npm install of @larksuite/cli, adding skills via npx, and running lark-cli config init --new.
Codex must be restarted after configuration; skills are not hot-reloaded and will not appear until a full restart.
OAuth authorization is optional but unlocks personal data access—calendars, private messages, and user-specific document permissions.
Cloud documents can be created, reviewed with inline comments, and revised by the AI without leaving Feishu.
Multidimensional tables support natural-language creation, data entry, filtered queries, automation rules (e.g., deadline reminders), and dashboard views with charts.
Cross-table aggregation lets the AI read multiple tables, compute statistics, and write a formatted weekly report into a Feishu doc.
Slides and whiteboards are generated as editable native Feishu files, not static exports; whiteboards can render Mermaid, mind maps, org charts, Gantt charts, and JS-driven infographics like radar charts.
Calendar scheduling pulls multiple attendees' availability, handles time zones, and creates the meeting directly.
Meeting minutes can be parsed to extract action items, which are then created as Feishu Tasks and posted to the relevant group chat.
Enterprise admins retain control; CLI-created apps still respect the organization's unified governance rules on the Feishu developer platform.
Conclusions

The real unlock is not the CLI itself but the combination of a local agent runtime (Codex) with a permissioned API surface—this turns the AI from a text generator into an authenticated user that can act on your behalf across an entire office suite.

Requiring a full restart of Codex for skills to load is a sharp edge that will trip up first-time users; it signals that the agent-plugin architecture is still early and not designed for seamless discovery.

The whiteboard's ability to run JavaScript for coordinate-level layout pushes it past simple diagram generation into a programmable visualization engine, which is unusual for an office suite integration.

Cross-table aggregation and automated dashboard creation hint at a future where weekly reporting is a fully automated pipeline, not a recurring human task—provided the underlying tables are kept current.

The authorization model creates a meaningful split: without OAuth, the AI is a public-space operator; with it, the AI becomes a full delegate with access to private calendar and message data, which raises trust and security questions that the guide does not address.

Concepts & terms
Feishu CLI (lark-cli)
An open-source command-line tool by Feishu (Lark) that wraps the platform's APIs into terminal commands, enabling AI agents to create documents, manage tables, send messages, schedule meetings, and perform 100+ other office operations programmatically.
Codex
An OpenAI desktop agent runtime that can execute local CLI commands and skills, acting as the host environment where Feishu CLI is installed so natural-language prompts translate into Feishu actions.
Multidimensional Table
Feishu's database-like table format supporting multiple views (grid, kanban, calendar, dashboard), field types, linked records, and automation rules—similar to Airtable or Notion databases.
Skills (in Codex context)
Pre-packaged capabilities added to Codex via npx that teach the agent how to use specific tools; Feishu CLI provides 19 skills covering different business domains like docs, sheets, calendar, and whiteboard.
Source: juejin.cn ↗ Google Translate ↗ Backup ↗