Skip to content

Lark Contact Lookup

Look up Lark/Feishu colleagues and bots by name, email or open_id via the lark-cli tool.

Repository
larksuite/cli
Stars
17,928
Licence
MIT
Files
4 files

What it does

This skill teaches an AI agent how to use the lark-cli command-line tool to look up people and bots in Lark (the international name for Feishu, a workplace chat and collaboration suite). Given a colleague's name or email, the agent can find that person's internal ID (open_id), then look up their profile details such as department, email, contact info, personal status or signature. It can also search for bots or AI agents visible to the user, so a later step like sending a message or scheduling a meeting can target the right person or bot.

Great for

  • Employees on Lark/Feishu who want an agent to find a colleague's ID before messaging or scheduling a meeting
  • Developers building workflows on top of the lark-cli tool who need to resolve names to open_ids
  • Teams that want to search for internal bots or AI assistants by keyword

Skip it if

  • Listing departments, browsing an org chart or fetching all employees in a department; the skill says these need the native OpenAPI instead
  • Users who do not have Lark/Feishu or the lark-cli tool installed and authenticated, since the skill cannot work without them
  • Sensitive lookups of people outside your organisation: cross-tenant users often return empty fields, and profile data is still personal information to handle carefully

Try asking

  • “Find the open_id for Zhang San who I chatted with recently, then send him a message saying hi”
  • “Look up the department and email of the person with open_id ou_xxx”
  • “Search Lark for bots matching 'meeting assistant' and show me the candidates”
  • “Check the personal status and signature of these three colleagues before I schedule a call”
Step-by-step guide: how to use Lark Contact LookupInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 4 original files, the MIT licence and an attribution note.

    lark-contact.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip lark-contact.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip lark-contact.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Ask the agent to list multiple matches and pick the right person yourself before any action that sends messages or invites people, since the skill says not to choose the first result automatically.
  • Use the --has-chatted option when searching by name to narrow results to people you have talked to.
  • If a name is ambiguous or sounds like a bot (for example, containing 'assistant' or 'agent'), tell the agent so it searches bots as well as people.

What's inside

  • references/lark-contact-get-user.md
  • references/lark-contact-search-bot.md
  • references/lark-contact-search-user.md
  • SKILL.md

Redistributed unmodified from larksuite/cli under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.