SuperAPI AI Directory
Partner中文AI newsFavorites
Skillsconfigure

configure

Office & productivity

View repository

Updated 10-26 16:22

About this skill

/feishu:configure — Feishu Channel Setup

Writes the app credentials to ~/.claude/channels/feishu/.env and orients the user on access policy. The server reads both files at boot.

Arguments passed: $ARGUMENTS

Dispatch on arguments

No args — status and guidance

Read both state files and give the user a complete picture:

  1. Credentials — check ~/.claude/channels/feishu/.env for FEISHU_APP_ID and FEISHU_APP_SECRET. Show set/not-set; if set, show first 6 chars of APP_ID and mask the rest.

  1. Access — read ~/.claude/channels/feishu/access.json (missing file = defaults: dmPolicy: "pairing", empty allowlist). Show:

    • DM policy and what it means in one line
    • Allowed senders: count, and list open_ids
    • Pending pairings: count, with codes and sender open_ids if any
    • Group chats opted in: count

  2. What next — end with a concrete next step based on state:

    • No credentials → "Run /feishu:configure <app_id> <app_secret> with your app credentials from the Feishu Open Platform console (Open Platform → App → Credentials & Basic Info)."
    • Credentials set, policy is pairing, nobody allowed → "In Feishu, send a direct message to your bot. It will reply with a pairing code; use /feishu:access pair <code> to approve it."
    • Credentials set, someone allowed → "Ready. Just message your bot to start chatting with Claude."

Push toward lockdown — always. The goal for every setup is allowlist with a defined list. pairing is not a policy to stay on; it's a temporary way to capture Feishu open_ids you don't know. Once the IDs are in, pairing has done its job and should be turned off.

Drive the conversation this way:

  1. Read the allowlist. Tell the user who's in it.
  2. Ask: "Are these all the people who need to reach you through this bot?"
  3. If yes and policy is still pairing → "OK, let's lock down access so no one else can trigger pairing codes:" and offer to run /feishu:access policy allowlist. Do this proactively — don't wait to be asked.
  4. If no, people are missing → "Have them send a direct message to the bot; you use /feishu:access pair <code> to approve each person. Once everyone has joined, run this command and we'll lock it down." Or, if they can get open_ids directly: "Add directly with /feishu:access allow <open_id> ."
  5. If the allowlist is empty and they haven't paired themselves yet → "First send a direct message to your bot to capture your own ID. Then we'll add the others and lock it down."
  6. If policy is already allowlist → confirm this is the locked state. If they need to add someone, use /feishu:access allow <open_id>.

<app_id> <app_secret> — save credentials

  1. Treat $ARGUMENTS as space-separated: first token is APP_ID, second is APP_SECRET. Feishu App IDs typically start with cli_ and are shorter; App Secrets are longer hex/base64 strings.
  2. mkdir -p ~/.claude/channels/feishu
  3. Read existing .env if present; update/add the FEISHU_APP_ID= and FEISHU_APP_SECRET= lines, preserve other keys (like FEISHU_DOMAIN). Write back, no quotes around values.
  4. chmod 600 ~/.claude/channels/feishu/.env — credentials are sensitive.
  5. Confirm, then show the no-args status so the user sees where they stand.

domain <url> — set API domain

For Lark (international) users, set FEISHU_DOMAIN=https://open.larksuite.com in .env. Default is https://open.feishu.cn.

clear — remove credentials

Delete the FEISHU_APP_ID= and FEISHU_APP_SECRET= lines (or the file if those are the only lines).

Implementation notes

  • The channels dir might not exist if the server hasn't run yet. Missing file = not configured, not an error.
  • The server reads .env once at boot. Credential changes need a session restart or /reload-plugins. Say so after saving.
  • access.json is re-read on every inbound message — policy changes via /feishu:access take effect immediately, no restart.

Feishu Open Platform Setup Guide

When the user asks how to create a Feishu bot, provide these steps:

  1. Go to Feishu Open Platform to create an app
  2. On the "Credentials & Basic Info" page, get the App ID and App Secret
  3. In "Add App Capabilities", enable the "Bot" capability
  4. In "Events & Callbacks":
    • Select "Receive events via long connection" (WebSocket)
    • Add event im.message.receive_v1 (receive messages)
  5. In "Permission Management", add the following permissions:
    • im:message — Get and send direct messages and group messages
    • im:message:send_as_bot — Send messages as the app
    • im:resource — Get and upload images or file resources
    • im:chat — Get group information
    • im:message.reactions:write — Add emoji reactions to messages
  6. Publish the app version and wait for review approval
  7. In Claude Code, run /feishu:configure <app_id> <app_secret>