Skills Guide

Feishu/Lark Bridge Manager

VerifiedCaution

Manage the Feishu/Lark bridge daemon for Claude Code and Codex. Includes setup, start/stop, logs, and health checks.

Download and use
Sby Skills Guide Bot
DevOpsIntermediate
7/22/2026
Claude CodeCodex
#feishu#lark#bridge-daemon#claude-code#codex

Recommended for

Backend developerClaude CodeDevOps engineerCodexGit automation

Automated summary

Manages the Feishu/Lark bridge daemon that connects Claude Code and Codex to Feishu instant messaging.

Strengths

  • Covers the full daemon lifecycle: onboard, start, stop, status, logs, doctor and upgrade
  • Detailed setup guidance listing required and optional config.env fields
  • Per-session runtime selection through /new:claude and /new:codex

Limitations

  • Feishu/Lark only; no other messaging platforms are supported
  • No multi-platform setup wizard: configuration is done manually in config.env
  • Requires Feishu app credentials and scopes configured in the Feishu console
When to use it

Use when a user wants to install, configure or operate the Feishu/Lark bridge between their coding agent and their chat workspace.

When not to use it

Avoid when the user needs Slack, Discord or any other messaging platform integration not covered here.

Security analysis

Caution
Quality score78/100

This is a legitimate daemon-management skill, but it uses bash, installs a global npm beta package, executes bundled shell scripts, and handles Feishu app secrets. These are powerful operations for a valid purpose, so it warrants caution rather than being considered risk-free.

Findings
  • •Installs and executes a third-party npm package (`agents-to-im@beta`) globally; beta channel may change without review.
  • •Runs shell scripts (`daemon.sh`, `doctor.sh`) from a skill directory resolved via glob, so the execution path should be verified.
  • •Handles Feishu app secrets (`CTI_FEISHU_APP_SECRET`) stored in `~/.agents-to-im/config.env`; file permissions and log redaction matter.
  • •The bridge daemon likely has network access to Feishu/Lark and local coding agents; allowed users and scopes should be constrained.
  • •No destructive, obfuscated, or secret-exfiltrating commands are present.
How this analysis is made

Examples

Install and onboard
Set up the Feishu bridge for my Claude Code agent and walk me through the required config.env fields.
Check bridge health
Run the agents-to-im doctor and tell me if the bridge is healthy, summarizing any problems.
Restart the daemon
Stop the agents-to-im daemon, start it again and show me its status.

name: agents-to-im description: | Manage the Feishu/Lark bridge daemon for Claude Code and Codex. Use for: CLI install guidance, setup guidance, start/stop/status/logs/doctor, checking bridge health, or explaining how to configure the Feishu bot. This skill is Feishu/Lark-only. argument-hint: "onboard | setup | start | stop | status | logs [N] | doctor | upgrade" allowed-tools:

  • Bash
  • Read
  • Write
  • Edit
  • Grep
  • Glob

Agents to IM Skill

You are managing the Feishu/Lark bridge daemon. User data is stored at ~/.agents-to-im/.

The skill directory is ~/.claude/skills/agents-to-im. If that path does not exist, find SKILL.md via glob and derive the root directory from it.

Commands

Map $ARGUMENTS to one of:

  • onboard
  • setup
  • start
  • stop
  • status
  • logs
  • doctor
  • upgrade

If no configuration exists at ~/.agents-to-im/config.env, show config.env.example and explain the required Feishu fields. Do not try to start the daemon without config.

CLI usage

Prefer the globally installed npm CLI:

  • install once: npm install -g agents-to-im@beta
  • agents-to-im onboard
  • agents-to-im start
  • agents-to-im restart
  • agents-to-im status
  • agents-to-im doctor
  • agents-to-im upgrade
  • agents-to-im logs 100

Use source checkout commands only for development/debugging.

Setup

This project no longer has a multi-platform setup wizard. Setup means:

  1. Show config.env.example.
  2. Explain the required fields:
    • CTI_FEISHU_APP_ID
    • CTI_FEISHU_APP_SECRET
    • CTI_DEFAULT_WORKDIR
  3. Explain optional fields:
    • CTI_FEISHU_DOMAIN
    • CTI_FEISHU_ALLOWED_USERS
    • external CODEX_HOME override if the user stores Codex config outside ~/.codex
  4. Point the user to references/setup-guides.md for the one-shot Feishu scopes import JSON.
  5. Remind the user to enable Feishu long connection events:
    • im.message.receive_v1
    • card.action.trigger
  6. Remind the user that private chat only accepts /new:claude and /new:codex, and real conversation happens in the auto-created group.

Runtime behavior

  • Runtime is selected per session.
  • /new:claude creates a Claude session.
  • /new:codex creates a Codex session.
  • /reset keeps the current group's runtime.

Execution

Use:

  • agents-to-im onboard
  • bash "SKILL_DIR/scripts/daemon.sh" start
  • bash "SKILL_DIR/scripts/daemon.sh" stop
  • bash "SKILL_DIR/scripts/daemon.sh" status
  • bash "SKILL_DIR/scripts/daemon.sh" logs 50
  • bash "SKILL_DIR/scripts/doctor.sh"

When showing logs or doctor output, summarize the important lines instead of dumping excessive raw output.

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/feishu-lark-bridge-manager-mrwaka8x/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/feishu-lark-bridge-manager-mrwaka8x' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/feishu-lark-bridge-manager-mrwaka8x/download' --output '.skill-downloads/feishu-lark-bridge-manager-mrwaka8x/SKILL.md.part' && mv '.skill-downloads/feishu-lark-bridge-manager-mrwaka8x/SKILL.md.part' '.skill-downloads/feishu-lark-bridge-manager-mrwaka8x/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

Original excerpt: Setup

This project no longer has a multi-platform setup wizard. Setup means:

  1. Show config.env.example.
  2. Explain the required fields:
    • CTI_FEISHU_APP_ID
    • CTI_FEISHU_APP_SECRET
    • CTI_DEFAULT_WORKDIR
  3. Explain optional fields:
    • CTI_FEISHU_DOMAIN
    • CTI_FEISHU_ALLOWED_USERS
    • external CODEX_HOME override if the user stores Codex config outside ~/.codex
  4. Point the user to references/setup-guides.md for the one-shot Feishu scopes import JSON.
  5. Remind the user to enable Feishu long connection events:
    • im.message.receive_v1
    • card.action.trigger
  6. Remind the user that private chat only accepts /new:claude and /new:codex, and real conversation happens in the auto-created group.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/feishu-lark-bridge-manager-mrwaka8x/SKILL.md' && test -s '.skill-downloads/feishu-lark-bridge-manager-mrwaka8x/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/agents-to-im' && cp -R '.skill-downloads/feishu-lark-bridge-manager-mrwaka8x' '.claude/skills/agents-to-im'

Codex
test -f '.skill-downloads/feishu-lark-bridge-manager-mrwaka8x/SKILL.md' && test -s '.skill-downloads/feishu-lark-bridge-manager-mrwaka8x/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/agents-to-im' && cp -R '.skill-downloads/feishu-lark-bridge-manager-mrwaka8x' '.agents/skills/agents-to-im'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/feishu-lark-bridge-manager-mrwaka8x'

openskills read 'feishu-lark-bridge-manager-mrwaka8x'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/feishu-lark-bridge-manager-mrwaka8x/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills

Configure a Chat Channel with SecretRefs

DevOps

Set up chat channels using non-interactive commands, with secrets only as SecretRefs. Covers gather, mutate, repair, and prove steps for reliable delivery.

Claude CodeCodexintermediateSafe 387,940
Skills Guide Bot

Investigate ClickHouse CI Failures

DevOps

Investigate a ClickHouse CI failure end-to-end from a PR or S3 report URL. Fetches failed tests, classifies flaky vs real regression, and checks for existing issues/fixes.

Claude CodeadvancedSafe 49,516
Skills Guide Bot

Ansible PR Review

DevOps

Reviews an Ansible PR following the project's standardized process, including changelog checks, test coverage validation, and feedback tracking.

Claude CodeintermediateSafe 70,491
Skills Guide Bot