feishu-notify

Send Feishu/Lark notifications for AutoResearch workflow events and checkpoints.

2|1|Updated Apr 19, 2026
One-click install
npx skills add https://github.com/raja21068/AutoResearch --skill feishu-notify-raja21068
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: feishu-notify
Source: https://github.com/raja21068/AutoResearch/tree/main/skills/aris/feishu-notify
Command: npx skills add https://github.com/raja21068/AutoResearch --skill feishu-notify-raja21068

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

AutoResearch users need reliable, non-blocking delivery of experiment, review, and checkpoint status updates without manually copying messages into Feishu/Lark.

Core Features & Use Cases

  • Push-only webhook notifications for quick, fire-and-forget updates when experiments complete or reviews score.
  • Interactive bidirectional notifications that request user approval/rejection during checkpoint phases via a bridge service.
  • Zero-impact behavior that disables itself silently when the required local configuration file is missing.

Quick Start

Send a Feishu/Lark notification with the message text you want by invoking the skill with an argument that contains the notification body.

Frequently Asked Questions about feishu-notify

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I send Feishu notifications for automated workflow events?

To send Feishu notifications, invoke the skill with the notification body as an argument. It uses a local JSON config at ~/.claude/feishu.json to push webhook updates for workflow events like experiment completion or review score updates.

Can I use interactive approve/reject checkpoints with Feishu or Lark?

Yes, interactive bidirectional notifications can request user approval or rejection during checkpoint phases via a bridge service. This supports polling to capture interactive decisions directly within your Feishu or Lark chat.

How do I configure a webhook to push status updates to Lark?

You need to create a local JSON configuration file at ~/.claude/feishu.json specifying your webhook details. Once configured, the skill automatically pushes fire-and-forget status updates when pipeline events occur.

What happens if my Feishu notification configuration is missing or the network fails?

If the local configuration file is missing or network access is unavailable, the skill applies a zero-impact fail-open behavior. It silently disables itself without blocking your underlying AutoResearch workflow.

Do I need a specific framework to trigger Lark messages from experiment pipelines?

The skill is designed for AutoResearch workflows and applies to experiment status reporting and pipeline completion summaries. It operates independently without requiring additional framework dependencies to trigger Lark messages.