Documents & Data · IN-DEPTH PROFILE

Lark Event Skill

Lark Event is a real-time subscription workflow that streams Feishu EventKeys as NDJSON for bots and agent subprocesses.

View listed source ↗Installation guide ↓
Best for

Developers building Feishu bots and event handlers

What you get

Discover event contracts + Consume bounded streams

Main limitation

It is a long-running subprocess contract, not a one-shot REST wrapper, and each process accepts only one EventKey.

First risk

Dropped events or leaked subscriptions. Hidden jq errors can skip events, while force-killing some consumers can leave server subscriptions behind. Preserve diagnostics and shut down gracefully.

EVIDENCE FRESHNESS

Three checks, kept separate

A recent source check is not a runtime test or security audit.

Upstream sourceChecked 2026-09-23

Pinned revision · a079fd7a

Open pinned commit ↗
SkillSignal profileSource-grounded

Updated 2026-08-20

Runtime & securityNot independently verified

Source review does not certify behavior or safety.

IN PLAIN ENGLISH

What it does—and when it fits

Lark Event is a real-time subscription workflow that streams Feishu EventKeys as NDJSON for bots and agent subprocesses. It provides event discovery, schemas, jq projection, bounded runs, readiness markers, structured errors, and coordinated local bus behavior across IM, Approval, Task, VC, Minutes, and Whiteboard domains.

This is aimed at Developers building Feishu bots and event handlers. Compare the examples below with your task, then review the limitations, permissions, and risks before installing.

What you get
  • Discover event contractsList legal EventKeys and inspect each output schema before filtering payloads.
  • Consume bounded streamsCapture a fixed number of events or run for a defined timeout for inspection and automation.
  • Power real-time agentsRun one isolated subprocess per EventKey with readiness and exit signals an orchestrator can parse.
What makes it different
  • This profile is manually organized around the current upstream SKILL.md workflow.
  • The capability boundary remains explicitly tied to open.feishu.cn.
  • Core uses, limitations, and risks are separated for pre-install review.
Community signalskills.sh All-time: #27 · 728.1K installs

No verified review text is in the current dataset. Use the linked source for the latest discussion.

Read the source note ↗

INSTALL BY AGENT

Choose your Agent

Paths come from official Agent docs or the universal installer behind skills.sh. Compatibility still follows this Skill's record.

Native

This Skill's current record explicitly names this Agent. Still inspect scripts, permissions, and external dependencies first.

Project install (recommended)
npx skills add larksuite/cli --skill lark-event --agent claude-code
Personal install
npx skills add larksuite/cli --skill lark-event --agent claude-code -g

Project install stays with this repository for team sharing. Personal install adds -g and works across repositories.

This command adds the Skill instructions only. Install lark-cli and sign in to Feishu separately before use. Official Lark CLI setup ↗

View install paths
Project path.claude/skills/lark-event/
Personal path~/.claude/skills/lark-event/
Official agent docs

Claude Code discovers custom Skill folders automatically at project or personal scope.

View path evidence ↗

TYPICAL WORKFLOW

A practical workflow

01

Discover event contracts

List legal EventKeys and inspect each output schema before filtering payloads.

02

Consume bounded streams

Capture a fixed number of events or run for a defined timeout for inspection and automation.

03

Power real-time agents

Run one isolated subprocess per EventKey with readiness and exit signals an orchestrator can parse.

THE TRADEOFFS

Advantages and tradeoffs

Notable strengths

  1. This profile is manually organized around the current upstream SKILL.md workflow.
  2. The capability boundary remains explicitly tied to open.feishu.cn.
  3. Core uses, limitations, and risks are separated for pre-install review.

Limitations

  1. It is a long-running subprocess contract, not a one-shot REST wrapper, and each process accepts only one EventKey.
  2. Payload shapes vary by event and can be pre-decoded; jq filters must follow the current schema descriptions.

COMPARE THE TRADEOFF

Consider these close alternatives

These are deterministic nearby candidates, not paid placements or a universal ranking. Open the full profile before choosing.

01

Same job family · native to Codex + Claude Code

create-llms

Create an llms.txt index from repository documentation.
Tradeoff to check
Detailed package files are not fully catalogued.
First risk
Review before install · Medium
Source state
Pinned · 1f564408
Open create-llms profile ↗
02

Same job family · native to Codex + Claude Code

csharp-docs

Write useful XML documentation for C# APIs.
Tradeoff to check
Detailed package files are not fully catalogued.
First risk
Review before install · Medium
Source state
Pinned · 1f564408
Open csharp-docs profile ↗
03

Same job family · native to Codex + Claude Code

java-docs

Write consistent Javadoc for Java types and APIs.
Tradeoff to check
Detailed package files are not fully catalogued.
First risk
Review before install · Medium
Source state
Pinned · 1f564408
Open java-docs profile ↗
Compare more in the directory →

BEST FIT

Who it is for

→

Developers building Feishu bots and event handlers

→

Agent orchestrators consuming live business events

BEFORE YOU USE IT

Risks to review before use

High

Dropped events or leaked subscriptions

Hidden jq errors can skip events, while force-killing some consumers can leave server subscriptions behind. Preserve diagnostics and shut down gracefully.

High

External data and identity boundary

Requests access Feishu tenant resources. Use the correct identity, least-privilege scopes, and keep sensitive content out of logs.

SECURITY

What the permission profile means

  • Declared access remains governed by the current upstream SKILL.md and runtime requests.
  • Treat Feishu documents, messages, people, and business records as permission-controlled data.
  • SkillSignal has not independently executed or security-audited this package; external skills.sh labels are not SkillSignal certification.

Not a security certification. External ratings are attributed references. SkillSignal has not independently executed or security-reviewed this Skill.

COMMON QUESTIONS

Lark Event Skill FAQ

What is the Lark Event Skill?

Lark Event is a real-time subscription workflow that streams Feishu EventKeys as NDJSON for bots and agent subprocesses. It provides event discovery, schemas, jq projection, bounded runs, readiness markers, structured errors, and coordinated local bus behavior across IM, Approval, Task, VC, Minutes, and Whiteboard domains.

How do I install the Lark Event Skill?

Open and review the listed source, choose the project or personal path for your Agent, then verify the first run in a controlled project. Open the listed source and read the current SKILL.md plus only the references required for this task.

Is the Lark Event Skill safe to use?

SkillSignal checked the source on 2026-09-23, but that is not a runtime test or security certification. Review the “Dropped events or leaked subscriptions” risk first and begin with the least access required.

INSIDE THE PACKAGE

Indexed files

SKILL.mdUpstream Skill instructionsSource-linked

TAGS

feishueventsstreaming

Manually expanded from the current upstream SKILL.md and linked source at open.feishu.cn, checked 2026-08-19. This is an original summary, not an execution result or security certification.