← Back to Skills Marketplace
OpenClaw Feishu Multi-Agent
by
CCharlesMeng
· GitHub ↗
· v1.0.1
· MIT-0
276
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install openclaw-feishu-multi-agent
Description
Build and troubleshoot OpenClaw multi-agent workflows on Feishu. This skill teaches coordinator and specialist agents to combine visible `<at>` mentions with...
Usage Guidance
This bundle is coherent for the stated purpose, but take these safety steps before running any write/fix operations: 1) Inspect roles.json and remove or avoid storing real appSecret/appId values in files you don't control; prefer setting secrets directly in the target OpenClaw config or a secure secret store. 2) Run the tools in dry-run mode first (no --write / no --fix) and review the planned changes printed by the scripts. 3) Back up your ~/.openclaw directory (or use the provided --backup flags) before applying changes. 4) Review the generated artifacts (openclaw.generated.json, PROTOCOL.generated.md, identities) and confirm they match expectations. 5) If you have low trust in the source, run the scripts in an isolated environment (Docker VM) and manually inspect diffs before committing to production. If you want extra assurance, you can audit the included Python files yourself — they operate on local files and contain no network calls or obfuscated code.
Capability Analysis
Type: OpenClaw Skill
Name: openclaw-feishu-multi-agent
Version: 1.0.1
The bundle provides a comprehensive set of Python utility scripts and Markdown instructions designed to facilitate and troubleshoot multi-agent collaboration for OpenClaw on the Feishu (Lark) platform. The scripts, such as `apply_feishu_multi_agent.py` and `repair_feishu_group_sessions.py`, manage local configuration files (e.g., `openclaw.json`, `PROTOCOL.md`) and session metadata within the `~/.openclaw` directory. The instructions in `SKILL.md` guide the AI agent to use these tools for scaffolding, auditing, and repairing setups. The functionality is strictly local, lacks networking capabilities, includes safety features like dry-run modes and file backups, and is entirely consistent with the stated purpose of the skill.
Capability Assessment
Purpose & Capability
The name/description (Feishu multi-agent orchestration) matches the included artifacts: docs, templates, and Python utilities to render, audit, apply, and repair OpenClaw configs under ~/.openclaw. The files and paths the skill reads/writes (openclaw.json, PROTOCOL.md, agent IDENTITY.md, agents' sessions files) are exactly what a deployment/troubleshooting tool would need.
Instruction Scope
SKILL.md explicitly instructs reading and optionally writing files under ~/.openclaw and running the provided scripts. The instructions do not direct data to external endpoints or ask the agent to read unrelated system paths. They clearly default to dry-run and require explicit --write or --fix flags to modify the user's state, which limits accidental changes.
Install Mechanism
No install spec or remote downloads are present. This is an instruction-and-script bundle only; all code is included in the package and will run locally with the system Python. There are no URLs, extract steps, or third-party package installs that would write or execute remote code.
Credentials
The skill does not request environment variables or external credentials at install time, but the roles JSON and templates include appId/appSecret fields. The scripts will copy non-placeholder appId/appSecret values from the roles file into openclaw.json if provided. This is reasonable for configuring Feishu accounts, but users should be aware they are placing secrets into local config files (and possibly backups).
Persistence & Privilege
The skill does not set always: true and does not modify other skills' config. It can modify ~/.openclaw files and agent session JSON files, but only when the user runs scripts with explicit flags (--write, --fix, --apply-identities). This behavior is consistent with a configuration/repair tool.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install openclaw-feishu-multi-agent - After installation, invoke the skill by name or use
/openclaw-feishu-multi-agent - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Improve public-facing English description, tagline, and discovery tags.
v1.0.0
Initial public release with docs, templates, render/audit/repair/apply scripts, and unified manager entrypoint.
Metadata
Frequently Asked Questions
What is OpenClaw Feishu Multi-Agent?
Build and troubleshoot OpenClaw multi-agent workflows on Feishu. This skill teaches coordinator and specialist agents to combine visible `<at>` mentions with... It is an AI Agent Skill for Claude Code / OpenClaw, with 276 downloads so far.
How do I install OpenClaw Feishu Multi-Agent?
Run "/install openclaw-feishu-multi-agent" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is OpenClaw Feishu Multi-Agent free?
Yes, OpenClaw Feishu Multi-Agent is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does OpenClaw Feishu Multi-Agent support?
OpenClaw Feishu Multi-Agent is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created OpenClaw Feishu Multi-Agent?
It is built and maintained by CCharlesMeng (@ccharlesmeng); the current version is v1.0.1.
More Skills