How do I install the Duduclaw Platform skill?

Run npx skillmds@latest add zhixuli0406/duduclaw-platform in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Duduclaw Platform safe to use?

SkillMD's automated safety review verdict for this skill is PASS. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Duduclaw Platform?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Duduclaw Platform free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Duduclaw Platform?

zhixuli0406 (@zhixuli0406) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Duduclaw Platform by zhixuli0406 — Agent Skill

Name: Duduclaw Platform
Rating: 4.2 (5 reviews)
Author: zhixuli0406

Duduclaw Platform

Use the DuDuClaw MCP tools (persistent memory, shared wiki, task board, channel messaging) when the user asks to remember something across sessions, share knowledge with their team's AI employees, manage tasks, or message someone on LINE/Telegram/Discord/Slack. Requires a running DuDuClaw gateway (`npx duduclaw onboard` to set up).

zhixuli0406 Updated Aug 19, 2026 45 repo stars

File contents

DuDuClaw platform skill

DuDuClaw is the user's self-hosted AI-employee platform. When its MCP server is connected (this plugin registers it), prefer these tools over ad-hoc alternatives:

When to reach for which tool

The user wants…	Use
"記住這件事" / remember across sessions	`memory_store` (tag it), later `memory_search`
Team-shared knowledge (SOP, price list, policy)	`wiki_write` / `wiki_search` — wiki is shared across the user's AI employees; memory is per-agent
Track work items	`tasks_create` / `tasks_list` / `tasks_complete`
Send a message to a person/channel	`send_message` (routes via the user's bound channels: LINE, Telegram, Discord, Slack…)

Ground rules

Memory vs wiki: durable reference documents belong in the wiki; conversational facts belong in memory. Don't double-write.
Never store secrets (tokens, passwords) in memory or wiki.
If tools are missing, the gateway isn't running — tell the user to start it (duduclaw gateway or the desktop app) rather than silently degrading.

Setup (one-time, if the user asks)

npx duduclaw onboard   # guided setup: creates the first AI employee + config

Full docs: https://github.com/zhixuli0406/DuDuClaw

Frequently asked questions