Omnilink Agent

OrganizationPopular

omnimind-ai

omnilink-agent

Use the built-in OmniLink collaboration primitives to inspect trusted devices, compose cross-device event workflows, send messages to another Xiaowan, and continue after reconnect.

Overview

Publisher	omnimind-ai
Repository	`OmniBot`
Skill name	`omnilink-agent`
Stars	2K
Forks	142
Bundled files	1
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by omnimind-ai on GitHub. Read the source before you install it.

Installation

Install the Omnilink Agent AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/omnimind-ai/OmniBot/tree/main/plugins/omnilink-agent/runtime-skill/omnilink-agent

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/omnimind-ai/OmniBot.git /tmp/OmniBot
mkdir -p .claude/skills
cp -r /tmp/OmniBot/plugins/omnilink-agent/runtime-skill/omnilink-agent .claude/skills/omnilink-agent

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Omnilink Agent in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Omnilink Agent on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Omnilink Agent is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

OmniLink 跨设备协作工具箱

这是小万的内置跨设备能力。它让两个设备上的小万通过 OmniLink 互相查询状态、接收事件和发信号。你要根据用户意图组合通用工具，不要为每个场景假造新的工具名，也不要要求用户复制 token、端口、MCP JSON 或 shell 命令。

这里的“生成工具”是由你在当前对话中生成一组有顺序的工具调用，而不是修改插件、编写 shell 或创造一个绕过授权的新 API。把自然语言意图拆成：发现设备 → 选择真实的 device_id → 读取或订阅事件 → 必要时给另一台小万发消息。一个意图可以组合多次调用；工具返回的状态、事件和 cursor 是下一步调用的输入。

例如，用户说“如果另一台手机有通知，就告诉那台设备上的小万我已经知道了”时，先用 omnilink_devices 找到目标，再用 omnilink_events(mode=subscribe) 订阅 NOTIFICATION_UPSERTED / NOTIFICATION_REMOVED。收到事件后，如果用户确实要求回信，再用 omnilink_control(action=send_message, input=...) 发送；不要把这个流程固化成一个名为“通知确认”的专用工具。对于只要求一次查询的意图，完成一次读取即可，不要擅自建立长期订阅。

对话触发

“列出协作设备” → omnilink_devices
“查另一台手机的电量/是否在线/是否充电/网络状态” → omnilink_devices，从目标设备的 reachable 和 readiness.device 自己组合答案
“现在读取另一台手机的通知” → omnilink_events，传入 device_id、event_types=[NOTIFICATION_UPSERTED, NOTIFICATION_REMOVED] 和 mode=read，需要短等候时使用 wait_ms
“开始持续接收另一台手机的通知” → omnilink_events，传入同一组 event_types 和 mode=subscribe
“停止接收另一台手机的通知” → omnilink_events，传入目标 device_id 和 mode=stop
“给另一台设备上的小万发信号/消息：……” → omnilink_control，传入 action=send_message 和结构化 input
“读取另一台设备的小万消息事件” → omnilink_events，传入 event_types=[AGENT_MESSAGE_RECEIVED] 和 mode=read

操作约束

先调用 omnilink_devices，再使用返回的稳定 device_id；不要猜设备 ID。
状态回答必须以 omnilink_devices 返回的 reachable 和 readiness.device 为准；不要根据设备名、上次结果或猜测回答电量。
batteryPercent 可能为空；为空时明确说“暂时没有电量读数”，不要补估计值。reachable=false 时明确说设备当前不可达。
通知事件只回流应用标识和安全摘要。通知标题、正文和敏感内容不会通过 Agent 工具传输；不要要求绕过这个限制。
发送消息时把用户原意放进 omnilink_control 的 input.message，不要把 token、私有路径或其他敏感数据放进消息。
只在确实需要时指定 input.conversationId、input.recipientAgentId、input.messageId；省略时由插件使用小万 Agent 的安全默认值并生成幂等 ID。
omnilink_events 的 event_types 只能使用 Agent-safe 类型；不要猜测未注册事件类型。
返回的 cursor 是不透明值，只能原样带回下一次读取；订阅由插件负责持久化游标和断线恢复。
omnilink_control(action=send_message) 返回 queued 只代表已进入 OmniLink 队列，不代表对方小万已经读到；只有看到入站事件或明确 receipt 才能说“已收到”。
如果返回本地授权或连接失败，明确告诉用户需要在 OmniLink 中批准/恢复，不要假装消息或通知已经送达。

开启通知监听后，后续通知由插件自动回流当前聊天；收到后说明“协作设备收到通知”及安全摘要，不显示通知正文、认证凭据或稳定设备 ID。入站 Agent 消息也会自动回流当前聊天。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

PACKAGED_RUNTIME_SKILL1 KB

Frequently asked questions

What does the Omnilink Agent AI skill do?

Use the built-in OmniLink collaboration primitives to inspect trusted devices, compose cross-device event workflows, send messages to another Xiaowan, and continue after reconnect.

Why use Omnilink Agent on TypingMind?

Because you install it once and use it with any model. Omnilink Agent is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Omnilink Agent in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/omnimind-ai/OmniBot/tree/main/plugins/omnilink-agent/runtime-skill/omnilink-agent. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Omnilink Agent?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Omnilink Agent?

As many as you like. As long as a model supports skills, you can use Omnilink Agent with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Omnilink Agent AI skill free?

It is published on GitHub by omnimind-ai. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

To Tickets

mattpocock

CommunityPopular

Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket…

Triage

Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.

Claude Handoff

Hand the current conversation off to a fresh background agent that picks up the work immediately.

Finishing A Development Branch

obra

CommunityPopular

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

OmniLink 跨设备协作工具箱

对话触发

操作约束

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now