world2agent-protocol
```markdown
What this skill does
```markdown
---
name: world2agent-protocol
description: Skill for using World2Agent (W2A) — the open protocol that standardizes how AI agents perceive the real world via structured sensor signals.
triggers:
- add a sensor to my agent
- set up world2agent
- how do I use W2A sensors
- make my agent perceive real-world data
- install a world2agent sensor
- build a custom W2A sensor
- configure world2agent in my project
- stream real-time signals to my AI agent
---
# World2Agent (W2A) Protocol
> Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection.
World2Agent (W2A) is an open protocol that standardizes how AI agents perceive the real world. Sensors watch data sources and emit structured signals following the W2A schema. Your agent receives those signals and decides what to do. The architecture is always: **World → Sensor → Agent**.
---
## Installation
### Option 1: Claude Code Plugin (Fastest)
In an active Claude Code session:
```
/plugin marketplace add machinepulse-ai/world2agent-plugins
/plugin install world2agent@world2agent-plugins
/reload-plugins
```
Add sensors:
```
/world2agent:sensor-add @world2agent/sensor-hackernews
/world2agent:sensor-add @quill-io/sensor-frontier-ai-news
```
Restart Claude Code with the plugin channel loaded:
```bash
claude --dangerously-load-development-channels plugin:world2agent@world2agent-plugins
```
### Option 2: SDK / Code Integration
Install the core SDK and a sensor:
```bash
npm install @world2agent/sdk
npm install @world2agent/sensor-hackernews
```
---
## Core Concepts
| Term | Description |
|------|-------------|
| **Sensor** | An npm package that watches a data source and emits W2A signals |
| **Signal** | A structured JSON object emitted by a sensor (follows W2A schema) |
| **SensorHub** | Catalog of all official and community sensors at [world2agent.ai/hub](https://world2agent.ai/hub) |
| **Channel** | A named stream that groups signals from one or more sensors |
---
## Signal Format
Every W2A signal shares a common schema:
```typescript
interface W2ASignal {
id: string; // Unique signal ID (UUID)
sensorId: string; // e.g. "@world2agent/sensor-hackernews"
sensorVersion: string; // semver
timestamp: string; // ISO 8601
type: string; // e.g. "story.new", "price.alert", "news.post"
priority: "low" | "medium" | "high" | "critical";
payload: Record<string, unknown>; // Sensor-specific structured data
meta?: {
source?: string; // URL or origin
tags?: string[];
confidence?: number; // 0–1
};
}
```
Example signal from the Hacker News sensor:
```json
{
"id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
"sensorId": "@world2agent/sensor-hackernews",
"sensorVersion": "1.2.0",
"timestamp": "2026-04-29T10:00:00Z",
"type": "story.new",
"priority": "medium",
"payload": {
"storyId": 39812345,
"title": "Show HN: My open-source project",
"url": "https://example.com",
"score": 142,
"author": "someone",
"commentCount": 38
},
"meta": {
"source": "https://news.ycombinator.com/item?id=39812345",
"tags": ["show-hn", "open-source"]
}
}
```
---
## SDK Usage
### Subscribing to Sensor Signals
```typescript
import { W2AClient } from "@world2agent/sdk";
import { HackerNewsSensor } from "@world2agent/sensor-hackernews";
const client = new W2AClient();
// Register sensors
client.use(new HackerNewsSensor({
filter: {
minScore: 100,
types: ["story.new", "story.trending"],
},
}));
// Listen for signals
client.on("signal", (signal) => {
console.log(`[${signal.priority}] ${signal.type}:`, signal.payload);
});
// Start receiving signals
await client.start();
```
### Handling Specific Signal Types
```typescript
import { W2AClient, W2ASignal } from "@world2agent/sdk";
const client = new W2AClient();
client.on("signal", (signal: W2ASignal) => {
switch (signal.type) {
case "story.new":
handleNewStory(signal.payload);
break;
case "price.alert":
handlePriceAlert(signal.payload);
break;
default:
console.log("Unhandled signal type:", signal.type);
}
});
function handleNewStory(payload: Record<string, unknown>) {
const { title, score, url } = payload as {
title: string;
score: number;
url: string;
};
console.log(`New story (score: ${score}): ${title} — ${url}`);
}
```
### Multiple Sensors
```typescript
import { W2AClient } from "@world2agent/sdk";
import { HackerNewsSensor } from "@world2agent/sensor-hackernews";
import { FrontierAINewsSensor } from "@quill-io/sensor-frontier-ai-news";
const client = new W2AClient({
channelName: "my-agent-feed",
});
client.use(new HackerNewsSensor({ minScore: 50 }));
client.use(new FrontierAINewsSensor({ labs: ["openai", "anthropic", "google"] }));
client.on("signal", (signal) => {
// Signals from all sensors arrive here with sensorId to distinguish source
console.log(`From ${signal.sensorId}:`, signal.type, signal.payload);
});
await client.start();
```
---
## Building a Custom Sensor
Install the build skill:
```bash
npx skills add https://github.com/machinepulse-ai/world2agent/skills/build-w2a-sensor
```
Or build manually in ~50 lines:
```typescript
// src/index.ts
import { BaseSensor, W2ASignal, SensorConfig } from "@world2agent/sdk";
interface MyWeatherSensorConfig extends SensorConfig {
city: string;
apiKey?: string; // use process.env.WEATHER_API_KEY
pollIntervalMs?: number;
}
export class WeatherSensor extends BaseSensor {
private city: string;
private apiKey: string;
private pollInterval: number;
constructor(config: MyWeatherSensorConfig) {
super({
id: "@myorg/sensor-weather",
version: "1.0.0",
});
this.city = config.city;
this.apiKey = config.apiKey ?? process.env.WEATHER_API_KEY ?? "";
this.pollInterval = config.pollIntervalMs ?? 60_000;
}
async start(): Promise<void> {
await this.poll(); // immediate first fetch
setInterval(() => this.poll(), this.pollInterval);
}
private async poll(): Promise<void> {
const res = await fetch(
`https://api.weatherapi.com/v1/current.json?key=${this.apiKey}&q=${this.city}`
);
const data = await res.json();
const signal: Omit<W2ASignal, "id" | "timestamp"> = {
sensorId: this.meta.id,
sensorVersion: this.meta.version,
type: "weather.update",
priority: data.current.temp_c > 35 ? "high" : "low",
payload: {
city: this.city,
tempC: data.current.temp_c,
condition: data.current.condition.text,
humidity: data.current.humidity,
windKph: data.current.wind_kph,
},
meta: {
source: `https://www.weatherapi.com`,
tags: ["weather", this.city.toLowerCase()],
},
};
this.emit(signal); // BaseSensor handles id + timestamp
}
}
```
### package.json for your sensor
```json
{
"name": "@myorg/sensor-weather",
"version": "1.0.0",
"description": "W2A sensor for real-time weather data",
"main": "dist/index.js",
"keywords": ["w2a-sensor", "world2agent", "weather"],
"peerDependencies": {
"@world2agent/sdk": "^1.0.0"
}
}
```
Publish it:
```bash
npm publish --access public
```
---
## Configuration Reference
### W2AClient Options
```typescript
const client = new W2AClient({
channelName?: string; // Default: "default"
logLevel?: "silent" | "info" | "debug"; // Default: "info"
signalBufferSize?: number; // How many signals to buffer. Default: 100
onError?: (err: Error) => void;
});
```
### Environment Variables
| Variable | Description |
|----------|-------------|
| `W2A_LOG_LEVEL` | Override log level (`silent`, `info`, `debug`) |
| `W2A_CHANNEL` | Default channel name |
| `WEATHER_API_KEY` | Example: API key for a weather sensor (sensor-specific) |
---
## Common Patterns
### Pattern: Agent reacts to high-priority signals only
```typescript
client.on("signal",Related in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.