菜单
Track which marketing campaign or web page generated an inbound call using the Voicenter Lead Tracker JS SDK
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Designs the structural skeleton of a Voicenter Bot via interview. Use this skill when the user wants to create, design, scope, or modify a Voicenter voice/chat bot — phrases like "design a bot", "create an agent spec", "build a Voicenter bot", "patch this bot", "add an intent", "change the bot's persona", "modify the flow graph", or any reference to the Agent Spec Designer / Skill 1 in the Voicenter bot generation pipeline. Produces an Agent Spec markdown file (sections 1-4, 4.5, section 5 stubs, section 6 initial, section 7 init). Two named entry modes — greenfield (no spec attached) and patch (spec attached). Does NOT author per-intent language content (validationPrompt, post-execution intentInstructions) — that's Skill 2 (Intent Detail Author). Does NOT emit wire-format JSON — that's Skill 3 (JSON Assembler).
Assembles a fully-detailed Voicenter Agent Spec into Bot JSON wire format — the final mechanical step in the three-skill pipeline. Use this skill when an Agent Spec exists with all section 5 entries marked `[detailed]` and the user wants the deployable JSON. Trigger phrases include "run Skill 3", "assemble the JSON", "emit the bot JSON", "publish the bot", "build the wire-format", "Skill 3 (JSON Assembler)", or any direct continuation from Skill 2's completion handoff. Produces a single `bot-<name>-<date>.json` file plus a banner identifying every fail-loud sentinel and any drift between spec section 6 and what Skill 3 regenerated. Refuses to assemble if any intent is still `[structural]` or `[detailed-revisit]`, or if the spec deviates from the strict template (Doc 2 §3.7). Runs the §15.4 cross-reference pass — 23 checks (8 §15.4 + 3 Compass + 3 botIntents-role + 1 duplicate-global-intent + 8 field-placement doctrine), checks 1–7, 11–13, 15, and 16–21 blocking. Does NOT author any text content (Skills 1 and
Authors the per-intent language content of a Voicenter Agent Spec — slot descriptions, validationPrompt, post-execution intentInstructions, and RT-specific Configuration text. Use this skill when an Agent Spec exists with section 5 entries marked `[structural]` or `[detailed-revisit]`, and the user wants to fill them in. Trigger phrases include "run Skill 2", "detail the intents", "fill in the per-intent fields", "Skill 2 (Intent Detail Author)", or any direct continuation from Skill 1's handoff hint. Walks intents in user-confirmed batches with a checkpoint after each batch. Reactivable — invoke as many times as needed; spec state is the resume point. Does NOT modify the structural skeleton (sections 1, 2, 3, 4, 4.5.1/.2/.4) — that's Skill 1 (Agent Spec Designer). Does NOT emit wire-format JSON — that's Skill 3 (JSON Assembler).
Pull call detail records (CDR) from Voicenter using the Call Log API
Receive and handle CDR push notifications from Voicenter after every call ends
Initiate or terminate outgoing calls using the Voicenter Click2Call API
| name | lead-tracker |
| description | Track which marketing campaign or web page generated an inbound call using the Voicenter Lead Tracker JS SDK |
Language. Reply in the user's language: detect what they write — Hebrew→Hebrew, English→English — and mirror it, switching if they switch mid-conversation. This shapes your prose, your questions, and your
AskUserQuestionoption labels only. It does not change the artifacts you produce — identifiers, JSON keys, BCP-47 language codes, API field names, and other data stay exactly as specified.
Help the developer integrate the Voicenter Lead Tracker — a JavaScript SDK that assigns dynamic phone numbers (DIDs) to website visitors to track which ad, campaign, or landing page led to each incoming call.
Use this skill when the user wants to:
VOICENTER_LEAD_TRACKER_TOKEN=your_did_pool_token_here
# Token is provided by Voicenter and is tied to a pool of DIDs configured for your account
CustomData — you know exactly which campaign generated it.Add the SDK script to your HTML <body>:
<script src="https://cdn.voicenter.co/cdn/Scripts/did_trace_worker/index.min.js"></script>
Then initialize:
VC_DID_TRACKER.init(
'YOUR_TOKEN_FROM_VOICENTER',
{ name: 'Visitor', utm_source: 'google' },
{ text: ['.phone-number'], href: ['#call-btn'], call: ['.click-to-call'] }
);
init() Arguments| Argument | Type | Required | Description |
|---|---|---|---|
token | String | ✅ | Token from Voicenter — maps to a pool of DIDs |
visitorInfo | Object | ❌ | Any data to associate with this visitor session (name, email, UTM params, GCLID, etc.) |
actions | Object | ❌ | DOM selectors to update automatically with the assigned DID |
actions.text | String[] | ❌ | Selectors whose innerText will be replaced with the DID |
actions.href | String[] | ❌ | Selectors whose href will be set to tel:<DID> |
actions.call | String[] | ❌ | Selectors that trigger a tel: call when clicked |
<p class="phone-display">03-123-4567</p>
<button class="call-btn">Call Us Now</button>
<script src="https://cdn.voicenter.co/cdn/Scripts/did_trace_worker/index.min.js"></script>
<script>
VC_DID_TRACKER.init(
'YOUR_TOKEN',
{ name: 'Visitor' },
{
text: ['.phone-display'],
call: ['.call-btn'],
}
);
</script>
const urlParams = new URLSearchParams(window.location.search);
VC_DID_TRACKER.init('YOUR_TOKEN', {
utm_source: urlParams.get('utm_source') ?? 'direct',
utm_campaign: urlParams.get('utm_campaign'),
utm_medium: urlParams.get('utm_medium'),
gclid: urlParams.get('gclid'),
fbclid: urlParams.get('fbclid'),
page: window.location.href,
});
VC_DID_TRACKER.init('YOUR_TOKEN', { name: 'Visitor' })
.then(function(did) {
console.log('Assigned DID:', did);
// Store in analytics, fire a custom GA event, etc.
gtag('event', 'phone_number_shown', { did });
});
<!DOCTYPE html>
<html>
<head><title>Landing Page</title></head>
<body>
<h1>Contact Us</h1>
<p>Call us: <span class="tracking-number">Loading...</span></p>
<a href="#" class="call-link">Click to Call</a>
<button class="call-btn">Call Now</button>
<script src="https://cdn.voicenter.co/cdn/Scripts/did_trace_worker/index.min.js"></script>
<script>
const params = new URLSearchParams(window.location.search);
VC_DID_TRACKER.init(
'YOUR_VOICENTER_TOKEN',
{
utm_source: params.get('utm_source') ?? 'direct',
utm_campaign: params.get('utm_campaign'),
gclid: params.get('gclid'),
page: window.location.href,
},
{
text: ['.tracking-number'],
href: ['.call-link'],
call: ['.call-btn'],
}
);
</script>
</body>
</html>
import { useEffect } from 'react';
declare const VC_DID_TRACKER: {
init: (token: string, visitorInfo?: object, actions?: object) => Promise<string>;
};
export function useLeadTracker(token: string) {
useEffect(() => {
const script = document.createElement('script');
script.src = 'https://cdn.voicenter.co/cdn/Scripts/did_trace_worker/index.min.js';
script.onload = () => {
const params = new URLSearchParams(window.location.search);
VC_DID_TRACKER.init(
token,
{
utm_source: params.get('utm_source') ?? 'direct',
utm_campaign: params.get('utm_campaign'),
page: window.location.href,
},
{
text: ['.tracking-phone'],
href: ['.phone-link'],
}
);
};
document.body.appendChild(script);
return () => { document.body.removeChild(script); };
}, [token]);
}
All visitorInfo fields are stored and associated with the call CDR. In the CDR Notification webhook, your UTM params, GCLID, and page URL will appear inside the CustomData field — enabling full offline call conversion attribution.
token maps to a pool of DIDs in your Voicenter account. Each concurrent visitor on the page gets a unique DID from the pool. Contact Voicenter to configure the pool size based on your expected concurrent traffic.localStorage so returning visitors within the DID expiry window get the same tracking number.gclid (Google Click ID) and fbclid (Facebook Click ID) to connect offline call conversions back to your ad campaigns.visitorInfo data in CustomData after the tracked call ends