What makes Chatbot Designer notable?

1K downloads. Trust evidence available

How should Chatbot Designer be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Chatbot Designer

Design customer service chatbot conversation flows for ecommerce — order status, returns, product recommendations, and escalation rules — that reduce ticket... Skill: Chatbot Designer Owner: leooooooow Summary: Design customer service chatbot conversation flows for ecommerce — order status, returns, product recommendations, and escalation rules — that reduce ticket... Tags: latest:1.1.0 Version history: v1.1.0 | 2026-06-05T14:44:21.110Z | user **Changelog – Version 1.0.1** - Added four documentation files: escalation-playbook.md, intent-library.md, output-template.md, and q

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.0k

Updated

Oct 11, 2026

Version

1.1.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.1.0release · observed Jun 5, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17974h9acjg4h7h5djv1hg51d83hcca:chatbot-designer

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-leooooooow-chatbot-designer/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

41,280 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: Chatbot Designer
description: Design customer service chatbot conversation flows for ecommerce — order status, returns, product recommendations, and escalation rules — that reduce ticket volume while maintaining satisfaction scores.
---

# Chatbot Designer

Design customer service chatbot conversation flows for ecommerce including order status inquiries, return requests, product recommendations, and escalation rules that reduce ticket volume while maintaining satisfaction scores. Most chatbot failures come not from the technology but from poorly designed flows — dead ends, missing escalation paths, or responses that feel robotic. This skill produces conversation architecture, intent mapping, and response logic that resolves common queries automatically while seamlessly handing off complex issues to human agents.

## Quick Reference

| Decision | Strong | Acceptable | Weak |
|---|---|---|---|
| Intent coverage | Map top 10 intents from ticket data before writing any flows | Map intents from assumption | Build flows for every possible scenario before launching |
| Escalation design | Graceful escalation after 2 failed responses + any customer frustration signal | Escalation only when explicitly requested | No escalation path — bot loops or dead-ends |
| Tone | Warm, direct, brand-consistent; acknowledges frustration | Neutral corporate tone | Overly casual/emoji-heavy OR stiff formal robospeak |
| Resolution path | Bot resolves or creates ticket — never leaves customer waiting without next step | Resolves common issues, drops others | Gives information without action ("call this number") |
| Order integration | Connected to OMS so bot can pull live order status | Static FAQs about shipping timelines | Cannot access order data at all |
| Return flow | Initiates return label automatically; confirms eligibility in real time | Explains return policy; directs to email | Can't process returns; sends customer elsewhere |
| Measurement | CSAT on bot interactions + containment rate + escalation rate tracked weekly | Track containment rate only | No metrics |

## Solves

- Support team overwhelmed with high-volume, repetitive queries (order status, return requests, shipping ETAs)
- Long first-response times hurting customer satisfaction and review scores
- After-hours support gaps — customers getting no response outside business hours
- Support costs scaling linearly with order volume instead of leveling off
- Inconsistent answers from human agents on standard policy questions
- High ticket volume from customers who can't self-serve on the website
- Returns and exchanges handled manually when they could be automated end-to-end

## Workflow

### Step 1 — Map Your Top 10 Support Intents

Pull 90 days of support ticket data and categorize by intent. Most ecommerce stores find 80% of volume concentrated in 5–7 intents.

**Typical ecommerce intent distribution:**

| Intent | Average % of tickets | Automatable? |
|---|---|---|
| Order status / tracking |

_meta.json

{
  "ownerId": "kn70fv0ehp50emedet9tx3fekd82pw3b",
  "slug": "chatbot-designer",
  "version": "1.1.0",
  "publishedAt": 1780670661110
}

escalation-playbook.md

# Escalation Playbook

## Escalation Philosophy

An escalation is not a failure — it is the chatbot doing its job. The goal is to:
1. Catch the moment when a human is needed
2. Transfer context so the customer doesn't repeat themselves
3. Set an accurate expectation for response time
4. Leave the customer feeling helped, not abandoned

A chatbot with excellent escalation design achieves higher CSAT than one that tries to resolve everything and gets stuck.

## Escalation Trigger Taxonomy

### Tier 1 — Immediate Escalation (within seconds)

| Trigger | Detection method | Queue |
|---|---|---|
| Physical safety mention | Keywords: injury, hurt, damaged, burned, allergic reaction | Emergency / Senior |
| Legal or fraud mention | Keywords: fraud, dispute, chargeback, lawyer, report | Legal / Senior |
| High-value customer | CRM tag: LTV > $[threshold] | Priority |
| Explicit human request | Keywords: human, agent, person, real | General |
| Severe frustration language | Keywords: furious, unacceptable, disgusting, lawsuit | Priority |

### Tier 2 — Escalation After 2 Failed Attempts

| Trigger | Condition | Queue |
|---|---|---|
| Unresolvable intent | Bot attempted twice, no resolution | General |
| Missing order data | Cannot find order after 2 lookups | General |
| Out-of-policy request | Outside return window, discontinued product | General |
| Complex multi-issue | Customer raises 3+ different issues in one session | General |

### Tier 3 — Proactive Escalation (Batched)

| Trigger | Timing | Action |
|---|---|---|
| Unhandled intent | Weekly review | Add to flow build queue |
| Low CSAT bot rating | <3/5 rating given | Review transcript; identify gap |
| Long session with no resolution | Session > 10 min, no confirmation | Flag for quality review |

## Escalation Handoff Protocol

### Step 1 — Signal the transition warmly
Never abruptly transfer. Use a bridging line:
> "Let me get one of our team members to help you with this."
> "This is something I want to make sure our specialists handle for you."
> "I'm connecting you now — you're in good hands."

### Step 2 — Summarize the conversation
Pre-fill the ticket with:
- Customer name and contact
- Order number(s) involved
- Issue summary in 2–3 sentences
- What the bot already tried
- Customer sentiment (frustrated / neutral / positive)
- Any data already collected (return reason, device type, etc.)

**Ticket pre-fill template:**
```
[BOT HANDOFF] Customer: [Name] | Order: #[number]
Issue: [1-sentence summary]
Bot actions taken: [what was attempted]
Data collected: [relevant fields]
Customer sentiment: [frustrated/neutral/satisfied]
Chat transcript: [attached]
```

### Step 3 — Set response time expectation
Never use vague language. Be specific:
- ✅ "Our team will reply within 2 business hours"
- ✅ "You'll hear back by 9am tomorrow"
- ❌ "Someone will be in touch soon"
- ❌ "We'll reply as quickly as possible"

### Step 4 — Confirm and close the bot interaction
> "I've sent everything to our team an

intent-library.md

# Intent Library — Ecommerce Chatbot

## Order Status Intent

**Trigger keywords:** "where is my order", "track", "tracking", "shipping status", "hasn't arrived", "order status", "when will it arrive", "delivery"

**Required data:** Order number OR email address

**Success response template:**
> "I found your order! Order #[number] shipped on [date] via [carrier]. Your tracking number is [tracking] — click here to see live updates: [link]. Estimated delivery: [date]. Is there anything else I can help with?"

**Delayed order response:**
> "Your order #[number] is currently showing a delay with [carrier]. The new estimated delivery is [date]. I've flagged this on your account. If it doesn't arrive by [date+1], come back and I can file a claim on your behalf."

**Not found response:**
> "I couldn't find an order with that information. Can you double-check the order number? It's usually in your confirmation email and starts with #. If you still can't find it, let me connect you with our team."

---

## Return Request Intent

**Trigger keywords:** "return", "refund", "exchange", "send back", "doesn't fit", "changed my mind", "not what I expected"

**Required data:** Order number, reason for return

**Eligible return response:**
> "I can process this return for you. Your order is within our [30-day] return window. I'll send a prepaid return label to [email] — please allow 5–10 minutes for it to arrive. Once we receive your return, your refund will be processed within [X] business days."

**Ineligible return response (outside window):**
> "This order was delivered on [date] — our [30-day] return window closed on [date]. I'm not able to process this automatically, but I'll connect you with our team who can review your situation."

**Exchange response:**
> "For an exchange, I'll need to process a return and place a new order. Would you like me to start the return process? You can then place a new order with the correct [size/color/item], and I can apply a discount code for the inconvenience."

---

## Shipping Delay Intent

**Trigger keywords:** "late", "delayed", "hasn't shipped", "still processing", "stuck", "where", "overdue"

**Response template:**
> "I'm sorry to hear your order is running late. Let me check on this. [Look up order status] Your order is currently [status]. [If in transit:] It looks like there's been a carrier delay — the new estimated delivery is [date]. [If not yet shipped:] It's still being prepared for shipment. I'll flag this as high priority for our fulfillment team."

---

## Wrong Item Received Intent

**Trigger keywords:** "wrong item", "wrong product", "not what I ordered", "incorrect", "different item"

**Response template:**
> "I'm really sorry about that — receiving the wrong item is frustrating. I'd like to make this right. Can you share: (1) your order number, and (2) what you received vs. what you ordered? I'll initiate a replacement shipment and arrange return of the incorrect item at no cost to you."

---

## Product

output-template.md

# Chatbot Flow Design Document

## Project Overview
- **Brand:** 
- **Platform:** Shopify / WooCommerce / Custom
- **Chatbot tool:** Gorgias / Tidio / Intercom / Zendesk / Custom
- **OMS integration:** Yes / No / Planned
- **Launch date target:** 

## Intent Priority Matrix
| Rank | Intent | % of ticket volume | Automation potential | Build priority |
|---|---|---|---|---|
| 1 | | % | High/Medium/Low | Launch / Phase 2 |
| 2 | | % | | |
| 3 | | % | | |
| 4 | | % | | |
| 5 | | % | | |

## Main Menu Design
```
Welcome message: 

Menu options:
1. 
2. 
3. 
4. 
5. Talk to a person
```

## Flow Designs

### Flow 1: [Intent Name]
**Trigger:** (menu selection / keywords / both)  
**Data required:** 

```
Step 1 — Acknowledge:

Step 2 — Data collect:

Step 3 — Lookup/check:

Step 4A — Resolve (success):

Step 4B — Cannot resolve:

Step 5 — Escalation:

Step 6 — Confirmation:
```

### Flow 2: [Intent Name]
**Trigger:**  
**Data required:** 

```
[Repeat structure]
```

## Escalation Rules
| Trigger | Rule | Action |
|---|---|---|
| Frustration keywords | "ridiculous", "furious", "unacceptable", "worst" | Immediate human handoff |
| 2 failed resolution attempts | Any intent | Escalate with transcript |
| Explicit request | "human", "agent", "real person" | Immediate handoff |
| High-value customer | LTV > $[threshold] | Priority queue |

## Response Time Commitments (communicated to customer)
- Business hours escalation: respond within ___ hours
- After-hours escalation: respond by ___ next business day
- Acknowledgement message: sent immediately upon escalation

## Measurement Plan
| KPI | Baseline | 30-day target | 90-day target |
|---|---|---|---|
| Containment rate | | >50% | >65% |
| Escalation rate | | <40% | <30% |
| CSAT (bot) | | >3.5/5 | >3.8/5 |
| Drop-off rate | | <20% | <15% |

## Unhandled Intent Review Schedule
- Weekly review: Mondays, 30 minutes
- New flow threshold: intent appears 10+ times in a week → add to build queue

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.