chatbot-builder
Design conversational chatbot flows with intents, responses, and escalation logic. TRIGGERS - Use when user wants to build a chatbot, design conversation flows, or create automated chat responses.
- License 许可
- MIT
- 最近更新
- 2026-11-09
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- chatbot-builder
- source
- https://github.com/Winbda/claude-skills-collection
- license
- MIT
- version
- 1.0.0
- category
- general
- description
- Design conversational chatbot flows with intents, responses, and escalation logic. TRIGGERS - Use when user wants to build a chatbot, design conversation flows, or create automated chat responses.
- disable-model-invocation
- false
03 SKILL.md 正文
Chatbot Builder
Overview
Designs complete chatbot architectures with conversation flows, intent mapping, response templates, and escalation rules.
Workflow
Step 1: Define the Bot
- Purpose: Customer support, lead qualification, FAQ, onboarding, or sales?
- Platform: Website widget, WhatsApp, Messenger, Slack, or custom?
- Persona: What's the bot's personality?
- Scope: What topics should it handle? What should it NOT handle?
- Escalation: When should it hand off to a human?
Step 2: Map Intents
| Intent | Example Phrases | Priority |
|---|---|---|
| Greeting | "hi", "hello", "hey there" | High |
| Pricing | "how much", "pricing", "cost" | High |
| Support | "help", "problem", "not working" | High |
| [Custom] | [phrases] | [priority] |
Step 3: Design Conversation Flows
USER: [trigger phrase]
↓
BOT: [response + follow-up question]
↓
USER: [option A] → BOT: [response A] → [next step]
USER: [option B] → BOT: [response B] → [next step]
USER: [unclear] → BOT: [clarification] → [retry]
↓
[3 unclear attempts] → ESCALATE TO HUMAN
Step 4: Write Response Templates
For each intent:
- Initial response: First message
- Follow-up questions: Gather needed info
- Resolution: Answer or action
- Fallback: When bot can't help
- Handoff message: Transition to human
Output Format
# Chatbot Design: [Bot Name]
## Bot Profile
- **Name**: [bot name]
- **Personality**: [description]
- **Platform**: [where it lives]
- **Supported languages**: [languages]
## Intent Map
[Table of all intents with examples and responses]
## Conversation Flows
### Flow 1: [Name]
[Visual flow with decision trees]
### Flow 2: [Name]
[Visual flow]
## Response Templates
[All response messages organized by intent]
## Escalation Rules
- After [X] failed attempts → human
- Keywords [list] → immediate human
- Sentiment negative → human
- Off-hours → ticket + follow-up
## Knowledge Base
[FAQ answers the bot should know]
## Implementation Notes
- Platform: [recommended tool]
- AI model: [if using LLM]
- Integration: [APIs needed]
Quality Checklist
- [ ] All common intents mapped
- [ ] Fallback responses for unrecognized input
- [ ] Escalation rules clear
- [ ] Persona consistent across responses
- [ ] Tested with 10+ conversation paths
04 同仓库更多 Skills
dei-assessment
Assess diversity, equity, and inclusion with metrics. TRIGGERS - Use when user needs help with dei-assessment related tasks.
dei-action-plan
Create DEI action plans with goals and initiatives. TRIGGERS - Use when user needs help with dei-action-plan related tasks.
culture-fit-assessment
Design culture add assessment processes. TRIGGERS - Use when user needs help with culture-fit-assessment related tasks.
cowork-to-code-bridge
Use an already-installed, independently verified cowork-to-code bridge to run narrowly approved actions on the user's own macOS, Linux, or WSL2 machine through a local file queue.
counter-offer-response
Draft counter-offer responses for retention. TRIGGERS - Use when user needs help with counter-offer-response related tasks.
continuous-feedback-system
Design continuous feedback systems. TRIGGERS - Use when user needs help with continuous-feedback-system related tasks.