crisp
About
The Crisp skill enables Claude to automate customer support operations on the Crisp platform through browser automation. It handles live chat management, helpdesk tickets, and CRM features, making it useful for developers building customer communication workflows. Setup involves environment variables for authentication and supports manual browser login for enhanced privacy.
Quick Install
Claude Code
Recommended/plugin add https://github.com/majiayu000/claude-skill-registrygit clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/crispCopy and paste this command in Claude Code to install this skill
Documentation
Crisp Skill
Overview
Automates Crisp customer messaging platform operations including live chat management, helpdesk tickets, knowledge base, and CRM features through browser automation.
Quick Install
curl -sSL https://canifi.com/skills/crisp/install.sh | bash
Or manually:
cp -r skills/crisp ~/.canifi/skills/
Setup
Configure via canifi-env:
# First, ensure canifi-env is installed:
# curl -sSL https://canifi.com/install.sh | bash
canifi-env set CRISP_EMAIL "[email protected]"
canifi-env set CRISP_PASSWORD "your-password"
Privacy & Authentication
Your credentials, your choice. Canifi LifeOS respects your privacy.
Option 1: Manual Browser Login (Recommended)
If you prefer not to share credentials with Claude Code:
- Complete the Browser Automation Setup using CDP mode
- Login to the service manually in the Playwright-controlled Chrome window
- Claude will use your authenticated session without ever seeing your password
Option 2: Environment Variables
If you're comfortable sharing credentials, you can store them locally:
canifi-env set SERVICE_EMAIL "your-email"
canifi-env set SERVICE_PASSWORD "your-password"
Note: Credentials stored in canifi-env are only accessible locally on your machine and are never transmitted.
Capabilities
- Respond to live chat conversations
- Manage helpdesk tickets
- Access visitor and contact data
- Use canned responses
- Create knowledge base articles
- Set operator availability
- View conversation analytics
- Manage chatbot flows
Usage Examples
Example 1: Respond to Live Chat
User: "Reply to the visitor asking about pricing on Crisp"
Claude: I'll respond to that chat.
- Navigate to Crisp inbox
- Find pricing inquiry conversation
- Review visitor context and history
- Compose helpful pricing response
- Send message
- Confirm delivery
Example 2: Create Ticket
User: "Convert this chat to a helpdesk ticket for follow-up"
Claude: I'll create that ticket.
- Open current conversation
- Click convert to ticket
- Set priority and category
- Assign to appropriate team
- Confirm ticket created
Example 3: Use Canned Response
User: "Send the business hours canned response"
Claude: I'll send that response.
- Open active conversation
- Access canned responses shortcut
- Select "business hours" response
- Insert and send
- Confirm message sent
Example 4: Update Knowledge Base
User: "Add a new FAQ article about returns to Crisp"
Claude: I'll create that article.
- Navigate to Knowledge Base section
- Click create new article
- Set category as FAQ
- Write returns policy content
- Publish article
- Confirm live
Authentication Flow
- Navigate to app.crisp.chat via Playwright MCP
- Enter email and password from canifi-env
- Select website if multiple
- Handle 2FA if enabled (notify user via iMessage)
- Verify inbox access
- Maintain session cookies
Error Handling
- Login Failed: Verify credentials, check for CAPTCHA
- Session Expired: Re-authenticate automatically
- 2FA Required: iMessage for verification code
- Website Not Found: List available websites for selection
- Conversation Closed: Cannot send to closed chats
- Visitor Offline: Message will be delivered when they return
- Rate Limited: Implement backoff for rapid messages
- Permission Denied: Check operator permissions
Self-Improvement Instructions
When encountering new Crisp features:
- Document new chat UI elements
- Add support for new message types
- Log successful response patterns
- Update for new helpdesk features
Notes
- Free plan has limited features
- Chatbot flows require Pro plan or higher
- Visitor data depends on tracking setup
- Knowledge base requires appropriate plan
- Multiple operators can view same conversation
- Mobile app notifications may duplicate
- Campaign features have separate interface
GitHub Repository
Related Skills
sglang
MetaSGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.
evaluating-llms-harness
TestingThis Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.
langchain
MetaLangChain is a framework for building LLM applications using agents, chains, and RAG pipelines. It supports multiple LLM providers, offers 500+ integrations, and includes features like tool calling and memory management. Use it for rapid prototyping and deploying production systems like chatbots, autonomous agents, and question-answering services.
llamaguard
OtherLlamaGuard is Meta's 7-8B parameter model for moderating LLM inputs and outputs across six safety categories like violence and hate speech. It offers 94-95% accuracy and can be deployed using vLLM, Hugging Face, or Amazon SageMaker. Use this skill to easily integrate content filtering and safety guardrails into your AI applications.
