admin/ClaudeCode-Custom-Skills
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: Add all 25+ OpenCode-compatible AI providers to Claw Setup

Browse Source 
Updated provider support to match OpenCode's full provider list:

Built-in Providers (18):
- Anthropic, OpenAI, Azure OpenAI
- Google AI, Google Vertex AI
- Amazon Bedrock
- OpenRouter, xAI, Mistral
- Groq, Cerebras, DeepInfra
- Cohere, Together AI, Perplexity
- Vercel AI, GitLab, GitHub Copilot

Custom Loader Providers:
- GitHub Copilot Enterprise
- Google Vertex Anthropic
- Azure Cognitive Services
- Cloudflare AI Gateway
- SAP AI Core

Local/Self-Hosted:
- Ollama, LM Studio, vLLM

Features:
- Model fetching from provider APIs
- Custom model input support
- Multi-provider configuration
- Environment variable security

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Claude Code
2026-02-22 03:51:55 -05:00
Unverified
parent 2072e16bd1
commit baffcf6db1
3 changed files with 466 additions and 820 deletions
Download Patch File Download Diff File Expand all files Collapse all files

528
skills/claw-setup/SKILL.md
View File

@@ -6,7 +6,7 @@ version: 1.0.0
# Claw Setup Skill
End-to-end professional setup of AI Agent platforms from the Claw family with security hardening and personal customization through interactive brainstorming.
End-to-end professional setup of AI Agent platforms from the Claw family with security hardening, multi-provider configuration, and personal customization through interactive brainstorming.
## Supported Platforms
@@ -18,275 +18,85 @@ End-to-end professional setup of AI Agent platforms from the Claw family with se
| **ZeroClaw** | Rust | <5MB | <10ms | Maximum performance, security |
| **NanoClaw** | TypeScript | ~50MB | ~5s | WhatsApp integration |
## What This Skill Does
## AI Providers (OpenCode Compatible - 25+ Providers)
### Phase 1: Platform Selection
- Interactive comparison of all platforms
- Hardware requirements check
- Use case matching
### Built-in Providers
### Phase 2: Secure Installation
- Clone from official GitHub repos
- Security hardening (secrets management, network isolation)
- Environment configuration
- API key setup with best practices
| Provider | SDK Package | Key Models | Features |
|----------|-------------|------------|----------|
| **Anthropic** | `@ai-sdk/anthropic` | Claude 3.5/4/Opus | Extended thinking, PDF support |
| **OpenAI** | `@ai-sdk/openai` | GPT-4o, o1, o3, GPT-5 | Function calling, structured output |
| **Azure OpenAI** | `@ai-sdk/azure` | GPT-5, GPT-4o Enterprise | Azure integration, custom endpoints |
| **Google AI** | `@ai-sdk/google` | Gemini 2.5, Gemini 3 Pro | Multimodal, Google Cloud |
| **Google Vertex** | `@ai-sdk/google-vertex` | Claude, Gemini on GCP | Anthropic on Google infra |
| **Amazon Bedrock** | `@ai-sdk/amazon-bedrock` | Nova, Claude, Llama 3 | AWS credentials, regional prefixes |
| **OpenRouter** | `@openrouter/ai-sdk-provider` | 100+ models | Multi-provider gateway |
| **xAI** | `@ai-sdk/xai` | Grok models | Real-time data integration |
| **Mistral AI** | `@ai-sdk/mistral` | Mistral Large, Codestral | Code-focused models |
| **Groq** | `@ai-sdk/groq` | Llama 3, Mixtral | Ultra-low latency inference |
| **DeepInfra** | `@ai-sdk/deepinfra` | Open source models | Cost-effective hosting |
| **Cerebras** | `@ai-sdk/cerebras` | Llama 3 variants | Hardware-accelerated inference |
| **Cohere** | `@ai-sdk/cohere` | Command R+, Embed | Enterprise RAG capabilities |
| **Together AI** | `@ai-sdk/togetherai` | Open source models | Fine-tuning and hosting |
| **Perplexity** | `@ai-sdk/perplexity` | Sonar models | Real-time web search |
| **Vercel AI** | `@ai-sdk/vercel` | Multi-provider gateway | Edge hosting, rate limiting |
| **GitLab** | `@gitlab/gitlab-ai-provider` | GitLab Duo | CI/CD AI integration |
| **GitHub Copilot** | Custom | GPT-5 series | IDE integration, OAuth |
### Phase 3: Personal Customization
- Interactive brainstorming session
- Custom agent templates
- Integration setup (messaging, calendar, etc.)
- Memory and context configuration
### Custom Loader Providers
### Phase 4: Verification & Deployment
- Health checks
- Test runs
- Production deployment options
| Provider | Auth Method | Use Case |
|----------|-------------|----------|
| **GitHub Copilot Enterprise** | OAuth + API Key | Enterprise IDE integration |
| **Google Vertex Anthropic** | GCP Service Account | Claude on Google Cloud |
| **Azure Cognitive Services** | Azure AD | Azure AI services |
| **Cloudflare AI Gateway** | Gateway Token | Unified billing, rate limiting |
| **SAP AI Core** | Service Key | SAP enterprise integration |
| **OpenCode Free** | None | Free public models |
## GitHub Repositories
### Local/Self-Hosted
```
OpenClaw: https://github.com/openclaw/openclaw
NanoBot: https://github.com/HKUDS/nanobot
PicoClaw: https://github.com/sipeed/picoclaw
ZeroClaw: https://github.com/zeroclaw-labs/zeroclaw
NanoClaw: https://github.com/nanoclaw/nanoclaw
```
| Provider | Base URL | Use Case |
|----------|----------|----------|
| **Ollama** | localhost:11434 | Local model hosting |
| **LM Studio** | localhost:1234 | GUI local models |
| **vLLM** | localhost:8000 | High-performance serving |
| **LocalAI** | localhost:8080 | OpenAI-compatible local |
## Usage Examples
```
"Setup OpenClaw on my server"
"I want to install NanoBot for personal use"
"Help me choose between ZeroClaw and PicoClaw"
"Deploy an AI assistant with security best practices"
"Setup Claw framework with my custom requirements"
```
## Installation Commands by Platform
### OpenClaw (Full Featured)
```bash
# Prerequisites
sudo apt install -y nodejs npm
# Clone and setup
git clone https://github.com/openclaw/openclaw.git
cd openclaw
npm install
npm run setup
# Configure
cp .env.example .env
# Edit .env with API keys
# Run
npm run start
```
### NanoBot (Python Lightweight)
```bash
# Quick install
pip install nanobot-ai
# Or from source
git clone https://github.com/HKUDS/nanobot.git
cd nanobot
pip install -e .
# Setup
nanobot onboard
nanobot gateway
```
### PicoClaw (Go Ultra-Light)
```bash
# Download binary
wget https://github.com/sipeed/picoclaw/releases/latest/picoclaw-linux-amd64
chmod +x picoclaw-linux-amd64
sudo mv picoclaw-linux-amd64 /usr/local/bin/picoclaw
# Or build from source
git clone https://github.com/sipeed/picoclaw.git
cd picoclaw
go build -o picoclaw
# Run
picoclaw gateway
```
### ZeroClaw (Rust Minimal)
```bash
# Download binary
wget https://github.com/zeroclaw-labs/zeroclaw/releases/latest/zeroclaw-linux-amd64
chmod +x zeroclaw-linux-amd64
sudo mv zeroclaw-linux-amd64 /usr/local/bin/zeroclaw
# Or from source
git clone https://github.com/zeroclaw-labs/zeroclaw.git
cd zeroclaw
cargo build --release
# Run
zeroclaw gateway
```
## Security Hardening
### Secrets Management
```bash
# Never commit .env files
echo ".env" >> .gitignore
echo "*.pem" >> .gitignore
# Use environment variables
export ANTHROPIC_API_KEY="your-key"
export OPENROUTER_API_KEY="your-key"
# Or use secret files with restricted permissions
mkdir -p ~/.config/claw
cat > ~/.config/claw/config.json << 'CONFIG'
{
"providers": {
"openrouter": { "apiKey": "${OPENROUTER_API_KEY}" }
}
}
CONFIG
chmod 600 ~/.config/claw/config.json
```
### Network Security
```bash
# Bind to localhost only
# In config, set:
# "server": { "host": "127.0.0.1", "port": 3000 }
# Use reverse proxy for external access
# nginx example:
server {
listen 443 ssl;
server_name claw.yourdomain.com;
ssl_certificate /etc/letsencrypt/live/yourdomain.com/fullchain.pem;
ssl_certificate_key /etc/letsencrypt/live/yourdomain.com/privkey.pem;
location / {
proxy_pass http://127.0.0.1:3000;
proxy_set_header Host $host;
proxy_set_header X-Real-IP $remote_addr;
}
}
```
### Systemd Service
```bash
# /etc/systemd/system/claw.service
[Unit]
Description=Claw AI Assistant
After=network.target
[Service]
Type=simple
User=claw
Group=claw
WorkingDirectory=/opt/claw
ExecStart=/usr/local/bin/claw gateway
Restart=on-failure
RestartSec=10
# Security hardening
NoNewPrivileges=true
PrivateTmp=true
ProtectSystem=strict
ProtectHome=true
ReadWritePaths=/opt/claw/data
[Install]
WantedBy=multi-user.target
```
## Brainstorm Session Topics
1. **Use Case Discovery**
- What tasks should the AI handle?
- Which platforms/channels to integrate?
- Automation vs. interactive preferences?
2. **Model Selection**
- Claude, GPT, Gemini, or local models?
- Cost vs. performance tradeoffs?
- Privacy requirements?
3. **Integration Planning**
- Messaging: Telegram, Discord, WhatsApp, Slack?
- Calendar: Google, Outlook, Apple?
- Storage: Local, cloud, hybrid?
- APIs to connect?
4. **Custom Agent Design**
- Personality and tone?
- Domain expertise areas?
- Memory and context preferences?
- Proactive vs. reactive behavior?
5. **Deployment Strategy**
- Local machine, VPS, or cloud?
- High availability requirements?
- Backup and recovery needs?
## AI Provider Configuration
### Supported Providers
| Provider | Type | API Base | Models |
|----------|------|----------|--------|
| **Anthropic** | Direct | api.anthropic.com | Claude 3.5/4/Opus |
| **OpenAI** | Direct | api.openai.com | GPT-4, GPT-4o, o1, o3 |
| **Google** | Direct | generativelanguage.googleapis.com | Gemini 2.0/1.5 |
| **OpenRouter** | Gateway | openrouter.ai/api | 200+ models |
| **Together AI** | Direct | api.together.xyz | Llama, Mistral, Qwen |
| **Groq** | Direct | api.groq.com | Llama, Mixtral (fast) |
| **Cerebras** | Direct | api.cerebras.ai | Llama (fastest) |
| **DeepSeek** | Direct | api.deepseek.com | DeepSeek V3/R1 |
| **Mistral** | Direct | api.mistral.ai | Mistral, Codestral |
| **xAI** | Direct | api.x.ai | Grok |
| **Replicate** | Gateway | api.replicate.com | Various |
| **Local** | Self-hosted | localhost | Ollama, LM Studio |
### Fetch Available Models
## Fetch Available Models
```bash
# OpenRouter - List all models
# OpenRouter - All models
curl -s https://openrouter.ai/api/v1/models \
-H "Authorization: Bearer $OPENROUTER_API_KEY" | jq '.data[].id'
# OpenAI - List models
# OpenAI - GPT models
curl -s https://api.openai.com/v1/models \
-H "Authorization: Bearer $OPENAI_API_KEY" | jq '.data[].id'
# Anthropic - Available models (static list)
# claude-opus-4-5-20250219
# claude-sonnet-4-5-20250219
# claude-3-5-sonnet-20241022
# claude-3-5-haiku-20241022
# Anthropic (static list)
# claude-opus-4-5-20250219, claude-sonnet-4-5-20250219, claude-3-5-sonnet-20241022
# Google Gemini
curl -s "https://generativelanguage.googleapis.com/v1/models?key=$GOOGLE_API_KEY" | jq '.models[].name'
curl -s "https://generativelanguage.googleapis.com/v1/models?key=$GOOGLE_API_KEY"
# Groq - List models
# Groq
curl -s https://api.groq.com/openai/v1/models \
-H "Authorization: Bearer $GROQ_API_KEY" | jq '.data[].id'
-H "Authorization: Bearer $GROQ_API_KEY"
# Together AI
curl -s https://api.together.xyz/v1/models \
-H "Authorization: Bearer $TOGETHER_API_KEY" | jq '.data[].id'
-H "Authorization: Bearer $TOGETHER_API_KEY"
# Ollama (local)
curl -s http://localhost:11434/api/tags | jq '.models[].name'
curl -s http://localhost:11434/api/tags
# models.dev - Universal model list
curl -s https://models.dev/api/models.json
```
### Configuration Templates
## Multi-Provider Configuration
#### Multi-Provider Config
```json
{
"providers": {
@@ -298,33 +108,85 @@ curl -s http://localhost:11434/api/tags | jq '.models[].name'
"apiKey": "${OPENAI_API_KEY}",
"baseURL": "https://api.openai.com/v1"
},
"azure": {
"apiKey": "${AZURE_OPENAI_API_KEY}",
"baseURL": "${AZURE_OPENAI_ENDPOINT}",
"deployment": "gpt-4o"
},
"google": {
"apiKey": "${GOOGLE_API_KEY}",
"baseURL": "https://generativelanguage.googleapis.com/v1"
},
"vertex": {
"projectId": "${GOOGLE_CLOUD_PROJECT}",
"location": "${GOOGLE_CLOUD_LOCATION}",
"credentials": "${GOOGLE_APPLICATION_CREDENTIALS}"
},
"bedrock": {
"region": "us-east-1",
"accessKeyId": "${AWS_ACCESS_KEY_ID}",
"secretAccessKey": "${AWS_SECRET_ACCESS_KEY}"
},
"openrouter": {
"apiKey": "${OPENROUTER_API_KEY}",
"baseURL": "https://openrouter.ai/api/v1"
"baseURL": "https://openrouter.ai/api/v1",
"headers": {
"HTTP-Referer": "https://yourapp.com",
"X-Title": "YourApp"
}
},
"groq": {
"apiKey": "${GROQ_API_KEY}",
"baseURL": "https://api.groq.com/openai/v1"
},
"together": {
"apiKey": "${TOGETHER_API_KEY}",
"baseURL": "https://api.together.xyz/v1"
},
"deepseek": {
"apiKey": "${DEEPSEEK_API_KEY}",
"baseURL": "https://api.deepseek.com/v1"
"xai": {
"apiKey": "${XAI_API_KEY}",
"baseURL": "https://api.x.ai/v1"
},
"mistral": {
"apiKey": "${MISTRAL_API_KEY}",
"baseURL": "https://api.mistral.ai/v1"
},
"xai": {
"apiKey": "${XAI_API_KEY}",
"baseURL": "https://api.x.ai/v1"
"groq": {
"apiKey": "${GROQ_API_KEY}",
"baseURL": "https://api.groq.com/openai/v1"
},
"cerebras": {
"apiKey": "${CEREBRAS_API_KEY}",
"baseURL": "https://api.cerebras.ai/v1"
},
"deepinfra": {
"apiKey": "${DEEPINFRA_API_KEY}",
"baseURL": "https://api.deepinfra.com/v1"
},
"cohere": {
"apiKey": "${COHERE_API_KEY}",
"baseURL": "https://api.cohere.ai/v1"
},
"together": {
"apiKey": "${TOGETHER_API_KEY}",
"baseURL": "https://api.together.xyz/v1"
},
"perplexity": {
"apiKey": "${PERPLEXITY_API_KEY}",
"baseURL": "https://api.perplexity.ai"
},
"vercel": {
"apiKey": "${VERCEL_AI_KEY}",
"baseURL": "https://api.vercel.ai/v1"
},
"gitlab": {
"token": "${GITLAB_TOKEN}",
"baseURL": "${GITLAB_URL}/api/v4"
},
"github": {
"token": "${GITHUB_TOKEN}",
"baseURL": "https://api.github.com"
},
"cloudflare": {
"accountId": "${CF_ACCOUNT_ID}",
"gatewayId": "${CF_GATEWAY_ID}",
"token": "${CF_AI_TOKEN}"
},
"sap": {
"serviceKey": "${AICORE_SERVICE_KEY}",
"deploymentId": "${AICORE_DEPLOYMENT_ID}"
},
"ollama": {
"baseURL": "http://localhost:11434/v1",
@@ -336,16 +198,29 @@ curl -s http://localhost:11434/api/tags | jq '.models[].name'
"model": "anthropic/claude-sonnet-4-5",
"temperature": 0.7,
"maxTokens": 4096
},
"fast": {
"model": "groq/llama-3.3-70b-versatile"
},
"coding": {
"model": "anthropic/claude-sonnet-4-5"
},
"research": {
"model": "perplexity/sonar-pro"
},
"local": {
"model": "ollama/llama3.2:70b"
}
}
}
```
#### Custom Model Configuration
## Custom Model Support
```json
{
"customModels": {
"my-fine-tuned-model": {
"my-fine-tuned-gpt": {
"provider": "openai",
"modelId": "ft:gpt-4o:my-org:custom:suffix",
"displayName": "My Custom GPT-4o"
@@ -355,110 +230,61 @@ curl -s http://localhost:11434/api/tags | jq '.models[].name'
"modelId": "llama3.2:70b",
"displayName": "Local Llama 3.2 70B"
},
"openrouter-model": {
"openrouter-custom": {
"provider": "openrouter",
"modelId": "meta-llama/llama-3.3-70b-instruct",
"displayName": "Llama 3.3 70B via OpenRouter"
"modelId": "custom-org/my-model",
"displayName": "Custom via OpenRouter"
}
}
}
```
### Provider Selection Flow
## Installation Commands
```
1. Ask user which providers they have API keys for:
□ Anthropic (Claude)
□ OpenAI (GPT)
□ Google (Gemini)
□ OpenRouter (Multi-model)
□ Together AI
□ Groq (Fast inference)
□ Cerebras (Fastest)
□ DeepSeek
□ Mistral
□ xAI (Grok)
□ Local (Ollama/LM Studio)
2. For each selected provider:
- Prompt for API key
- Fetch available models (if API supports)
- Let user select or input custom model
3. Generate secure configuration:
- Store keys in environment variables
- Create config.json with model selections
- Set up key rotation reminders
4. Test connectivity:
- Send test prompt to each configured provider
- Verify response
### OpenClaw
```bash
git clone https://github.com/openclaw/openclaw.git
cd openclaw && npm install && npm run setup
```
### Model Fetching Script
### NanoBot
```bash
pip install nanobot-ai
nanobot onboard
```
### PicoClaw
```bash
wget https://github.com/sipeed/picoclaw/releases/latest/picoclaw-linux-amd64
chmod +x picoclaw-linux-amd64 && sudo mv picoclaw-linux-amd64 /usr/local/bin/picoclaw
```
### ZeroClaw
```bash
wget https://github.com/zeroclaw-labs/zeroclaw/releases/latest/zeroclaw-linux-amd64
chmod +x zeroclaw-linux-amd64 && sudo mv zeroclaw-linux-amd64 /usr/local/bin/zeroclaw
```
## Security Hardening
```bash
#!/bin/bash
# fetch-models.sh - Fetch available models from providers
# Secrets in environment variables
export ANTHROPIC_API_KEY="your-key"
export OPENAI_API_KEY="your-key"
echo "=== AI Provider Model Fetcher ==="
# Restricted config permissions
chmod 600 ~/.config/claw/config.json
# OpenRouter
if [ -n "$OPENROUTER_API_KEY" ]; then
echo -e "\n📦 OpenRouter Models:"
curl -s https://openrouter.ai/api/v1/models \
-H "Authorization: Bearer $OPENROUTER_API_KEY" | \
jq -r '.data[] | " • \(.id) - \(.name // .id)"' | head -20
fi
# OpenAI
if [ -n "$OPENAI_API_KEY" ]; then
echo -e "\n📦 OpenAI Models:"
curl -s https://api.openai.com/v1/models \
-H "Authorization: Bearer $OPENAI_API_KEY" | \
jq -r '.data[] | select(.id | contains("gpt")) | " • \(.id)"' | sort -u
fi
# Groq
if [ -n "$GROQ_API_KEY" ]; then
echo -e "\n📦 Groq Models:"
curl -s https://api.groq.com/openai/v1/models \
-H "Authorization: Bearer $GROQ_API_KEY" | \
jq -r '.data[].id' | sed 's/^/ • /'
fi
# Ollama (local)
echo -e "\n📦 Ollama Models (local):"
curl -s http://localhost:11434/api/tags 2>/dev/null | \
jq -r '.models[].name' | sed 's/^/ • /' || echo " Ollama not running"
# Together AI
if [ -n "$TOGETHER_API_KEY" ]; then
echo -e "\n📦 Together AI Models:"
curl -s https://api.together.xyz/v1/models \
-H "Authorization: Bearer $TOGETHER_API_KEY" | \
jq -r '.data[].id' | head -20 | sed 's/^/ • /'
fi
echo -e "\n✅ Model fetch complete"
# Systemd hardening
NoNewPrivileges=true
PrivateTmp=true
ProtectSystem=strict
```
### Custom Model Input
## Brainstorm Session Topics
When user selects "Custom Model", prompt for:
1. **Provider**: Which provider hosts this model
2. **Model ID**: Exact model identifier
3. **Display Name**: Friendly name for UI
4. **Context Window**: Max tokens (optional)
5. **Capabilities**: Text, vision, code, etc. (optional)
Example custom model entry:
```json
{
"provider": "openrouter",
"modelId": "custom-org/my-fine-tuned-v2",
"displayName": "My Fine-Tuned Model v2",
"contextWindow": 128000,
"capabilities": ["text", "code"]
}
```
1. **Use Case**: Coding, research, productivity, automation?
2. **Model Selection**: Claude, GPT, Gemini, local?
3. **Integrations**: Telegram, Discord, calendar, storage?
4. **Deployment**: Local, VPS, cloud?
5. **Custom Agents**: Personality, memory, proactivity?