About integrating-providers
A skill for integrating AI providers with Claude Council, covering executable shell scripts, API key setup, and testing. It lists current providers and default models, with troubleshooting guidance.
Key features
- 01Defines provider script input and output
- 02Explains script creation and test steps
- 03Lists API key variables and default models
- 04Covers discovery and API error troubleshooting
Use cases
- 01Add an AI provider to Claude Council
- 02Write a shell provider script to the interface
- 03Set keys and verify provider responses
- 04Troubleshoot discovery or response parsing failures
Install
Copy the command and run it in a terminal.
$
npx skills add https:/ / github.com/ hex/ claude-council --skill integrating-providersAfter installing, type/integrating-providersin Claude Code to confirm it loaded.
Bundled filesapi-patterns.md
Details
From the project READMEAdding AI Providers to Claude Council
Provider Script Interface
Each provider is a shell script in scripts/providers/ that:
- Accepts a prompt as the first argument
- Outputs the AI response to stdout
- Exits 0 on success, non-zero on failure
Quick Start
- Create
scripts/providers/{name}.sh(seeapi-patterns.mdfor templates) chmod +x scripts/providers/{name}.sh- Set
{NAME}_API_KEYenvironment variable - Test:
./scripts/providers/{name}.sh "Hello"
Current Providers
| Provider | API Key Variable | Default Model |
|---|---|---|
| Gemini | GEMINI_API_KEY | gemini-3.1-pro-preview |
| OpenAI | OPENAI_API_KEY | gpt-5.5-pro |
| Grok | XAI_API_KEY (or GROK_API_KEY) | grok-4.20-reasoning |
| Perplexity | PERPLEXITY_API_KEY | sonar-reasoning-pro |
Troubleshooting
- Not discovered: Check API key is set and script is executable
- API errors: Verify key, check rate limits, confirm model name
- Parse fails: Add
echo "$RESPONSE"to debug, check response format
Reference
For API patterns and code templates, see api-patterns.md in this directory.
Comments
Markdown supported