Menu
Send a chat message to the running agent server and display the response
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Generate a new SparkGen-AWS project from the cookiecutter template
Develop and modify the SparkGen-AWS cookiecutter template — variables, hooks, files
Run cookiecutter matrix tests to verify template generates correctly across all variable combinations
Add, modify, remove, list, or show agents in the workflow
Switch LLM providers, deployment modes, and manage environment configuration
Diagnose issues with Ollama, Docker, AWS, endpoints, guardrails, RAG, or general health
| name | sparkgen-chat |
| description | Send a chat message to the running agent server and display the response |
| user_invokable | true |
| auto_invokable | false |
| arguments | <message> [--agent name] [--session id] [--max-iterations N] |
Send a chat message to the running SparkGen agent and display the full response.
Before sending:
curl -sf http://localhost:8000/health
/sparkgen-deploy local or make local.env (default: dev-local-key)Build and send the request:
curl -s -X POST http://localhost:8000/v1/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: ${API_KEY:-dev-local-key}" \
-d '{
"message": "<user message>",
"agent_name": "<agent or empty for default>",
"session_id": "<session or auto-generated>",
"max_iterations": <N or 10>
}'
Parse and display the JSON response:
When --session is provided, the agent maintains conversation history. Use the same session ID for follow-up messages to test multi-turn behavior.
/sparkgen-chat "What tools do you have?"
/sparkgen-chat "Search for deployment docs" --agent researcher
/sparkgen-chat "Follow up on that" --session abc123
/sparkgen-debug generalcurl http://localhost:11434/api/tags)