skills-4
от hubentu
DevOps & CloudКратко
How to use the coala-client CLI for chat with LLMs, MCP servers, and skills.
Описание
Что делает этот навык
coala-client is a CLI tool for chatting with OpenAI-compatible LLMs and connecting to MCP (Model Context Protocol) servers. It supports importing CWL toolsets as MCP servers, loading skills into context, and optionally running shell commands in a sandbox.
Combines LLM chat, MCP server management, and skill loading in a single CLI without requiring separate tooling for each.
Когда его использовать
- Chat with a local Ollama model without an API key
- Import a CWL toolset and call its tools from the command line
- Load a skill file into chat context mid-session
- Switch between OpenAI, Gemini, and Ollama providers in one tool
- Run a single prompt against MCP tools with coala ask
Пример сценария
User asks: how do I call an MCP tool for gene variant lookup
- 1
Run coala init to create config files
- 2
Import the gene-variant CWL toolset with coala mcp-import
- 3
Run coala mcp-list gene-variant to inspect available tools
- 4
Call the tool directly with coala mcp-call gene-variant.ncbi_datasets_gene --args '{"data":[{"gene":"TP53","taxon":"human"}'
Tool returns gene data for TP53 in human without starting a full chat session
Требования
- OPENAI_API_KEY environment variable (for OpenAI provider)
- GEMINI_API_KEY environment variable (for Gemini provider)
Установка
clawhub install hubentu/skills-4Выполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.