nl-to-tools-mapper
This skill should be used when guiding the OpenAI agent to map natural language user input to appropriate MCP tools, handling phrases like "Add task" → add_task, "List pending" → list_tasks(status="pending"), tool chains, and extracting user email from JWT.
npx skills add majiayu000/claude-skill-registry --skill nl-to-tools-mapper-abdulahad139-hackathon2-phase4 --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# NL to Tools Mapper Skill This skill provides guidance for mapping natural language input to MCP tools and extracting user context from JWT. ## Purpose Guide the agent to map user input to tools: - "Add task" → add_task - "List pending" → list_tasks(status="pending") - Handle tool chains (list then delete) - Extract user email from JWT, respond in natural language ## When to Use Use this skill when: - Configuring agent instructions for tool mapping - Building natural language understanding for task commands - Implementing multi-step tool chains - Extracting user identity from authentication ## Capabilities - **NL Mapping**: Convert natural language to tool calls - **Intent Recognition**: Identify user intent (add, list, complete, delete, update) - **Parameter Extraction**: Pull relevant details from user input - **Tool Chaining**: Execute multiple tools in sequence - **User Context**: Extract and use JWT claims ## Agent System Prompt ```python SYSTEM_PROMPT = """You are a helpful task management assistant. You help users manage their tasks using the available tools. ## Your Capabilities 1. **Adding Tasks**: When user says "add task", "create task", "new task": - Use add_task tool
- Purpose
- When to Use
- Capabilities
- Agent System Prompt
- Intent Recognition Pattern
- Parameter Extraction
- Tool Chain Handling
- JWT User Extraction
- Complete Agent Loop
- Response Templates
- Verification Checklist
What does the nl-to-tools-mapper skill do?
This skill should be used when guiding the OpenAI agent to map natural language user input to appropriate MCP tools, handling phrases like "Add task" → add_task, "List pending" → list_tasks(status="pending"), tool chains, and extracting user email from JWT.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill nl-to-tools-mapper-abdulahad139-hackathon2-phase4 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.