devtu-create-tool
Build, validate, and test new scientific tools for the ToolUniverse framework.
Install
mkdir -p .claude/skills/devtu-create-tool && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/3409" && unzip -o skill.zip -d .claude/skills/devtu-create-tool && rm skill.zipInstalls to .claude/skills/devtu-create-tool
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Create new scientific tools for ToolUniverse framework with proper structure, validation, and testing. Use when users need to add tools to ToolUniverse, implement new API integrations, create tool wrappers for scientific databases/services, expand ToolUniverse capabilities, or follow ToolUniverse contribution guidelines. Supports creating tool classes, JSON configurations, validation, error handling, and test examples.Key capabilities
- →Register new tool classes with ToolUniverse
- →Generate JSON tool definitions for API wrappers
- →Implement validation logic for tool parameters
- →Create test examples for tool verification
- →Configure tool registration in default_config.py
How it works
The skill guides the creation of a Python class using the @register_tool decorator and a corresponding JSON file to define wrappers, ensuring all registration steps are met.
Inputs & outputs
When to use devtu-create-tool
- →Create new scientific tools
- →Implement API wrappers for databases
- →Validate tool structure and logic
About devtu-create-tool
Provides structure and best practices for creating tool wrappers, managing API integrations, and implementing scientific database connectivity within ToolUniverse.
Create new scientific tools for ToolUniverse framework with proper structure, validation, and testing. Use when users need to add tools to ToolUniverse, implement new API integrations, create tool wrappers for scientific databases/services, expand ToolUniverse capabilities, or follow ToolUniverse contribution guidelines. Supports creating tool classes, JSON configurations, validation, error handling, and test examples.
When not to use it
- →Creating tools that do not follow the multi-operation pattern
- →Adding tools without corresponding JSON definitions
Prerequisites
Limitations
- →Tool names must be 55 characters or fewer
- →Requires return_schema to use oneOf for success and error states
How it compares
It enforces strict structural and validation patterns specific to the ToolUniverse framework rather than generic tool creation.
Compared to similar skills
devtu-create-tool side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| devtu-create-tool (this skill) | 1 | 8mo | Caution | Intermediate |
| mcp-builder | 136 | 7mo | Review | Advanced |
| ai-agents-architect | 5 | 10mo | No flags | Advanced |
| llm-app-patterns | 3 | 10mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by mims-harvard
View all by mims-harvard →You might also like
mcp-builder
anthropics
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
ai-agents-architect
davila7
Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous agent, tool use, function calling.
llm-app-patterns
davila7
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
agentica-infrastructure
parcadei
Reference guide for Agentica multi-agent infrastructure APIs
mcp-builder
keepsty
MCP 服务器构建方法论 — 系统化构建生产级 MCP 工具,让 AI 助手连接外部能力
llm-council
am-will
Orchestrate a configurable, multi-member CLI planning council (Codex, Claude Code, Gemini, OpenCode, or custom) to produce independent implementation plans, anonymize and randomize them, then judge and merge into one final plan. Use when you need a robust, bias-resistant planning workflow, structured JSON outputs, retries, and failure handling across multiple CLI agents.