做什么
为具有适当结构、验证和测试的 Tool University 框架创建新的科学工具
技能库 智客分类:Agent 工作流 devtu-create-tool
为TolleUniverse框架创建具有适当结构、验证和测试的新科学工具。 当用户需要向"工具Universe"添加工具时使用,实施新的API集成,为科学数据库/服务创建工具包,扩展"工具Universe"能力,或遵循"工具Universe"贡献指南. 支持创建工具类,JSON配置,验证,错误处理,以及测试示例.
官方网址:skills.sh
先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。
为具有适当结构、验证和测试的 Tool University 框架创建新的科学工具
用户需要向"工具Universe"添加工具,实施新的API集成,为科学数据库/服务创建工具包,扩展"工具Universe"能力,或遵循"工具Universe"贡献指南. 支持创建工具类, JSON 配置, 校验, 错误
按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:ToolUniverse Tool Creator、Top 7 Mistakes (90% of Failures)、Two-Stage Architecture、Three-Step Registration、Implementation Guide、Files to Create。 其中含规范建议的小节:分步指令。
文件分析:除 SKILL.md 外,正文引用了 references/testing-guide.md、scripts/test_new_tools.py、references/advanced-patterns.md、references/implementation-guide.md、references/tool-improvement-checklist.md,属于带资源的技能包,这些文件按需再读。
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.
ToolUniverse Tool CreatorTop 7 Mistakes (90% of Failures)Two-Stage ArchitectureThree-Step RegistrationImplementation GuideFiles to CreatePython Tool Class (Multi-Operation Pattern)JSON ConfigurationCritical RequirementsParameter DesignMutually Exclusive Parameters (CRITICAL — #1 issue)API Key Configuration
来源分类:skills.sh agent-skill
namedevtu-create-tooldescriptionreferences/testing-guide.mdscripts/test_new_tools.pyreferences/advanced-patterns.mdreferences/implementation-guide.mdreferences/tool-improvement-checklist.md以下路径提取自原文;文件是否齐全请以来源仓库中的完整目录为准。
具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗
先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。
该技能引用了附属文件,请从来源获取完整目录;仅复制 SKILL.md 可能缺少依赖。
复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。
把 Agent Skill「devtu-create-tool」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-0cda88f5291ec8ee-Devtu-%E5%88%9B%E5%BB%BA%E5%B7%A5%E5%85%B7.html 请存为 .cursor/skills/devtu-create-tool/SKILL.md 或 .claude/skills/devtu-create-tool/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。 该技能还带 scripts/、references/、assets/ 等文件,请从 https://github.com/mims-harvard/tooluniverse 取完整目录,不要只建一个 SKILL.md。
需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。
npx skills add 'https://github.com/mims-harvard/tooluniverse' --list
npx skills add 'https://github.com/mims-harvard/tooluniverse' --skill 'devtu-create-tool'
CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。
Create new scientific tools following established patterns.
default_config.py Entry — tools silently won't loadtest_new_tools.py — misses schema/API issuesStage 1: Tool Class Stage 2: Wrappers (Auto-Generated)
@register_tool("MyTool") MyAPI_list_items()
class MyTool(BaseTool): MyAPI_search()
def run(arguments): MyAPI_get_details()
One class handles multiple operations. JSON defines individual wrappers. Need BOTH.
Step 1: Class registration via @register_tool("MyAPITool")
Step 2 (MOST COMMONLY MISSED): Config registration in default_config.py:
TOOLS_CONFIGS = {
"my_category": os.path.join(current_dir, "data", "my_category_tools.json"),
}
Step 3: Automatic wrapper generation on tu.load_tools()
src/tooluniverse/my_api_tool.py — implementationsrc/tooluniverse/data/my_api_tools.json — tool definitionstests/tools/test_my_api_tool.py — testsfrom typing import Dict, Any
from tooluniverse.tool import BaseTool
from tooluniverse.tool_utils import register_tool
import requests
@register_tool("MyAPITool")
class MyAPITool(BaseTool):
BASE_URL = "https://api.example.com/v1"
def __init__(self, tool_config):
super().__init__(tool_config)
self.parameter = tool_config.get("parameter", {})
self.required = self.parameter.get("required", [])
def run(self, arguments: Dict[str, Any]) -> Dict[str, Any]:
operation = arguments.get("operation")
if not operation:
return {"status": "error", "error": "Missing: operation"}
if operation == "search":
return self._search(arguments)
return {"status": "error", "error": f"Unknown: {operation}"}
def _search(self, arguments: Dict[str, Any]) -> Dict[str, Any]:
query = arguments.get("query")
if not query:
return {"status": "error", "error": "Missing: query"}
try:
response = requests.get(
f"{self.BASE_URL}/search",
params={"q": query}, timeout=30
)
response.raise_for_status()
data = response.json()
return {"status": "success", "data": data.get("results", [])}
except requests.exceptions.Timeout:
return {"status": "error", "error": "Timeout after 30s"}
except requests.exceptions.HTTPError as e:
return {"status": "error", "error": f"HTTP {e.response.status_code}"}
except Exception as e:
return {"status": "error", "error": str(e)}
[
{
"name": "MyAPI_search",
"class": "MyAPITool",
"description": "Search items. Returns array of results. Supports Boolean operators. Example: 'protein AND membrane'.",
"parameter": {
"type": "object",
"required": ["operation", "query"],
"properties": {
"operation": {"const": "search", "description": "Operation (fixed)"},
"query": {"type": "string", "description": "Search term"},
"limit": {"type": ["integer", "null"], "description": "Max results (1-100)"}
}
},
"return_schema": {
"oneOf": [
{"type": "object", "properties": {"data": {"type": "array"}}},
{"type": "object", "properties": {"error": {"type": "string"}}, "required": ["error"]}
]
},
"test_examples": [{"operation": "search", "query": "protein", "limit": 10}]
}
]
{API}_{action}_{target} template{"status": "error", "error": "..."}{"status": "success|error", "data": {...}}When tool accepts EITHER id OR name, BOTH must be nullable:
{
"id": {"type": ["integer", "null"], "description": "Numeric ID"},
"name": {"type": ["string", "null"], "description": "Name (alternative to id)"}
}
Without "null", validation fails when user provides only one parameter.
Common cases: id OR name, gene_id OR gene_symbol, any optional filters.
Optional keys (tool works without, better with):
{"optional_api_keys": ["NCBI_API_KEY"]}
self.api_key = os.environ.get("NCBI_API_KEY", "") # Read from env only
Required keys (tool won't work without):
{"required_api_keys": ["NVIDIA_API_KEY"]}
Rules: Never add api_key as tool parameter for optional keys. Use env vars only.
Full guide: references/testing-guide.md
run(), check responsetu.tools.YourTool_op1(...), check registrationpython scripts/test_new_tools.py your_tool -v → 0 failures# Check all 3 registration steps
python3 -c "
import sys; sys.path.insert(0, 'src')
from tooluniverse.tool_registry import get_tool_registry
import tooluniverse.your_tool_module
assert 'YourToolClass' in get_tool_registry(), 'Step 1 FAILED'
from tooluniverse.default_config import TOOLS_CONFIGS
assert 'your_category' in TOOLS_CONFIGS, 'Step 2 FAILED'
from tooluniverse import ToolUniverse
tu = ToolUniverse(); tu.load_tools()
assert hasattr(tu.tools, 'YourCategory_op1'), 'Step 3 FAILED'
print('All 3 steps verified!')
"
python3 -m json.tool src/tooluniverse/data/your_tools.json # Validate JSON
python3 -m py_compile src/tooluniverse/your_tool.py # Check syntax
grep "your_category" src/tooluniverse/default_config.py # Verify config
python scripts/test_new_tools.py your_tool -v # MANDATORY test
Agent 工作流
创造有效技能指南。 当用户想创造出新的技能(或更新现有的技能),以专业知识,工作流程,或工具集成来扩展克洛德的能力时,应该使用这种技能.
Agent 工作流
使用ClawdHub CLI搜索,安装,更新并发布从taladhub.com的代理技能. 需要获取苍蝇上的新技能时使用,将安装的技能同步到最新版本或特定版本,或者发布 npm-instainddhub CLI 的新/更新的技能文件夹.
Agent 工作流
管弦乐团多代理团队,任务设定周期,交接协议,审查工作流程. 使用时间: (1)建立2+特派员队伍,具有不同专业,(2)确定任务路线和生命周期(收录框_ spec_建设_审查_完成),(3)在特派员之间制定交接协议,(4)建立审查和质量关口,(5)管理特派员之间的交流和文物共享.
Agent 工作流
Spec-first,TDD,子代理驱动的软件开发工作流程. 当:(1)构建任何新功能或应用——触发脑暴_计划_子代理执行回路,(2)调试出一个bug或测试失败——触发系统性的根起过程,(3)用户说"让我们构建","帮助我计划","我想添加X",或"这个被打破",(4)完成一个功…