skills/hqman_qveris
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Initial commit with translated description

Browse Source
This commit is contained in:
zlei9
2026-03-29 09:46:10 +08:00
commit f74991da27
6 changed files with 459 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

70
README.md Normal file
View File

@@ -0,0 +1,70 @@
# QVeris Skill for Claude Code
[中文文档](README.zh-CN.md) | English
A skill that enables Claude Code to dynamically search and execute tools via the QVeris API.
## Features
- **Tool Discovery**: Search for APIs by describing what you need
- **Tool Execution**: Execute any discovered tool with parameters
- **Wide Coverage**: Access weather, stocks, search, currency, and thousands more APIs
## Installation
### Prerequisites
This skill requires `uv`, a fast Python package manager. Install it first:
**macOS and Linux:**
```bash
curl -LsSf https://astral.sh/uv/install.sh | sh
```
**Windows:**
```powershell
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
```
For other installation methods, see the [official uv installation guide](https://docs.astral.sh/uv/getting-started/installation/).
### Install the Skill
1. Copy this folder to your Claude Code skills directory:
```bash
cp -r qveris ~/.claude/skills/
```
2. Set your API key:
```bash
export QVERIS_API_KEY="your-api-key-here"
```
Get your API key at https://qveris.ai
## Usage
Once installed, Claude Code will automatically use this skill when you ask questions about:
- Weather data
- Stock prices and market analysis
- Web searches
- Currency exchange rates
- And more...
### Manual Commands
```bash
# Search for tools
uv run scripts/qveris_tool.py search "stock price data"
# Execute a tool
uv run scripts/qveris_tool.py execute <tool_id> --search-id <id> --params '{"symbol": "AAPL"}'
```
## Author
[@hqmank](https://x.com/hqmank)
## License
MIT

70
README.zh-CN.md Normal file
View File

@@ -0,0 +1,70 @@
# QVeris Skill for Claude Code
中文文档 | [English](README.md)
这是一个让 Claude Code 能够通过 QVeris API 动态搜索和执行工具的技能。
## 功能特性
- **工具发现**：通过描述您的需求来搜索 API
- **工具执行**：使用参数执行任何已发现的工具
- **广泛覆盖**：访问天气、股票、搜索、货币以及数千种其他 API
## 安装
### 前置要求
此技能需要 `uv`，一个快速的 Python 包管理工具。请先安装它：
**macOS 和 Linux:**
```bash
curl -LsSf https://astral.sh/uv/install.sh | sh
```
**Windows:**
```powershell
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
```
更多安装方式，请查看 [uv 官方安装指南](https://docs.astral.sh/uv/getting-started/installation/)。
### 安装技能
1. 将此文件夹复制到您的 Claude Code 技能目录：
```bash
cp -r qveris ~/.claude/skills/
```
2. 设置您的 API 密钥：
```bash
export QVERIS_API_KEY="your-api-key-here"
```
在 https://qveris.ai 获取您的 API 密钥
## 使用方法
安装完成后，当您询问以下问题时，Claude Code 将自动使用此技能：
- 天气数据
- 股票价格和市场分析
- 网络搜索
- 货币汇率
- 更多...
### 手动命令
```bash
# 搜索工具
uv run scripts/qveris_tool.py search "stock price data"
# 执行工具
uv run scripts/qveris_tool.py execute <tool_id> --search-id <id> --params '{"symbol": "AAPL"}'
```
## 作者
[@hqmank](https://x.com/hqmank)
## 许可证
MIT

87
SKILL.md Normal file
View File

@@ -0,0 +1,87 @@
---
name: qveris
description: "通过QVeris API搜索和执行动态工具。在需要查找和调用外部API/工具时使用。"
triggers:
- pattern: "股票|stock|股价|股市"
description: "检测股票相关查询"
- pattern: "交易|trading|买卖|成交"
description: "检测交易相关查询"
- pattern: "分析|analysis|数据|指标|技术分析|基本面"
description: "检测分析相关查询"
- pattern: "市值|涨跌|收盘|开盘|市盈率|pe|pb"
description: "检测股票指标查询"
auto_invoke: true
examples:
- "帮我查一下特斯拉的股价"
- "分析一下苹果公司的财报数据"
- "查询今日A股涨停板"
- "获取比特币实时价格"
---
# QVeris Tool Search & Execution
QVeris provides dynamic tool discovery and execution - search for tools by capability, then execute them with parameters.
## Setup
Requires environment variable:
- `QVERIS_API_KEY` - Get from https://qveris.ai
## Quick Start
### Search for tools
```bash
uv run scripts/qveris_tool.py search "weather forecast API"
```
### Execute a tool
```bash
uv run scripts/qveris_tool.py execute openweathermap_current_weather --search-id <id> --params '{"city": "London", "units": "metric"}'
```
## Script Usage
```
scripts/qveris_tool.py <command> [options]
Commands:
search <query> Search for tools matching a capability description
execute <tool_id> Execute a specific tool with parameters
Options:
--limit N Max results for search (default: 5)
--search-id ID Search ID from previous search (required for execute)
--params JSON Tool parameters as JSON string
--max-size N Max response size in bytes (default: 20480)
--json Output raw JSON instead of formatted display
```
## Workflow
1. **Search**: Describe the capability needed (not specific parameters)
- Good: "weather forecast API"
- Bad: "get weather for London"
2. **Select**: Review tools by `success_rate` and `avg_execution_time`
3. **Execute**: Call tool with `tool_id`, `search_id`, and `parameters`
## Example Session
```bash
# Find weather tools
uv run scripts/qveris_tool.py search "current weather data"
# Execute with returned tool_id and search_id
uv run scripts/qveris_tool.py execute openweathermap_current_weather \
--search-id abc123 \
--params '{"city": "Tokyo", "units": "metric"}'
```
## Use Cases
- **Weather Data**: Get current weather, forecasts for any location
- **Stock Market**: Query stock prices, historical data, earnings calendars
- **Search**: Web search, news retrieval
- **Data APIs**: Currency exchange, geolocation, translations
- **And more**: QVeris aggregates thousands of API tools

6
_meta.json Normal file
View File

@@ -0,0 +1,6 @@
{
"ownerId": "kn7cpk0s04wpxzfp5m4eefgzj98024p8",
"slug": "qveris",
"version": "0.1.0",
"publishedAt": 1769858151112
}

8
pyproject.toml Normal file
View File

@@ -0,0 +1,8 @@
[project]
name = "qveris-skill"
version = "0.1.0"
description = "QVeris API tool search and execution skill for Claude Code"
requires-python = ">=3.10"
dependencies = [
"httpx>=0.25.0",
]

218
scripts/qveris_tool.py Normal file
View File

@@ -0,0 +1,218 @@
#!/usr/bin/env python3
# /// script
# requires-python = ">=3.10"
# dependencies = [
# "httpx",
# ]
# ///
"""
QVeris Tool Search & Execution CLI
Search for tools by capability and execute them via QVeris API.
Usage:
uv run qveris_tool.py search "weather forecast"
uv run qveris_tool.py execute <tool_id> --search-id <id> --params '{"city": "London"}'
"""
import argparse
import asyncio
import json
import os
import sys
import httpx
BASE_URL = "https://qveris.ai/api/v1"
def get_api_key() -> str:
"""Get QVeris API key from environment."""
key = os.environ.get("QVERIS_API_KEY")
if not key:
print("Error: QVERIS_API_KEY environment variable not set", file=sys.stderr)
print("Get your API key at https://qveris.ai", file=sys.stderr)
sys.exit(1)
return key
async def search_tools(query: str, limit: int = 5) -> dict:
"""Search for tools matching a capability description."""
api_key = get_api_key()
async with httpx.AsyncClient(timeout=30) as client:
response = await client.post(
f"{BASE_URL}/search",
headers={
"Authorization": f"Bearer {api_key}",
"Content-Type": "application/json",
},
json={"query": query, "limit": limit},
)
response.raise_for_status()
return response.json()
async def execute_tool(
tool_id: str,
search_id: str,
parameters: dict,
max_response_size: int = 20480,
) -> dict:
"""Execute a specific tool with parameters."""
api_key = get_api_key()
async with httpx.AsyncClient(timeout=60) as client:
response = await client.post(
f"{BASE_URL}/tools/execute",
params={"tool_id": tool_id},
headers={
"Authorization": f"Bearer {api_key}",
"Content-Type": "application/json",
},
json={
"search_id": search_id,
"parameters": parameters,
"max_response_size": max_response_size,
},
)
response.raise_for_status()
return response.json()
def display_search_results(result: dict) -> None:
"""Display search results in a formatted way."""
search_id = result.get("search_id", "N/A")
tools = result.get("results", [])
total = result.get("total", len(tools))
print(f"\nSearch ID: {search_id}")
print(f"Found {total} tools\n")
if not tools:
print("No tools found.")
return
for i, tool in enumerate(tools, 1):
tool_id = tool.get("tool_id", "N/A")
name = tool.get("name", "N/A")
desc = tool.get("description", "N/A")
# Stats
stats = tool.get("stats", {})
success_rate = stats.get("success_rate", "N/A")
avg_time = stats.get("avg_execution_time_ms", "N/A")
if isinstance(success_rate, (int, float)):
success_rate = f"{success_rate:.0%}"
if isinstance(avg_time, (int, float)):
avg_time = f"{avg_time:.1f}ms"
print(f"[{i}] {name}")
print(f" ID: {tool_id}")
print(f" {desc[:100]}{'...' if len(desc) > 100 else ''}")
print(f" Success: {success_rate} | Avg Time: {avg_time}")
# Show params
params = tool.get("params", [])
if params:
required = [p["name"] for p in params if p.get("required")]
optional = [p["name"] for p in params if not p.get("required")]
if required:
print(f" Required: {', '.join(required)}")
if optional:
print(f" Optional: {', '.join(optional[:5])}{'...' if len(optional) > 5 else ''}")
# Show example
examples = tool.get("examples", {})
sample = examples.get("sample_parameters")
if sample:
print(f" Example: {json.dumps(sample)}")
print()
def display_execution_result(result: dict) -> None:
"""Display tool execution result."""
success = result.get("success", False)
exec_time = result.get("elapsed_time_ms", "N/A")
cost = result.get("cost", 0)
status = "Success" if success else "Failed"
print(f"\n{status}")
print(f"Time: {exec_time}ms | Cost: {cost}")
if not success:
error = result.get("error_message", "Unknown error")
print(f"Error: {error}")
data = result.get("result", {})
if data:
print("\nResult:")
print(json.dumps(data, indent=2, ensure_ascii=False))
async def main():
parser = argparse.ArgumentParser(
description="QVeris Tool Search & Execution CLI",
formatter_class=argparse.RawDescriptionHelpFormatter,
epilog="""
Examples:
%(prog)s search "weather forecast API"
%(prog)s execute openweathermap_current_weather --search-id abc123 --params '{"city": "London"}'
""",
)
subparsers = parser.add_subparsers(dest="command", required=True)
# Search command
search_parser = subparsers.add_parser("search", help="Search for tools")
search_parser.add_argument("query", help="Capability description to search for")
search_parser.add_argument("--limit", type=int, default=5, help="Max results (default: 5)")
search_parser.add_argument("--json", action="store_true", help="Output raw JSON")
# Execute command
exec_parser = subparsers.add_parser("execute", help="Execute a tool")
exec_parser.add_argument("tool_id", help="Tool ID to execute")
exec_parser.add_argument("--search-id", required=True, help="Search ID from previous search")
exec_parser.add_argument("--params", default="{}", help="Tool parameters as JSON string")
exec_parser.add_argument("--max-size", type=int, default=20480, help="Max response size")
exec_parser.add_argument("--json", action="store_true", help="Output raw JSON")
args = parser.parse_args()
try:
if args.command == "search":
result = await search_tools(args.query, args.limit)
if args.json:
print(json.dumps(result, indent=2, ensure_ascii=False))
else:
display_search_results(result)
elif args.command == "execute":
params = json.loads(args.params)
result = await execute_tool(
args.tool_id,
args.search_id,
params,
args.max_size,
)
if args.json:
print(json.dumps(result, indent=2, ensure_ascii=False))
else:
display_execution_result(result)
except httpx.HTTPStatusError as e:
print(f"HTTP Error: {e.response.status_code}", file=sys.stderr)
print(e.response.text, file=sys.stderr)
sys.exit(1)
except json.JSONDecodeError as e:
print(f"Invalid JSON in --params: {e}", file=sys.stderr)
sys.exit(1)
except Exception as e:
print(f"Error: {e}", file=sys.stderr)
sys.exit(1)
if __name__ == "__main__":
asyncio.run(main())