drclaw/agent_hub/templates/earth-science/skills/seawater-sound-speed-calculation/SKILL.md
Calculate sound speed in seawater from practical salinity, temperature, and pressure using the Gibbs Seawater Oceanographic Toolbox.
npx skillsauth add qzzqzzb/drclaw seawater-sound-speed-calculationInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
import asyncio
import json
from mcp.client.streamable_http import streamablehttp_client
from mcp import ClientSession
class OceanClient:
"""OceanGSW-Tool MCP Client"""
def __init__(self, server_url: str, api_key: str):
self.server_url = server_url
self.api_key = api_key
self.session = None
async def connect(self):
"""Establish connection and initialize session"""
try:
self.transport = streamablehttp_client(
url=self.server_url,
headers={"SCP-HUB-API-KEY": self.api_key}
)
self.read, self.write, self.get_session_id = await self.transport.__aenter__()
self.session_ctx = ClientSession(self.read, self.write)
self.session = await self.session_ctx.__aenter__()
await self.session.initialize()
return True
except Exception as e:
print(f"✗ connect failure: {e}")
return False
async def disconnect(self):
"""Disconnect from server"""
try:
if self.session:
await self.session_ctx.__aexit__(None, None, None)
if hasattr(self, 'transport'):
await self.transport.__aexit__(None, None, None)
except Exception as e:
print(f"✗ disconnect error: {e}")
def parse_result(self, result):
"""Parse MCP tool call result"""
try:
if hasattr(result, 'content') and result.content:
content = result.content[0]
if hasattr(content, 'text'):
return json.loads(content.text)
return str(result)
except Exception as e:
return {"error": f"parse error: {e}", "raw": str(result)}
This workflow calculates sound speed in seawater using thermodynamic equations.
Workflow Steps:
Implementation:
## Initialize client
client = OceanClient(
"https://scp.intern-ai.org.cn/api/v1/mcp/34/OceanGSW-Tool",
"<your-api-key>"
)
if not await client.connect():
print("connection failed")
exit()
## Input: Seawater properties
input_params = {
'SP': [35.0, 5.0], # Practical salinity (PSU)
't': [15.0, 10.0], # In-situ temperature (°C)
'p': [1000.0, 1000.0], # Pressure (dbar)
'lon': [120.0, 165.0], # Longitude (degrees East)
'lat': [30.0, 45.0] # Latitude (degrees North)
}
## Step 1: Calculate absolute salinity (SA)
result = await client.session.call_tool(
"gsw_example_absolute_salinity",
arguments={
"SP": input_params['SP'],
'p': input_params['p'],
'lon': input_params['lon'],
'lat': input_params['lat']
}
)
result_data = client.parse_result(result)
SA_result = result_data["st"]
print("Absolute Salinity:")
for i, sa in enumerate(SA_result):
print(f" SP={input_params['SP'][i]} → SA={sa:.4f} g/kg")
## Step 2: Calculate conservative temperature (CT)
result = await client.session.call_tool(
"gsw_example_conservative_temperature",
arguments={
"SA": SA_result,
't': input_params['t'],
'p': input_params['p']
}
)
result_data = client.parse_result(result)
CT_result = result_data["st"]
print("\nConservative Temperature:")
for i, ct in enumerate(CT_result):
print(f" t={input_params['t'][i]}°C → CT={ct:.4f}°C")
## Step 3: Calculate sound speed
result = await client.session.call_tool(
"gsw_example_sound_speed",
arguments={
"SA": SA_result,
'CT': CT_result,
'p': input_params['p']
}
)
result_data = client.parse_result(result)
sound_speed_result = result_data["st"]["sound_speed"]
print("\nSound Speed Results:")
for i, speed in enumerate(sound_speed_result):
print(f"{i+1}. SA={SA_result[i]:.2f} g/kg, CT={CT_result[i]:.2f}°C, p={input_params['p'][i]} dbar")
print(f" Sound speed: {speed:.2f} m/s\n")
await client.disconnect()
OceanGSW-Tool Server:
gsw_example_absolute_salinity: Calculate absolute salinity
SP (list): Practical salinity (PSU)p (list): Pressure (dbar)lon (list): Longitude (degrees East)lat (list): Latitude (degrees North)gsw_example_conservative_temperature: Calculate conservative temperature
SA (list): Absolute salinity (g/kg)t (list): In-situ temperature (°C)p (list): Pressure (dbar)gsw_example_sound_speed: Calculate sound speed
SA (list): Absolute salinity (g/kg)CT (list): Conservative temperature (°C)p (list): Pressure (dbar)Input:
SP: Practical salinity (0-42 PSU typical range)t: In-situ temperature (-2 to 40°C)p: Sea pressure (0-11000 dbar)lon: Longitude (-180 to 180°E)lat: Latitude (-90 to 90°N)Output:
content-media
当用户明确要求“写/生成 NSFC 预算说明书”“写预算说明”“生成 budget.tex / budget.pdf”“写国自然预算 justification”时使用。基于用户标书正文或补充材料,输出一份可提交的预算说明书 LaTeX 项目并渲染 `budget.pdf`。若用户未指定工作目录,必须暂停并先要求其指定。⚠️ 不适用:用户只是想了解预算原则;用户仅要预算表数字而不写说明书;或用户是 2026 青年 A/B/C 默认包干制且无需预算说明书的场景。
tools
当用户明确要求"写/润色 NSFC 标书摘要""生成中文摘要和英文摘要""把中文摘要翻译成英文摘要"时使用。输出中文、英文两个版本(英文必须是中文的忠实翻译版),同时输出标题建议(1个推荐标题+5个候选标题及理由)。中文摘要默认≤400字符,英文摘要默认≤4000字符。输出方式:将结果写入工作目录下的 `NSFC-ABSTRACTS.md`。⚠️ 不适用:用户只想翻译一段与标书无关的通用文本(应直接翻译);用户只想写立项依据/研究内容/研究基础正文(应使用对应 nsfc 系列 skill)。
documentation
当用户明确要求"更新项目指南""同步指南""沉淀洞见到指南"时使用。将对话中新产生的可复用写作洞见实时沉淀到项目指南文件,保持术语口径一致、结构稳定、可检验与可复现。调用时必须指定指南文件路径。
content-media
当用户明确要求"从文件/图片/网页/描述中提取综述主题"或"生成主题+关键词+核心问题结构化输出"时使用。支持文件(PDF/Word/Markdown/Tex)、文件夹、图片、自然语言描述、网页 URL 等多种输入源,自动识别输入类型并提取内容,生成可直接用于 systematic-literature-review 及其他文献综述技能的结构化输出。