AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
MCP verified MIT Self-run

OneSkills

mcp-onescience-ai-oneskills · by onescience-ai

A skill library for AI-native scientific research. Reusable skills for workflow orchestration, coding, runtime submission, and environment setup. Works with Claude Code, Codex CLI, Trae.

↗ Repository
— No reviews yet
0 installs
38 views
0.0% view→install

Install

$ agentstack add mcp-onescience-ai-oneskills

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/mcp-onescience-ai-oneskills)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 2mo ago

Declared compatibility

Claude CodeClaude DesktopCursorWindsurf

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of OneSkills? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

OneSkills

面向 AI4S 的科研智能体技能库

[安装 / Installation](./install/README.md)

[中文](./README.md) | [English](./README_EN.md)

OneSkills 是面向 AI4S 的科研智能体技能库，聚焦科研开发、实验运行与环境交付等关键环节，提供可复用、可组合、可落地的任务执行能力。

支持的智能体

说明：需要先拉取 skills 仓库

git clone https://gitee.com/onescience-ai/oneskills.git
cd oneskills

| Agent | 使用方式 | 备注 | | :---------: | :----------------------------------------------------------: | :----------------------------------------------------------: | | Claude Code | python3 install/installoneskills.py --agent claude --project /your/project | 1. 若需同时安装运行资产，可增加 --profile runtime 参数。更多参数见 [install/README.md](install/README.md)。2. 安装后会在 /your/project 文件夹中生成 .claude 隐藏文件夹，并将 OneSkills 相应技能与所需的其它文件按 Claude 能识别的方式存储。 | | Codex | python3 install/installoneskills.py --agent codex --project /your/project | 1. 安装后会在 /your/project 文件夹中生成 .Codex 隐藏文件夹，并将 OneSkills 相应技能与所需的其它文件按 Codex 能识别的方式存储。 | | Trae | python3 install/installoneskills.py --agent trae --project /your/project | 1. 安装后会在 /your/project 文件夹中生成 .trae 隐藏文件夹，并将 OneSkills 相应技能与所需的其它文件按 Trae 能识别的方式存储。 | | OpencCode | python3 install/installoneskills.py --agent opencode --project /your/project | 1. 安装后会在 /your/project 文件夹中生成 .opencode 隐藏文件夹，并将 OneSkills 相应技能与所需的其它文件按 opencode 能识别的方式存储。 |

功能介绍

  • 任务理解与编排：任务路由准确率达 100%，角色协作执行准确率达 90%，编排协调准确率达 100%
  • 数据任务：数据类任务代码生成通过率达 70%
  • 模型任务：覆盖FourCastNet、Pangu-Weather等气象领域主流模型，模型类任务代码生成通过率达87.5%
  • 论文复现任务：能够完成任务拆解、代码实现与验证，覆盖数据接入、模型改造与配置补全等关键环节
  • 工程任务：科研代码重构、项目结构整理中，能够完成代码生成、配置修复与入口脚本补齐
  • 运行任务：能够完成远程环境识别、依赖安装、任务提交与故障诊断
  • 评测任务：能够完成实验验证路径梳理、测试方案选择与结果检查

使用场景

  • 复现论文：使用OneScience技能复现https://arxiv.org/abs/2406.01465论文
  • 接入数据集：使用OneSkills技能接入OneScience平台的ERA5数据集并生成对应的Earth DataPipe
  • 改造或补全一个模型：使用OneScience实现任务,结合FourCastNet的全局感受野优势和Pangu-Weather的局地精细建模能力，构建一个混合天气预报模型
  • 在远程 GPU / DCU 环境安装并运行OneScience：使用OneScience技能在远程DCU环境安装运行依赖并启动训练任务
  • 提交科研任务到远端环境并排查运行失败原因：使用OneScience技能把这个训练任务提交到远端GPU集群并诊断运行失败原因
  • 判断一个科研需求应该如何拆解、执行、验证：使用OneScience技能帮我拆解这个科研需求并规划执行与验证路径

贡献说明

本仓库公开通用技能、公开参考资料与用户可用文档。如果你想了解如何在本仓库中扩展自定义技能，优先阅读：[docs/open-source/customskillcontribution.md](customskillcontribution.md)

项目治理

  • [LICENSE](../../LICENSE)
  • [CONTRIBUTING.md](../../CONTRIBUTING.md)
  • [SECURITY.md](../../SECURITY.md)

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Integrations