scnet-chat

scnet-chat is a skill for Claude Code, Codex from onescience-ai/OneSkills. It costs 105 tokens per session (3,956 once invoked), scanned A, original, MIT.

A natural-language interface for SCNet, a high-performance computing platform used to run scientific or technical jobs on shared clusters. It can also manage files, account details, regions, and queues.

In plain words
What is it for?
Use it to query or manage running and historical jobs, inspect queues, upload or download files, check account balances and usage, and switch regions.
Why use it?
It avoids requiring users to remember separate commands for checking jobs, moving files, viewing resources, or changing computing regions.

Skill for Claude CodeCodex

Part of the oneskills plugin — 18 skills shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/onescience-ai/oneskills/scnet-chat
Any agent
npx skills add onescience-ai/OneSkills --skill scnet-chat
Clone the repo
git clone --depth 1 https://github.com/onescience-ai/OneSkills

Made for: Claude Code, Codex.

Or install oneskills, the plugin that ships this one along with the rest of its 18 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for scnet-chat

README.md
[![agentmods](https://agentmods.dev/badge/skills/onescience-ai/oneskills/scnet-chat.svg)](https://agentmods.dev/skills/onescience-ai/oneskills/scnet-chat)
Your own site
<a href="https://agentmods.dev/skills/onescience-ai/oneskills/scnet-chat"><img src="https://agentmods.dev/badge/skills/onescience-ai/oneskills/scnet-chat.svg" alt="Measured on agentmods" height="20"></a>
Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,956 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00105 $0.03956
Opus 5 $0.00053 $0.01978
Sonnet 5 $0.00021 $0.00791
Haiku 4.5 $0.00011 $0.00396

Measured 5d ago against content hash b039333fc295, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scnet-chat scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

The scan reads SKILL.md. This mod also ships 17 executable files (assets/run_integration_tests.py, assets/test_intent_unit.py, scripts/cache.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/scnet-chat/SKILL.md · 321 lines

How it starts

The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SCNet Chat 技能

通过自然语言交互管理 SCNet 超算平台资源。

When to Run

  • 用户提到 SCNet、超算、作业管理、文件管理等关键词
  • 用户需要查询作业(未指定实时/历史时同时查询两者)、提交作业、删除作业
  • 用户需要上传/下载/管理远程文件
  • 用户需要查看账户信息、余额、机时、作业统计(统计实时作业)
  • 用户需要切换计算区域(昆山、山东、西安等)

Workflow

  1. 确定用户意图:识别用户是想查询作业、管理文件、查看账户信息还是切换区域
  2. 检查配置:优先检查项目根目录 onescience.json.runtime.scnet 是否完整;缺失时应先调用 onescience-runsite 与用户交互补齐,不能依赖 ~/.scnet-chat.env 直接提交任务
  3. 执行命令(根据操作系统选择正确的启动脚本):
    • macOS/Linux: ./scripts/run "自然语言命令"
    • Windows: ./scripts/run.bat "自然语言命令"
  4. 返回结果:将执行结果格式化后返回给用户

说明scripts/runscripts/run.bat 是跨平台包装脚本,会自动检测并使用正确的 Python 解释器(macOS/Linux 优先使用 python3,Windows 优先使用 python)。

常用命令示例

macOS/Linux:

# 查询作业
# 作业管理 - 查询(基础)
# ⚠️ 注意:实时作业列表和历史作业列表是全区域聚合查询,一次调用返回所有区域的作业
# 💡 重要:如果未明确指定"实时"或"历史",默认同时查询实时作业和历史作业
./scripts/run "查询作业"                      # 未明确指定 → 同时查询实时作业+历史作业
./scripts/run "查看运行中的作业"              # 明确指定实时 → 仅查询实时作业
./scripts/run "实时作业"                      # 明确指定实时 → 仅查询实时作业
./scripts/run "历史作业"                      # 明确指定历史 → 仅查询历史作业
./scripts/run "作业详情 12345"                # 查询特定作业详情(需指定区域)

# 作业管理 - 查询(高级筛选)
./scripts/run "查询作业 第2页 每页20条"
./scripts/run "查询队列 debug 的作业 所有字段"
./scripts/run "查询用户 zhangsan 的作业"
./scripts/run "查询组作业"
./scripts/run "查询区域ID 12345 的作业"       # 筛选特定区域的作业

# 作业管理 - 历史作业查询(高级用法)
./scripts/run "历史作业 开始时间 2024-01-01 00:00:00 结束时间 2024-01-31 23:59:59"
./scripts/run "历史作业 最近7天"
./scripts/run "查询最近三天的历史作业"                    # 中文数字支持
./scripts/run "查询从2026-04-01到2026-04-03的历史作业"   # 简写日期范围
./scripts/run "查询历史作业,每页5条,显示第二页"         # 中文页码
./scripts/run "查询历史作业,状态为失败"                  # 中文状态筛选
./scripts/run "查询历史作业,队列为comp,每页10条"

# 作业管理 - 实时作业查询(高级用法)
# 💡 含"历史作业"关键词 → 仅查历史;含"实时"/"运行中" → 仅查实时;否则同时查两者
./scripts/run "查询作业 开始时间 2024-01-01 00:00:00 结束时间 2024-01-31 23:59:59"
./scripts/run "查询最近3天的作业"
./scripts/run "查询运行中的作业,每页5条"
./scripts/run "查询作业,状态为排队,显示第2页"

# 提交作业
./scripts/run "提交作业 sleep 900" # 简单命令
./scripts/run "提交作业 sleep 900 --queue comp --ppn 2 --wall-time 12:00:00 --job-name production-run1" # 位置命令 + 显式参数格式(推荐)

#提交作业帮助
./scripts/run "如何提交作业"
./scripts/run "提交作业帮助"
./scripts/run "作业有哪些参数"

# 删除作业
./scripts/run "删除作业 12345"

# 作业管理 - 队列和集群
./scripts/run "查询队列"
./scripts/run "集群信息"

# 文件管理 - 列表和上传下载
./scripts/run "文件列表"
./scripts/run "查看文件 /public/home/user"
./scripts/run "上传文件 ./data 到 /public/home/user/"
./scripts/run "下载文件 /public/home/user/data 到 ./"

# 文件管理 - 创建和删除
./scripts/run "创建目录 /public/home/user/workspace"
./scripts/run "创建文件 /public/home/user/data"
./scripts/run "删除文件 /public/home/user/data"

# 文件管理 - 复制移动和重命名
./scripts/run "复制文件 /src/data 到 /dst/"
./scripts/run "移动文件 /src/data 到 /dst/"
./scripts/run "重命名 /old/data 为 data1"
./scripts/run "检查文件 /public/home/user/file"

# 账户信息
./scripts/run "查询余额"
./scripts/run "查询用户"
./scripts/run "作业统计"                      # 按作业状态统计实时作业数量(非历史作业)
./scripts/run "机时"

# 区域切换
./scripts/run "切换到山东"
./scripts/run "切换到西安"

# 缓存管理
./scripts/run "刷新缓存"

# 帮助
./scripts/run "帮助"

Read the full file on GitHub · 321 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 321 lines · 105 tokens per session scan A b039333fc295

Subscribe to this mod's changes

scnet-chat is a skill published in the GitHub repository onescience-ai/OneSkills (20 stars, last pushed 22d ago), licensed MIT. It adds 105 tokens to every session and 3,956 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

results-analysis

This skill should be used when the user asks to "analyze experimental results", "run strict statistical analysis", "compare model performance", "generate scientific figures", "check significance", "do ablation analysis", or mentions interpreting experiment data with rigorous statistics and visualization. It focuses on…

Galaxy-Dawn/claude-scholar · 68 tokens

daily-paper-generator

Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.

Galaxy-Dawn/claude-scholar · 47 tokens

nsfc-budget

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。.

huangwb8/ChineseResearchLaTeX · 138 tokens

paper-select-journal

当用户明确要求“推荐投稿期刊”“帮我的论文选 SCI 杂志”“这篇 manuscript 适合投哪些 journal”“期刊匹配/选刊/投稿建议”时必须使用。适用于用户提供全文、摘要、Markdown、LaTeX、PDF、Word 或混合材料的场景;本 skill 会基于 manuscript 与用户偏好,先用内置 2023IF.xlsx 做最小硬过滤生成候选池,再由宿主模型自主规划 Set1/Set2/Set3,并联网核验 scope / 质量 / 近 3 个月 PubMed 论文,最后输出 1 份按推荐度排序的 Markdown 选刊报告。⚠️…

huangwb8/ChineseResearchLaTeX · 194 tokens

research-literature-radar

发现、筛选并长期归档重要研究论文;当用户要求按主题寻找经典、rising star、社区精选、热点或顶会/顶刊论文时使用。采用分层发现策略,调用 research-literature-search 完成其中的关键词/数据库检索,再由本 skill 负责多渠道汇总、idea-level 价值判断、论文类型分类、跨轮次跟踪和论文库归档。.

huangwb8/ChineseResearchLaTeX · 96 tokens

paper-search

Search, download, and read academic papers from 20+ sources (arXiv, PubMed, Semantic Scholar, CrossRef, etc). Use when the user asks to find papers, search for research, look up academic literature, download a paper PDF, or extract text from a paper.

openags/paper-search-mcp · 62 tokens