What makes SJTU SLURM Skill notable?

1K downloads. Trust evidence available

How should SJTU SLURM Skill be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

SJTU SLURM Skill

Log in to the SJTU HPC platform (also known as "交我算") as the user to perform job queries, submissions, cancellations, and data management. Use this skill whe...

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.0k

Updated

Oct 11, 2026

Version

0.2.3

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1K downloadsadoption · observed Oct 11, 2026
Latest release: 0.2.3release · observed Apr 28, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17a7tzmmkbwha68wry3vfwq8h851s1r:sjtu-slurm-skill

Install using `clawhub skill install s17a7tzmmkbwha68wry3vfwq8h851s1r:sjtu-slurm-skill` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/taleintervenor/sjtu-slurm-skill before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-taleintervenor-sjtu-slurm-skill/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

128,149 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: sjtu-slurm-skill
description: Log in to the SJTU HPC platform (also known as "交我算") as the user to perform job queries, submissions, cancellations, and data management. Use this skill when the user requests operations related to HPC or "交我算".
metadata:
{
"openclaw":
{
"emoji": "🦞",
"homepage": https://github.com/SJTU-HPC/SJTU-SLURM-Skill,
}
}
---

# sjtu-slurm-skill

## Overview

Use this skill to log in to the SJTU HPC (交我算) platform as the user, acting on their behalf to perform personal job queries, submissions, cancellations, and data management operations.

General Principles:

- **Risk-aware operations**: Deleting user's data and interrupting running jobs are risky operations. Before performing any risky operation, always confirm with the user that they clearly understand the impact of the operation and agree to its execution.
- private credentials: All user's credential files (like SSH key, certificate, API token, etc...) should be stored in the `credentials` directory under workspace (e.g., `~/.openclaw/workspace/default/credentials`). **Do Not store user's plain text password or contain it in your talk messages**.

## Quick Start

1. Ensure HPC API token file is available in the workspace, which should be stored in `credentials` directory. If not, request a new token.
2. For each user request, analyze whether you need to log in to an HPC entry node to perform the operation remotely. You can ask more questions to clarify any ambiguous parts of the request.
- If user wants to know its storage quota usage or update its account (like password, binding Email/jAccount, preferred contact method), then you can meet the requirement directly by calling HPC API with the token.
- if user is talking about job or its data, then you have to select an entry node to do remote operation. In this case, take the following steps.
- if user want to get a passwordless certificate for SSH login, refer to [certificates section](#ssh-keys-and-certificates).
3. Ensure SSH keys and certificates are available in the workspace, which should be stored in `credentials` directory. If not, request a new SSH certificate for the user. Remind the user that requesting a certificate will trigger two-factor authentication.
4. For each user request need remote operation, identify the node group/partition the user is interested in and the operation type to select the correct entry node.
5. Use the SSH certificate to connect to the corresponding entry node based on the cluster and operation type, execute the user's requested operations on it.

## Ensure Token Available

Before calling any HPC API, ensure there is a valid token in the credentials directory. Go through the following steps:

1. Check whether `hpc_token` file exists in the `credentials` directory under workspace. If it exists, goto step 2, otherwise goto step 3.
2. Try to refresh the token with `refresh_token.py --workspace "path_to_workspace"`. If success, then

README.md

# SJTU slurm skill

This is the skill to interact with SJTU HPC platform on behalf of a user.

## Skill ability

- Manage your HPC account information like jAccount/Email binding, password update, prefer contact method setting, etc.
- Query job status, partition queue, platform information, storage usage, etc.
- Submit/manage job according to your instructions.
- Help you to migrate data between hot/cold storages.

In a sense, it can help to do all the things you can through SSH login to platform's entry node.

## Notes on using this skill

This skill will request API token and SSH key/certificate for you, and store them in workspace. **Make sure your claw is in safe environment. Never use this skill on a shared machine.**

To fullfill your instructions, claw agent may need to call lots of command, channel clients (like Feishu, weixin, QQ, etc.) cannot display the background command call process in real time. You may have to wait for a while to see the final reply, be patient if your LLM models service is not fast enough.

## Install skill

This skill has been published on [clawhub](https://clawhub.ai/taleintervenor/sjtu-slurm-skill) , so you can simplily ask your claw to install sjtu-slurm-skill skill itself.

Or if you prefer to maintain skills manually:

```
openclaw skills install sjtu-slurm-skill
openclaw skills update sjtu-slurm-skill
```

## Repository

This project is hosted on GitHub at https://github.com/SJTU-HPC/SJTU-SLURM-Skill. If you have any suggestions for improvement, feel free to open an issue or submit a pull request.

_meta.json

{
  "ownerId": "kn7fzph2hetmda1vp99dwh114s850q1p",
  "slug": "sjtu-slurm-skill",
  "version": "0.2.3",
  "publishedAt": 1777361538183
}

skill-card.md

## Description:

Log in to the SJTU HPC platform (also known as "交我算") as the user to perform job queries, submissions, cancellations, and data management.

This skill is ready for commercial/non-commercial use.

## Publisher:

[taleintervenor](https://clawhub.ai/user/taleintervenor)

### License/Terms of Use:

MIT-0

## Use Case:

External SJTU HPC users use this skill to manage account information, query SLURM jobs and partitions, submit or cancel jobs, and move data between hot and cold storage through HPC APIs and SSH entry nodes.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill handles reusable HPC passwords, bearer tokens, SSH keys, and certificates stored in the workspace.

Mitigation: Use it only in a trusted local environment for an SJTU HPC account the user controls, avoid entering passwords directly in chat, and protect or remove credential files when no longer needed.

Risk: The skill can perform user-level SSH, job, account, and data operations, including actions that may interrupt jobs or affect stored data.

Mitigation: Confirm destructive, account-changing, or job-interrupting actions with the user and verify target partitions, storage paths, and entry nodes before execution.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/taleintervenor/skills/sjtu-slurm-skill)
- [Project homepage](https://github.com/SJTU-HPC/SJTU-SLURM-Skill)
- [SJTU HPC API documentation](https://api.hpc.sjtu.edu.cn/doc/index.html#/)
- [SJTU HPC account security documentation](https://docs.hpc.sjtu.edu.cn/accounts/security.html)

## Skill Output:

**Output Type(s):** [text, markdown, shell commands, configuration, guidance]

**Output Format:** [Markdown with inline shell commands and operational guidance]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May initiate API calls, SSH sessions, credential setup, and long-running remote job or data operations when used by an agent.]

## Skill Version(s):

0.2.3 (source: server release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.