Skip to content
Back to skills

Rumo Linux Inspect

ASecurity

Use when explicitly asked for a read-only Linux inspection, either a hardware inventory that saves raw evidence and a concise Chinese device-configuration TXT, or a memory and performance inspection for high memory, OOM, garbage-collection, slow-log, process, or port symptoms. Never change the target, install packages, or operate services.

  • 3 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added October 19, 2026
developmentperformance

Works with

  • terminal

Security analysis

A100/100

Pro scans all 7 files and shows the line behind each finding

Scanned October 19, 2026

npx -y skills add rumoii/rumo-engineering-skills --skill rumo-linux-inspect --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Rumo Linux Inspect?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Rumo Linux Inspect
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rumoii-rumo-linux-inspect/badge)](https://www.skillsdirectory.com/skills/rumoii-rumo-linux-inspect)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: rumo-linux-inspect
description: Use when explicitly asked for a read-only Linux inspection, either a hardware inventory that saves raw evidence and a concise Chinese device-configuration TXT, or a memory and performance inspection for high memory, OOM, garbage-collection, slow-log, process, or port symptoms. Never change the target, install packages, or operate services.
disable-model-invocation: true
---

# Rumo Linux Inspect

Collect Linux facts without changing the target. Pick the mode and read its reference in full before connecting.

| Mode | Produces | Reference |
| --- | --- | --- |
| Hardware inventory | A raw evidence TXT and a concise Simplified Chinese device-configuration TXT, returned verbatim in chat | [references/hardware-inventory.md](references/hardware-inventory.md) and [collection-commands.md](references/collection-commands.md) |
| Memory inspection | A local evidence directory and a risk classification | [references/memory-inspection.md](references/memory-inspection.md) |

## Shared Boundaries

- Confirm the target host, port, user, environment purpose, and SSH host fingerprint before connecting. Access only targets the user identified and authorized; production stays read-only.
- Run read-only commands only: no package changes, configuration edits, remote files, password changes, service operations, reboots, or deletions.
- Passwords and `sudo` prompts appear only in a visible interactive terminal. Never place credentials in arguments, scripts, environment variables, profiles, reports, or chat.
- Use `rumo-project-profile` for private install roots, log directories, and service patterns; there are no built-in hosts or paths.
- Treat a missing command, denied permission, empty field, and unsupported device as distinct evidence gaps. Do not infer facts the output does not prove.
- Report what was collected, where it was saved, and what the collected layer does not prove.

Files in this skill

  • SKILL.md1.9 KB
  • agents/openai.yaml329 B
  • references/collection-commands.md4.1 KB
  • references/hardware-inventory.md4 KB
  • references/memory-inspection.md1.8 KB
  • references/targets.example.tsv183 B
  • scripts/remote_memory_inspection.py5.2 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.