Works with the AI Agents you already use
tux
A Linux troubleshooting agent: diagnoses hardware and software problems on your machine, explains what it finds, and applies fixes with your approval.
$5
tux
Example session with this skill installed
My system is feeling sluggish and I think one of my drives might be failing. Can you run a checkup?
- Read your context and instructions
- Compiled the tux
I have completed a comprehensive system scan. I checked the storage stack, CPU usage, and kernel logs. I found a critical issue with one of your SSDs and a high-load process consuming memory.
System Health Report
| Area | Status | Findings | Proposed Fix |
|---|---|---|---|
| Storage | CRITICAL | /dev/sdb reporting 142 reallocated sectors; SMART status: FAIL | Backup data immediately and replace drive |
| Memory | WARNING | OOM killer recently terminated node; Swap usage at 92% | Investigate node memory leaks or increase RAM |
| CPU | HEALTHY | Load average 0.45; no thermal throttling detected | N/A |
| Network | HEALTHY | All interfaces up; no packet loss detected | N/A |
| Services | WARNING | docker.service failed to start 3 times in the last hour | Check daemon.json for syntax errors |
Next steps
- Would you like me to show you the full SMART attributes for
/dev/sdb? - I can investigate the
docker.servicelogs to see why it is failing to start. - Shall we enable background monitoring to alert you if the drive health worsens?
Connects securely to your tools. The creator never sees your data.
About this skill
Stop manually grepping logs and hunting for misconfigured services. This Linux troubleshooting suite provides a systematic way to diagnose and repair system health issues. It handles everything from kernel errors and OOM kills to disk SMART health and driver instability.
What it does
- System Diagnostics runs comprehensive scans across CPU, GPU, memory, storage, and network stacks to identify root causes.
- Background Monitoring configures systemd timers to watch for hardware errors, overheating, and service failures locally.
- Automated Remediation proposes specific fixes for detected problems and applies them only with explicit user approval.
- Transaction History maintains a record of every change, allowing for safe rollbacks of config edits or package modifications.
- State Snapshots captures the system state before and after scans to provide evidence-based reporting.
How it works
- Health Check initiates a scan of hardware and software layers using
tux-snapshotandtux-scan. - Investigation digs into logs and configs for any suspicious metrics or failed components.
- Reporting delivers a prioritized list of problems, warnings, and healthy areas with proposed fixes.
- Monitoring enables local background checks via
tux-monitorthat trigger desktop notifications on new failures. - Undo reverts specific changes by referencing a change ID from the
tux-undo list.
Frameworks & tools
Built for Linux environments. Uses standard system utilities and systemd user timers for local monitoring.
Why this beats prompting it yourself
Generic LLMs lack the system-level context to know which logs to check or how to interpret specific kernel hardware errors. This skill uses dedicated local tools to gather raw evidence before the AI analyzes it, ensuring fixes are based on reality rather than hallucinated paths.
Use cases
- Diagnose why a machine is running slow or feeling unstable.
- Monitor laptop battery wear and hardware SMART status in the background.
- Roll back a configuration change that caused a service to stop starting.
- Perform a fresh audit of a new Linux installation for hardware compatibility.
Known limitations
Background monitoring is strictly local and requires systemd. Undoing changes might require manual intervention if files were edited externally after the agent's modification.
Requires systemd for background monitoring. Automated undo may fail if files were manually edited after the agent modified them, requiring a force flag.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 29 days ago
Requires
Permissions
Allowed Hosts