agentleFS
Sign inStart free
fritzprixfritzprix/libr-agent/.agents/skills/computer-diagnosis/SKILL.md

computer-diagnosis

Skill11 starsChanged 20 days agoMITView on GitHub

Comprehensive computer diagnosis and troubleshooting. Use this skill when a user reports issues with their computer (e.g., "my computer is slow", "it's freezing", "loud fan noise", "no disk space") to analyze system metrics (CPU, RAM, Disk, Network) across macOS, Windows, and Linux, and generate a detailed report with actionable recommendations.

  • Installs packages

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When a user reports an issue, execute the data collection script to snapshot the current system state.

    line 13
  2. Distinctive:

    Use the analysis script to parse the collected JSON and identify critical issues (high CPU/Memory, full disks).

    line 20
  3. Very specific:

    Read both sys_info.json and analysis_result.json.

    line 27
  4. Very specific:

    Ensure you have permission to read system states.

    line 36
  5. Distinctive:

    Always provide actionable recommendations alongside the raw data.

    line 37

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Computer Diagnosis Skill

This skill allows Claude to act as a technical support assistant. It gathers system information using Python's psutil library (making it cross-platform), analyzes the metrics for common issues, and provides a structured report.

Workflow

  1. Information Gathering: When a user reports an issue, execute the data collection script to snapshot the current system state.

    python scripts/collect_info.py > sys_info.json

  2. Data Analysis: Use the analysis script to parse the collected JSON and identify critical issues (high CPU/Memory, full disks).

    python scripts/analyze_info.py sys_info.json > analysis_result.json
  3. Report Generation: Read both sys_info.json and analysis_result.json. Present the findings to the user using the template found in assets/report_template.md.

Reference Materials

  • Symptoms Guide: See references/symptoms.md to map user descriptions to specific metrics.

Notes

  • The scripts rely on psutil. If it's missing, you may need to install it (pip install psutil).
  • Ensure you have permission to read system states. Some disk partitions or network interfaces might throw PermissionError, which the script handles by skipping them.
  • Always provide actionable recommendations alongside the raw data. Users want to know how to fix the problem.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free