Run a comprehensive, read-only health check on the user's computer and return a scored chat summary with prioritized, plain-English recommendations and safe cleanup suggestions. Use this whenever the user wants to check their computer's health, speed it up, free up / reclaim disk space, find what's eating CPU / memory / storage, check battery health and wear, audit login & startup items, see pending updates, or asks for a "tune-up", "checkup", "system report", "health check", or "is my Mac/PC/laptop healthy". Trigger even on casual phrasing like "my laptop feels slow", "why is my fan so loud", "my computer is laggy", "running out of space", or "clean up my machine". Works on macOS, Windows, and Linux. This is a Desktop Commander skill: it relies on a real local shell (start_process / interact_with_process) and is strictly read-only by default — it never needs sudo and only performs cleanups the user explicitly approves.
89
96%
Does it follow best practices?
Impact
61%
1.19xAverage score across 3 eval scenarios
Passed
No findings from the security scan
Disk space cleanup planning
Real measurements
100%
100%
No sudo in commands
100%
0%
No cleanups executed
100%
100%
Exact shell commands
80%
100%
Safe vs user-decision split
66%
80%
Ordered by benefit
100%
100%
3 to 5 recommendations
100%
100%
Reversible targets featured
100%
100%
Largest bucket first
100%
100%
Deep scan mentioned
0%
0%
Linux health check report with scoring rubric and recommendations
OS detection first
50%
25%
Linux reference file used
0%
62%
Batched collection script
0%
40%
Bounded output
50%
75%
Slow/network checks skipped and mentioned
100%
100%
Emoji traffic-light scoring
0%
75%
Correct score arithmetic
0%
0%
Correct verdict label
0%
12%
Correct category thresholds
25%
37%
Exact report structure
20%
30%
Recommendation count and order
100%
87%
Real measured values
100%
100%
Uptime restart rule and optional-check handling in system health report
Uptime recommendation rule
33%
33%
Named high-CPU process
46%
33%
Optional deep checks mentioned
0%
0%
Optional checks not executed
100%
100%
Maintenance category threshold
10%
100%
Resource hog category threshold
30%
50%
Real uptime value present
0%
30%
Numeric overall score
30%
100%
One-word verdict
0%
100%
Read-only collection
100%
100%
a781f5a
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.