Local Linux lag and performance diagnosis. Run read-only probes based on the user's symptoms to find CPU, memory, disk, or local network bottlenecks, then give safe advice. Never auto-remediate. Also matches Chinese requests such as 系统卡顿、机器好慢、内存不足、突然重启、OOM、磁盘很慢.
Standardmäßig ist der Prompt ausgewählt, der zuerst die Quelle prüft. Sie können zu einem direkten Befehl wechseln oder eine lokale Kopie herunterladen.
Quelldateien prüfen
Lesen Sie SKILL.md und alle von SkillsMP angezeigten Begleitdateien, bevor Sie sich für eine Installation entscheiden.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Ein direkter Befehl überspringt den Prüf-Prompt. Prüfen Sie die Quelle, bevor Sie ihn ausführen.
Local Linux lag and performance diagnosis. Run read-only probes based on the user's symptoms to find CPU, memory, disk, or local network bottlenecks, then give safe advice. Never auto-remediate. Also matches Chinese requests such as 系统卡顿、机器好慢、内存不足、突然重启、OOM、磁盘很慢.
author
aish
context
subagent
agent
troubleshoot
allowed-tools
["bash","read_file","grep","glob"]
triggers
["diagnose_system_lag","system lag diagnosis","performance check","system is slow","high load","out of memory","OOM","disk is slow","unexpected reboot","系统卡顿诊断","看看系统卡不卡","系统很卡","机器好慢","内存不足","磁盘很慢","突然重启","异常关机"]
platforms
["linux"]
distributions
["deepin","debian","ubuntu","uos"]
System lag diagnosis
Short-path, read-only diagnosis for lag, slowness, resource pressure, or a recent unexpected reboot on this host.
Out of scope: full sos collection, long-running health baselines, cloud VPC troubleshooting, auto config changes or killing processes. Use sosreport-analyzer, deepin-sysassist, or other skills for those.
Rules
Read-only: do not change config, kill processes, drop caches, tune sysctl, or unload modules.
Symptom-first: decide what to probe from the user's report; do not run a fixed full command list every time.
Stop when enough: stop once the symptom is explained and key objects (process / mount / device) are named.
Follow-ups fill gaps only: the next probe answers “what is still missing”, not “scan every focus again”.
Advice needs confirmation: prefer action targets; give concrete kill/restart commands only if asked, and remind the user to save work.
Isolated sessions: do not run report-writing scripts under this skill (for example scripts/diagnose.sh).
Honest probes: if a tool is missing or a probe fails, state that in Evidence—do not treat it as “no problem found”.
Workflow
Understand symptom → quick check (only if vague) → focused probes → answer
↑ stop when evidence is enough ↑
1. Understand the symptom
User report
Focus
First step
Slow / high load / no specifics
Unknown
Quick check
Low memory, Swap, OOM, process killed
Memory
Memory probes
Copy/open large files stalls, disk noise, frozen I/O
Disk
Disk probes
High CPU, fans spinning, one process pegged
CPU
CPU probes
Slow/unreachable network (local host side)
Network
Local network probes
Sudden reboot, black screen then recovery, unclean shutdown
Incident
Reboot/crash probes
Named apps (browser, WPS, Java, a service) are suspects under the matching focus—not a separate workflow.
Correlated OOM/panic/I/O → conclude from that. Otherwise inconclusive; suggest re-running after the next incident or using sosreport-analyzer.
4. Threshold hints (secondary to evidence)
CPU: load stays > nproc × 1.5 and idle < 20% → CPU pressure
I/O: sustained wa > 5%, or very high device %util → I/O pressure
Memory: very low MemAvailable, or Swap used ≥ 50% / ≥ 2GB → memory pressure
Disk space: root or home ≥ 90% → full-disk risk
Thresholds help; conclusions must follow this run’s samples and logs.
Output format
## Conclusion
1–2 sentences: whether something is wrong, main cause, blast radius.
## Evidence
- Only metrics/processes/logs that support the conclusion
- Label timing: current sample / current boot logs / previous boot logs
- Note unavailable or failed probes when relevant
## Recommendations
- Short-term action targets (close user apps, free space, etc.)
- Concrete commands only if asked; warn before kill
- Never recommend stopping: Xorg, wayland, dde-*, systemd, dbus, NetworkManager, fcitx5/ibus
If the system looks healthy, still use this skeleton; say no action needed instead of inventing problems. Reply in the user's language.
Desktop app hints
Kind
Keywords
Browser
chrome, chromium, firefox
WPS
wps, wpp, et
WeCom
WXWork, WeMail
Editor
code, cursor, typora
Proxy
clash
Terminal
warp-terminal
Examples
User: Desktop freezes while copying a large file
Focus → disk (skip a blind full check)
Disk probes → high wa, D state processes, busy disk
Enough → stop
Conclude I/O saturation; suggest off-peak copy / check free space and disk health
User: Screen went black briefly; did it crash?
Focus → incident
Previous-boot journals + last -x
OOM → memory pressure + suspect process; no clue → say evidence is insufficient and offer next steps
