CC cachyos-expert

Senior Systems Engineer für CachyOS und Arch Linux. Nutze bei ALLEN Fragen zu CachyOS, Arch, Pacman, AUR, paru/yay, BORE/EEVDF, sched-ext/scx, ZRAM, BTRFS, Gaming (Proton, GameMode, Wine), chwd, cachyos-Kernel, mkinitcpio/dracut, systemd-boot/GRUB, Wayland/Xorg, NVIDIA/AMD, sysctl, udev, Boot-Probleme, PipeWire, Bluetooth, Netzwerk, Firewall, VPN, Snapper/Borg Backup, LUKS, Secure Boot, Docker/Podman, KVM/QEMU, GPU-Passthrough, PKGBUILD, Flatpak, TLP, Systemd-Units. Triggert bei: 'pacman Fehler', 'AUR bauen', 'Kernel wechseln', 'Boot hängt', 'Linux Gaming', 'System schneller', 'NVIDIA Problem', 'PipeWire', 'BTRFS Fehler', 'systemctl failed', 'Arch chroot', 'VM einrichten', 'Podman rootless', 'mein CachyOS', 'mein Arch'.

ClawHub Agent Skills author: Alexander Schneider v1.0.0 MIT-0 11 files body ≈ 698 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

Procedure Docker Infrastructuretype and topics are labelled automatically from the skill text

Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode

JSON

Technical rating

62/100

safety, quality, tests

Safety 60%: 53
Quality 40%: 76
Run on models: none yet

Process rating

53/100

Has gaps

Result and completion w 14: 0
Inputs and preconditions w 11: 0
When it triggers w 12: 20

the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.

For the model run — optional

Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 43

✓ No critical or high findings

Medium and low: 43

medium Dangerous commands cmd-destructive-fs-scoped references/boot-and-encryption.md:224

Destructive command on a partition / current directory (normal in admin docs; verify the target) (documentation of a security skill)
```
sudo mkfs.btrfs /dev/mapper/cryptroot
```
security skill
low Dangerous commands cmd-background-process references/backup-and-recovery.md:36

Starts a background / autostarted process (documentation of a security skill)
```
sudo systemctl enable --now snapper-timeline.timer
```
security skill
low Dangerous commands cmd-background-process references/backup-and-recovery.md:37

Starts a background / autostarted process (documentation of a security skill)
```
sudo systemctl enable --now snapper-cleanup.timer
```
security skill
low Dangerous commands cmd-background-process references/backup-and-recovery.md:58

Starts a background / autostarted process (documentation of a security skill)
```
sudo systemctl enable --now grub-btrfsd
```
security skill
low Dangerous commands cmd-background-process references/backup-and-recovery.md:110

Starts a background / autostarted process (documentation of a security skill)
```
sudo systemctl enable --now btrbk.timer
```
security skill
low Dangerous commands cmd-privilege references/boot-and-encryption.md:49

Privilege escalation / world-writable permissions (documentation of a security skill)
```
sudo cp /boot/loader/entries/linux-cachyos.conf /boot/loader/entries/linux-cachyos-lts.conf
```
security skill
low Dangerous commands cmd-privilege references/boot-and-encryption.md:224

Privilege escalation / world-writable permissions (documentation of a security skill)
```
sudo mkfs.btrfs /dev/mapper/cryptroot
```
security skill
low Dangerous commands cmd-privilege references/boot-and-encryption.md:236

Privilege escalation / world-writable permissions (documentation of a security skill)
```
sudo dd if=/dev/urandom of=/etc/cryptsetup-keys.d/cryptroot.key bs=512 count=4
```
security skill
low Dangerous commands cmd-privilege references/boot-and-encryption.md:237

Privilege escalation / world-writable permissions (documentation of a security skill)
```
sudo chmod 000 /etc/cryptsetup-keys.d/cryptroot.key
```
security skill
low Dangerous commands cmd-background-process references/desktop-and-audio.md:161

Starts a background / autostarted process (documentation of a security skill)
```
sudo systemctl enable gdm
```
security skill
low Dangerous commands cmd-background-process references/desktop-and-audio.md:260

Starts a background / autostarted process (documentation of a security skill)
```
sudo systemctl enable sddm
```
security skill
low Dangerous commands cmd-background-process references/desktop-and-audio.md:263

Starts a background / autostarted process (documentation of a security skill)
```
sudo systemctl enable gdm
```
security skill
low Dangerous commands cmd-background-process references/desktop-and-audio.md:267

Starts a background / autostarted process (documentation of a security skill)
```
sudo systemctl enable lightdm
```
security skill
low Dangerous commands cmd-background-process references/desktop-and-audio.md:277

Starts a background / autostarted process (documentation of a security skill)
```
sudo systemctl enable gdm
```
security skill
low Dangerous commands cmd-background-process references/networking.md:72

Starts a background / autostarted process (documentation of a security skill)
```
sudo systemctl enable --now iwd.service
```
security skill
low Dangerous commands cmd-background-process references/networking.md:96

Starts a background / autostarted process (documentation of a security skill)
```
sudo systemctl enable --now systemd-networkd systemd-resolved
```
security skill
low Dangerous commands cmd-background-process references/networking.md:127

Starts a background / autostarted process (documentation of a security skill)
```
sudo systemctl enable --now firewalld
```
security skill
low Dangerous commands cmd-background-process references/networking.md:182

Starts a background / autostarted process (documentation of a security skill)
```
sudo systemctl enable --now nftables
```
security skill
low Dangerous commands cmd-background-process references/networking.md:192

Starts a background / autostarted process (documentation of a security skill)
```
sudo systemctl enable --now systemd-resolved
```
security skill
low Dangerous commands cmd-privilege references/networking.md:270

Privilege escalation / world-writable permissions (documentation of a security skill)
```
echo 'net.…ard=1' | sudo tee /etc/sysctl.d/99-t…onf
```
security skill
low Dangerous commands cmd-privilege references/networking.md:271

Privilege escalation / world-writable permissions (documentation of a security skill)
```
echo 'net.…ing=1' | sudo tee -a /etc/sysctl.d/99-t…onf
```
security skill
low Dangerous commands cmd-privilege references/package-management.md:192

Privilege escalation / world-writable permissions (documentation of a security skill)
```
sudo rm -rf /etc/pacman.d/gnupg
```
security skill
low Dangerous commands cmd-background-process references/performance-tweaks.md:41

Starts a background / autostarted process (documentation of a security skill)
```
sudo systemctl enable --now scx.service
```
security skill
low Dangerous commands cmd-privilege references/performance-tweaks.md:104

Privilege escalation / world-writable permissions (documentation of a security skill)
```
echo 'vm.swappiness=180' | sudo tee /etc/sysctl.d/99-s…onf
```
security skill
low Dangerous commands cmd-privilege references/performance-tweaks.md:108

Privilege escalation / world-writable permissions (documentation of a security skill)
```
echo 'vm.watermark_scale_factor=125' | sudo tee -a /etc/sysctl.d/99-s…onf
```
security skill
low Dangerous commands cmd-privilege references/performance-tweaks.md:109

Privilege escalation / world-writable permissions (documentation of a security skill)
```
echo 'vm.watermark_boost_factor=0' | sudo tee -a /etc/sysctl.d/99-s…onf
```
security skill
low Dangerous commands cmd-privilege references/performance-tweaks.md:125

Privilege escalation / world-writable permissions (documentation of a security skill)
```
echo madvise | sudo tee /sys/kernel/mm/transparent_hugepage/enabled
```
security skill
low Dangerous commands cmd-privilege references/performance-tweaks.md:128

Privilege escalation / world-writable permissions (documentation of a security skill)
```
echo 'vm.nr_hugepages=1024' | sudo tee /etc/sysctl.d/99-h…onf
```
security skill
low Dangerous commands cmd-background-process references/performance-tweaks.md:310

Starts a background / autostarted process (documentation of a security skill)
```
sudo systemctl enable nvidia-suspend.service
```
security skill
low Dangerous commands cmd-background-process references/performance-tweaks.md:311

Starts a background / autostarted process (documentation of a security skill)
```
sudo systemctl enable nvidia-resume.service
```
security skill
low Dangerous commands cmd-background-process references/performance-tweaks.md:312

Starts a background / autostarted process (documentation of a security skill)
```
sudo systemctl enable nvidia-hibernate.service
```
security skill
low Dangerous commands cmd-background-process references/performance-tweaks.md:315

Starts a background / autostarted process (documentation of a security skill)
```
sudo systemctl enable nvidia-persistenced.service
```
security skill
low Dangerous commands cmd-background-process references/systemd-and-diagnostics.md:62

Starts a background / autostarted process (documentation of a security skill)
```
sudo systemctl enable <service>
```
security skill
low Dangerous commands cmd-background-process references/systemd-and-diagnostics.md:64

Starts a background / autostarted process (documentation of a security skill)
```
sudo systemctl enable --now <service>   # Enable + Start
```
security skill
low Dangerous commands cmd-background-process references/systemd-and-diagnostics.md:148

Starts a background / autostarted process (documentation of a security skill)
```
sudo systemctl enable --now mein-backup.timer
```
security skill
low Dangerous commands cmd-background-process references/virtualization.md:26

Starts a background / autostarted process (documentation of a security skill)
```
sudo systemctl enable --now libvirtd.service
```
security skill
low Dangerous commands cmd-background-process references/virtualization.md:27

Starts a background / autostarted process (documentation of a security skill)
```
sudo systemctl enable --now virtlogd.service
```
security skill
low Dangerous commands cmd-privilege references/virtualization.md:70

Privilege escalation / world-writable permissions (documentation of a security skill)
```
# Intel: echo 'options kvm_intel nested=1' | sudo tee /etc/modprobe.d/kvm-nested.conf
```
security skill
low Dangerous commands cmd-privilege references/virtualization.md:71

Privilege escalation / world-writable permissions (documentation of a security skill)
```
# AMD:   echo 'options kvm_amd nested=1' | sudo tee /etc/modprobe.d/kvm-nested.conf
```
security skill
low Dangerous commands cmd-background-process references/virtualization.md:138

Starts a background / autostarted process (documentation of a security skill)
```
sudo systemctl enable --now docker.service
```
security skill
low Dangerous commands cmd-background-process references/virtualization.md:238

Starts a background / autostarted process (documentation of a security skill)
```
sudo systemctl enable --now lxd.service
```
security skill

low Risky intent intent-offensive-security skill-card.md:25

Offensive-security / dual-use content (legitimate for authorised testing; review intended use)

Mitigation: Explain the security impact first, apply the narrowest change needed, and avoid remote script piping or privilege escalation unless the user confirms the tradeoff. <br>

low Dangerous commands cmd-privilege SKILL.md:24

Privilege escalation / world-writable permissions (documentation of a security skill)
```
sudo cp /etc/<datei> /etc/<datei>.bak.$(date +%F)
```
security skill

Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 53/100

0Result and completion. Does not say what the result is
0Inputs and preconditions. Does not say what the process needs to start
20When it triggers. No condition that starts the skill
50Failures and branches. 0 branches, has a failure section
60Tools and files. Uses tools (bash) that frontmatter does not declare
100Steps. 23 steps
100Consistency. Name and required fields are in place
100Execution cost. Instruction body is 698 tokens
100Running it twice. No mutating operations
100Progress reporting. Reports progress

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

+5Description has no quoted example phrases that should trigger the skill
+4Description does not say when NOT to use the skill (false activations)
+3Output format is not stated: the model decides each time
+1No license
+2Single-language instructions
+3Description length 729: enough signal without eating the budget
+4Structure: 7 headings
+3Step-by-step instructions: 23 items
+4Has examples (2 code blocks)
+4Reference files are cited in the instructions (9 of 9)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.

External checks

ClawHub: suspicious

This appears to be a legitimate CachyOS/Arch administration skill, but its reference material includes powerful system-changing commands that need review before use.

LLM: suspicious (high) · VirusTotal: · 29 May 2026

Tests

— no evals.json

— no spec.yaml

— not run on models

Files · 11

references/backup-and-recovery.md 6K
references/boot-and-encryption.md 8K
references/desktop-and-audio.md 7K
references/gaming.md 7K
references/networking.md 7K
references/package-management.md 8K
references/performance-tweaks.md 14K
references/systemd-and-diagnostics.md 10K
references/virtualization.md 7K
skill-card.md 3K
SKILL.md 4K

Frontmatter

version: 1.0.0

Dates

In catalog since 9 Apr 2026

Updated in catalog 11 May 2026

First seen here 9 Sept 2026

Last analysis 11 Sept 2026, 02:16 UTC

Last seen in crawl 8 h ago

Score history

Date		Score	Safety	Qual.
9 Sept 2026	C	62	53	76