← All skills
gke-stockout-investigator
97 / 100 · Low risk
Fine to try.
By gke-labs/kube-agents (GitHub) · other · 126 stars · scanned at commit e9a8105
Act upon GKE cluster-autoscaler scale-up failure and capacity constraint alerts, diagnose them using ComputeClass debugging guidelines, and submit a remediation Pull Request.
Works with any agent that supports SKILL.md skills.
What this skill can do
Runs commands on your computer
This is disclosed by the author in the skill's SKILL.md or README.
Found in 13 places.
Show 10 more
- agentplugins/gke-stockout-investigator/files/skills/gke-stockout-investigator/SKILL.md, line 69
kubectl describe pod <pod_name> -n <namespace> - agentplugins/gke-stockout-investigator/files/skills/gke-stockout-investigator/SKILL.md, line 86
python3 "$HERMES_HOME"/skills/submit-suggestion/scripts/submit_suggestion.py prepare \ - agentplugins/gke-stockout-investigator/files/skills/gke-stockout-investigator/SKILL.md, line 151
gcloud compute regions describe us-central1 --format="json(quotas.filter(metric=CPUS))" - agentplugins/gke-stockout-investigator/files/skills/gke-stockout-investigator/SKILL.md, line 162
gcloud compute reservations list --format="json" - agentplugins/gke-stockout-investigator/files/skills/gke-stockout-investigator/SKILL.md, line 171
kubectl top node - agentplugins/gke-stockout-investigator/files/skills/gke-stockout-investigator/SKILL.md, line 186
gcloud beta compute advice capacity \ - agentplugins/gke-stockout-investigator/files/skills/gke-stockout-investigator/SKILL.md, line 196
gcloud beta compute advice capacity-history \ - agentplugins/gke-stockout-investigator/files/skills/gke-stockout-investigator/SKILL.md, line 209
kubectl get configmap cluster-autoscaler-status -n kube-system -o yaml - agentplugins/gke-stockout-investigator/files/skills/gke-stockout-investigator/SKILL.md, line 277
> In background/PubSub sessions, any invocation of `execute_code` (Python or bash script execution) triggers interactive command approval safeguards that will b - agentplugins/gke-stockout-investigator/files/skills/gke-stockout-investigator/SKILL.md, line 313
BODY=$(mktemp -p /opt/data/scratch pr_body.XXXXXX.md)
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'gke-stockout-investigator' ] || [ -L ~/.agents/skills/'gke-stockout-investigator' ]; then echo 'A skill folder named gke-stockout-investigator already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/gke-labs/kube-agents' "$d" && git -C "$d" checkout --quiet 'e9a8105f6fbd52d51780c0fa524f960463304bc0' -- 'agentplugins/gke-stockout-investigator/files/skills/gke-stockout-investigator' && mkdir -p ~/.agents/skills && cp -R "$d"/'agentplugins/gke-stockout-investigator/files/skills/gke-stockout-investigator' ~/.agents/skills/'gke-stockout-investigator' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'gke-stockout-investigator' ~/.claude/skills/'gke-stockout-investigator' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for gke-labs/kube-agents shows the score of its lowest-scoring skill.

[](https://zalavijaysinh.github.io/skilltrust/repos/gke-labs/kube-agents/)
Score history
| Date | Version | Score |
|---|
| 2026-11-13 | e9a8105 | 97 |
| 2026-11-09 | 26dabb5 | 97 |
| 2026-11-07 | 2e7a07f | 97 |