Skill Crossroads ec2
rubric v1.2 · deterministic
A+ 97/100 overall
Correctness & Structure 100 pass
Triggering & Discoverability 100 pass
Clarity & Instructions 100 pass
Token & Context Cost 91 1 warn
Safety & Security 89 1 warn
Verifiability & Maintainability 100 pass

Top fixes — ranked by score impact

⚠ SAFETY-03 No destructive auto-invocation
SKILL.md:10auto-invocable (no disable-model-invocation) → performs a destructive action ("terminate")
Skill appears to "terminate" but the model can auto-invoke it — a destructive action could fire without the user asking.
terminate
Fix If this action is destructive/irreversible, set `disable-model-invocation: true` so it only runs when explicitly invoked.
⚠ TOKEN-03 Description budget footprint
SKILL.md:1
Description is 1382 chars (~461 tokens) — heavy for something loaded every turn.
Fix Tighten the description; it is always-on budget cost.
★ scores higher than ≈77% of 208 public skills (deterministic rubric v1.2 sample, 2026-09)

Embed this badge

Skill Crossroads grade A+ Always-fresh — it re-scans and updates on its own. 
[![Skill Crossroads](https://skillcrossroads.com/api/badge/itsmostafa/aws-agent-skills/skills/ec2.svg)](https://skillcrossroads.com/s/itsmostafa/aws-agent-skills/skills/ec2)
Grade your own Claude Code skill — evidence-cited, file-and-line, free. Scan your own skill →