Skill Crossroads sns
rubric v1.2 · deterministic
B+ 89.9/100 overall
Correctness & Structure 100 pass
Triggering & Discoverability 100 pass
Clarity & Instructions 100 pass
Token & Context Cost 100 pass
Safety & Security 64 1 fail
Verifiability & Maintainability 53 1 fail

Top fixes — ranked by score impact

✗ SAFETY-01 No hardcoded secrets
notification-patterns.md:197— → matches Assigned credential literal pattern
Possible hardcoded secret (Assigned credential literal) — Toke***********************m'
Toke***********************m'
Fix Remove the secret from source, rotate it, and reference it via an environment variable instead.
✗ VERIFY-01 Evals or tests present
SKILL.md:1the skill works → no evals/, tests/, or verification section found
No way to prove the skill does what it claims.
Fix Add an evals/ folder (test prompts + expected outcomes) and a '## Verify' step in the body.
⚠ SAFETY-03 No destructive auto-invocation
SKILL.md:25auto-invocable (no disable-model-invocation) → performs a destructive action ("publishing")
Skill appears to "publishing" but the model can auto-invoke it — a destructive action could fire without the user asking.
publishing
Fix If this action is destructive/irreversible, set `disable-model-invocation: true` so it only runs when explicitly invoked.
★ scores higher than ≈22% of 208 public skills (deterministic rubric v1.2 sample, 2026-09)

Embed this badge

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