review-patterns — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited review-patterns (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Surface the team's coding conventions and review preferences from cubic's learned patterns.
git remote get-url originExtract the owner and repo name.
Call list_learnings with the owner and repo.
Match learning categories to the user's current task:
If a specific learning is highly relevant, call get_learning for full details including the original review feedback that generated it.
Present learnings as team preferences, not rigid rules. Group related learnings and include confidence levels.
## Team Patterns for this repo
### Error Handling (High Confidence)
- **Always wrap external API calls in try/catch** — The team prefers explicit error
handling over global middleware. Learned from senior reviewer feedback.
- **Use custom error classes** — Throw `AppError` subclasses, not raw `Error`.
### Naming (Medium Confidence)
- **Boolean variables use `is`/`has` prefix** — e.g., `isActive`, `hasPermission`.
### Testing (High Confidence)
- **Integration tests for all API endpoints** — Unit tests alone are not sufficient
for route handlers.
_3 learnings from senior reviewer analysis · 1 from user feedback_If no learnings exist, explain that cubic learns patterns over time from senior reviewer feedback.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.