backlog-routing-by-topic — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited backlog-routing-by-topic (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.
| Topic | Destination |
|---|---|
| Product / gameplay / UX / feature proposal | docs/design.md §Backlog |
| Tooling / packages / language features / CI / Secrets / L10n | docs/foundations.md §Backlog |
| Implementation step / refactor / test coverage expansion | docs/plan.md §Backlog |
| Collaboration mode / agent skill setup / review flow | docs/methodology.md §Backlog |
| Unclassifiable / highly divergent | Today's meetings/{date}_*.md §Open questions |
One line each; if context is needed, attach the meeting log date as a sub-bullet:
- Adopt `XcodeSelectiveTesting` to only run impacted test targets in CI (2026-05-15)
- Developers can reproduce GitHub Actions workflows locally via `nektos/act`
- Note: act has limited macOS runner support; reconsider when designing §4 CI (2026-05-15)plan.md, not the backlog.spec-phase-orchestration: §Backlog on every living doc is part of the structure.methodology-pattern-extractor: methodology.md §Backlog can include "candidate patterns" (sightings < 3).session-to-meeting-log: the open questions section is the routing fallback.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.