weekly — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited weekly (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.
The Cadence layer at week resolution: close the loop on the week, surface what stalled, and aim the next week at the priorities that matter.
Not to be confused with: /audit (is the kit healthy — connections, freshness) or /level-up (build one new automation). This skill reviews your week and priorities.
## Weekly review — week of <date>
**Moved** — progress on each 90-day priority this week (concrete, not vibes).
**Stalled / at risk** — priorities or loops that didn't move + why + the unblock.
**Closed loops** — commitments resolved this week.
**Carrying forward** — open loops into next week, with owners.
**Next week's focus** — 3–5 outcomes for the coming week, tied to priorities.
**Surfaced for /level-up** — any task done manually 3+ times this week (candidate to automate).context/priorities.md, decisions/log.md (this week's entries), projects/, and open loops (tools/open_loops.py if present).decisions/log.md (allowed without approval).L2 — drafts the review and next-week plan; the human confirms.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.