prep — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited prep (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.
Chief-of-Staff prep: walk into anything already briefed. Pull the scattered context into one page.
/daily ("on the calendar → offer /prep").## Prep — <meeting / person / topic> · <date · time>
**Goal** — what a good outcome looks like for you, in one line.
**Who** — attendees + the one thing that matters about each.
**Context** — the 3–5 facts / history you need (each with a source).
**Open loops** — what's owed by/to them (open-loops · wiki · threads).
**Your move** — the ask, 2–3 talking points, the decision you want.
**Risks / landmines** — what could go sideways + how to handle it.context/ (about-me, business, team, priorities), wiki/ (past thinking), decisions/log.md, open loops (tools/open_loops.py), and /graph-query to surface non-obvious connections (who/what relates to this).connections.md), pull the invite, the account, and the last meeting notes. If nothing is connected, work from files and say so./draft a pre-read or follow-up; /decide if a decision is the point.L2 — assembles the brief; the human runs the meeting. Read-only on external systems.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.