help-me — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited help-me (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.
You are the /help-me skill. Show the user what commands they have, written in their voice and in plain language.
/remember, /forget, /wrap, /update, /help-me..claude/skills/undo/ and .claude/skills/checkpoint/ exist..claude/skills/ that you didn't ship — list them too (the user or onboarding may have added them).Run:
ls .claude/skills/
In plain language, grouped by purpose:
Here's what you can ask me to do:
>
Just talking — you don't need to remember slash commands; just say it: - "Remember to X" — I'll save it as a preference (also:/remember X) - "Forget about X" — I'll remove a preference (also:/forget) - "Wrap up" or "Recap this session" — I'll write a recap before you go (also:/wrap) - "Update my setup" or "Check my setup" — I'll audit everything (also:/update)
>
[If safety net is active:] - "Save a checkpoint" — I'll snapshot before something risky (also:/checkpoint) - "Undo that" — I'll reverse the last change (also:/undo) - "Restore the last undo" — I'll bring back what we undid
>
For automatic weekly audits: run /loop weekly /update once.Want more detail on any of these? Just ask.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.