skill-publish — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited skill-publish (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.
Takes a skill from ~/.claude/commands/ and packages it into the public skills repo.
Skill to publish: $ARGUMENTS
~/.claude/commands/skill-publish/scripts/stage.sh "$ARGUMENTS"If the script exits with an error, stop and explain what's wrong.
Read every file in ~/dev/mad-house/skills/skills/$ARGUMENTS/ and check for:
/home/samhc/ beyond ~, specific org names in ~/dev/)Mad House branding and org identity (e.g. madebymadhouse, mad-house/lab) is fine to keep. Generic paths using ~ or $HOME are fine.
If you find anything that needs scrubbing, fix it before continuing.
Open ~/dev/mad-house/skills/README.md and add the skill to the correct section of the skills table. Use the same one-line description style as existing entries.
If it does not fit an existing section, add a new one.
cd ~/dev/mad-house/skills && git add . && git commit -m "Add $ARGUMENTS skill
Co-Authored-By: Claude Sonnet 4.6 <[email protected]>" && git pushConfirm the push succeeded and give the user the GitHub URL for the skill folder.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.