skill-spotlight-publisher — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited skill-spotlight-publisher (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 thesis: 340 skills is an inventory; one well-explained skill per day is a story. Daily skill-of-the-day spotlights turn the catalog into a year-long content stream — 365 explainers per year, each one a Cooper-voice artifact a solo founder can read in 60 seconds and decide whether to use.
bash skills/skill-spotlight-publisher/run.sh # daily run
bash skills/skill-spotlight-publisher/run.sh --skill <name> # spotlight a specific skill
bash skills/skill-spotlight-publisher/run.sh --dry-run # pick + render, no publishskills/<X>/SKILL.md weighted by:a. Has not been spotlit in last 60 days (stored at data/skill-spotlights/_history.json). +5 weight. b. SKILL.md is non-trivial (>50 lines). +2 weight. c. owner_agent is set (P5 compliant). +1 weight. d. NOT a stretch-skill (heuristic: name doesn't start with _). +1 weight.
DAI OS. Three-part shape: what it solves / when to reach for it / the single most surprising thing about it.
site/skills/<slug>/spotlight.html, appendto site/skills/index.html (or create), append to _history.json. Either fails → write to data/skill-spotlights/drafts/<YYYY-MM-DD>-<slug>.md.
STATUS=ok skill=<slug> path=<html> (published) STATUS=draft skill=<slug> path=<md> reason=<voice|scrubber> (held for review) STATUS=skip reason=ollama-down|no-eligible-skill STATUS=error reason=<...>
Static-template HTML wrapping a 200-word explainer with:
data/skill-spotlights/_history.json:
{
"<slug>": {
"spotlit_at": "<ISO>",
"voice_score": <int>,
"html_path": "<...>"
}
}Used for the "last 60 days" weighting in step 1a.
site/skills/. P11 still applies: the explainer describes architecture and capability, not customer outcomes.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.