deck — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited deck (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.
scripts/preflight.sh passes.skills/distill/ engine is installed.When --preset is missing, ask via HITL — "Which preset? e.g. `pitch-deck` for a 3-slide presentation." Selected preset resolves to references/preset-{name}.md.
| # | Preset | Shape |
|---|---|---|
| 1 | decision-sandwich-6 | decision deck, 6 slides |
| 2 | pitch-deck | presentation, 3 slides |
| 3 | concept-explain | concept introduction, 4–5 slides |
| 4 | story-arc | variable length |
Pick mode/ratio from the preset (read the preset file's frontmatter):
distill --mode {preset.mode} --ratio {preset.ratio} --audience {X}.EngineOutput.units + preset mapping → SlideSpec[]:
references/design-tokens.md.| File | Content |
|---|---|
docs/galmuri-deck-{slug}.json | SlideSpec[] array (machine consumption) |
docs/galmuri-deck-{slug}.md | per-slide script + visual cues (humans) |
"Create both files? docs/galmuri-deck-{slug}.{json,md} (y/n/edit-slug)"No binary build step. Do not introduce logic that emits native presentation-program file formats.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.