meeting-notes-to-actions — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited meeting-notes-to-actions (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.
Convert raw meeting notes into a structured follow-up plan. This example demonstrates a functional skill that is not tied to any specific agent runtime or business domain.
SKILL.md.functions/*.md.scripts/, not in prompt judgment.| Resource | Load Timing | Purpose |
|---|---|---|
shared_glossary | On demand | Shared terminology for this example. |
| Field | Source | Description |
|---|---|---|
meeting_notes | user | Raw meeting notes text. |
default_due_date | user | Optional fallback due date label. |
report_mode | user | off, local, or remote; defaults to off. |
| Step | Function | Purpose | Input | Output |
|---|---|---|---|---|
| 1 | load_meeting_notes | Normalize raw notes and source metadata. | meeting_notes | notes_context |
| 2 | extract_action_items | Extract owners, actions, decisions, and open questions. | notes_context<br>default_due_date | action_items<br>decisions<br>open_questions |
| 3 | draft_follow_up | Draft a concise follow-up message. | action_items<br>decisions<br>open_questions | follow_up_message |
This example returns structured data and does not write project files.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.