action-brief — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited action-brief (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.
When any conversation produces something actionable — check-in, sparring, focused work, goal-setting, data analysis — produce an action brief.
Write to actions/YYYY-MM-DD-<short-name>.md in the data directory. Scale depth to the task.
# <Action Name>
## Goal
What this achieves and why it matters. Tie to weekly/monthly/quarterly goals.
## Context
Relevant data, findings, links to data files that informed this decision.
## Target Project
Where this gets executed (if applicable — e.g., the main codebase, a marketing channel, etc.)
## Scope
What's in. What's explicitly out.
## Success Criteria
How do we know it worked?
## Benchmarks
Current numbers to measure against. Link to data source in `data/` if available.Goal and Scope in a few sentences is enough. The brief should be exactly as detailed as the person executing it needs — no more.
up-next.md — add to the appropriate section (This Week or Queued) in priority orderactions/YYYY-MM-DD-name.md."actions/ = work in progressactions/ directory = everything shipped~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.