apw-work-with-work-item-artifacts — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited apw-work-with-work-item-artifacts (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.
This skill is the single source of truth for where a work item's artifacts live. Other skills name the artifact they produce (its filename) and point here for the location; they do not restate the path.
A work item's artifacts live together under `docs/work-items/<slug>/` in the project root.
<slug> is a short kebab-case name for the work item (a work item ≈ a task). Reuse the same `<slug>` across every skill that touches the same work item — research, plan, implementation, verification, and so on — so all of that work item's artifacts sit side by side in one folder.
For example, the research and plan for a work item slugged payment-retry live at docs/work-items/payment-retry/research.md and docs/work-items/payment-retry/plan.md.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.