invoice-three-way-match-preflight-ed57d0 — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited invoice-three-way-match-preflight-ed57d0 (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.
Use the repository skill at invoice-three-way-match-preflight/SKILL.md.
When installed as a Claude Code skill mirror, keep the full repository available so relative paths to scripts/, references/, templates/, and examples/ resolve correctly.
Run the fixture smoke test:
python3 invoice-three-way-match-preflight/scripts/invoice_three_way_match_preflight.py \
--invoices invoice-three-way-match-preflight/scripts/fixtures/invoices.csv \
--purchase-orders invoice-three-way-match-preflight/scripts/fixtures/purchase_orders.csv \
--receipts invoice-three-way-match-preflight/scripts/fixtures/receipts.csvFollow the canonical workflow in the root skill file: preserve the AP review boundary, compare invoice lines against purchase orders and receipts, classify exceptions by risk/action/owner, and do not approve, post, cancel, or pay live invoices.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.