review-workflow — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited review-workflow (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 this owner for review-only work.
sdd-workflow.effective-interact for material reviews, severity filters, option comparison, or evidence tours.compound-code-review for deep pre-PR or CE-style code review.security-review for focused security-sensitive review.claude-api for Anthropic API or SDK reviews.mcp-builder for MCP server or tool-contract reviews.doc-coauthoring for document structure and reader-risk review.internal-comms for internal update, FAQ, incident, or leadership communication review.theme-factory for theme consistency review of existing artifacts.web-design-guidelines for UI/UX audits only when that helper is relevant and available.verification-loop only for final command gates, not finding analysis.For parallel review lenses, follow workflow-router/references/orchestration-policy.md: subagents can run independent read-only passes, but the main agent owns severity, synthesis, and final conclusions.
Findings first. Then open questions, residual risk, and a short summary if useful.
Do not implement fixes inside this workflow.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.