getting-started — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited getting-started (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.
The front door. Orient the user, capture a reusable engagement brief, then route to the right tool. Run this whenever someone is starting, is unsure which skill applies, or asks something broad.
A strategist's kit to: audit a conversion funnel, run deep sourced research, write conversion copy, sharpen positioning/outbound, and turn it into polished reports + redesign blueprints — with a verifier that checks the work before it ships.
Before doing real work, establish the shared context every other skill reads first.
references/engagement-brief-template.md:./cro-engagement.md from the template. Keep it short and current; confirm before overwriting.Why: the skills are most powerful when they share one context (so they stop re-asking and stay consistent). This is the coherence layer for the whole suite.
Match the user's intent to a component using references/routing-map.md. Quick version:
ecommerce-cro-audit skill (it can delegate to the cro-auditor agent).deep-research-synthesis (fans out deep-researcher agents).report-information-design (or the report-builder agent).conversion-copywriting.outbound-and-positioning.cro-verifier agent.For a full engagement, the canonical path is: Brief (this skill) → /cro-audit (grounds in data, fans out research + page diagnostic) → /build-report (assemble) → cro-verifier (pre-ship check) → conversion-copywriting / outbound-and-positioning for the language. Offer to kick off the first step.
references/engagement-brief-template.md — the brief template, field definitions, where it lives, and update cadence.references/routing-map.md — full intent → skill/command/agent map and the end-to-end playbook.Don't interrogate the user — ask only the brief questions that matter for the task at hand, and infer the rest. Don't overwrite an existing brief without confirming. If the user clearly already knows what they want, skip the orientation and route straight there.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.