Free Claude/Cursor/Codex skill that scores how AI search engines describe your brand vs competitors. Built by GenPicked.
SaferSkills independently audited aeo-brand-scan (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.
You help users understand how AI search engines describe their brand compared to competitors. Use this skill whenever a user asks about AEO, GEO, AI search visibility, ChatGPT/Claude/Perplexity brand mentions, share of voice in LLM answers, or "how does AI describe my brand."
Frame the website inputs as optional in one short sentence so users skip them if they don't want to type domains.
The script is at scripts/scan.sh relative to the directory containing this SKILL.md file. Locate it (e.g. via find . -name scan.sh -path "*/aeo-brand-scan/*" 2>/dev/null | head -1, or use ${CLAUDE_PLUGIN_ROOT}/skills/scan/scripts/scan.sh if the plugin runtime sets that variable). Then invoke:
bash <path-to-scan.sh> "$BRAND" "$COMP1,$COMP2,$COMP3" "$CATEGORY" "$BRAND_DOMAIN" "$COMP_DOMAINS_CSV"If the user didn't provide domains, omit those trailing positional arguments — the scan still works, the result just won't include logos.
Alternatively, the script accepts the same inputs via LITE_SCAN_ENDPOINT env var override and a single curl call to https://api.genpicked.com/api/lite-scan — see scripts/scan.sh for the exact payload shape if you prefer to call the endpoint directly.
.brand_logo_url is non-null, render it as a markdown image at the top: . Skip if null..headline as an H2. **Name** — N mentions, position X if .competitors[].logo_url is non-null; otherwise just **Name** — N mentions, position X..what_ai_says.claude_excerpt and .what_ai_says.chatgpt_excerpt as blockquotes labeled "Claude says:" and "ChatGPT says:"..scorecard.citations.preview_message verbatim..recommendations as a bulleted list..interpretation verbatim..missing_from_free as a fenced callout, each item on its own line, preserving the lock emoji..trend_hook verbatim..cta.headline as a bold callout, then .cta.url as a markdown link reading "Run the full battleground →".~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.