AI Discoverability Audit
Audits how a brand appears in AI search (ChatGPT, Perplexity, Claude) and scores gaps
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 21, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 0473fb3
Fetched SKILL.md via raw GitHub: frontmatter parses with name+description, no scripts referenced, no security smells; bundled references/query-bank.md and SKILL-OC.md both return HTTP 200. Trigger phrasings tested (3 should-fire: "how does my SaaS show up when people ask ChatGPT for recommendations", "run an AEO / AI discoverability audit on my brand", "is my company visible to LLMs like Perplexity and Claude"; 2 should-not: "do a technical SEO audit of crawlability and Core Web Vitals", "write me a ChatGPT prompt to generate blog ideas") — all 5 judged correctly. For output I audited Plausible Analytics against my own Claude knowledge: baseline (110 words) was unstructured prose ending "strong presence, keep publishing comparisons"; the skill-followed artifact (442 words) produced a pre-audit entity-clarity hypothesis that surfaced a genuine miss (the dictionary word "plausible" diluting non-branded queries), a 6-dimension 24/30 score, a same-query-set competitor matrix, tiered gaps, dated 30/60/90-day re-audit checkpoints, and a self-critique flagging that only 1 of 3 platforms was actually queried. Output scored 7 not higher because the multi-platform empirical testing that is the audit's core promise cannot run without web access or manual result-pasting.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 7/10
- Docs & honesty 4/5
What AI Discoverability Audit does
A prompt-only skill that audits how a brand is described and recommended by AI assistants like ChatGPT, Perplexity, Claude, and Gemini, then scores six dimensions out of 30 and outputs a priority-tiered fix roadmap with dated 30/60/90-day re-audit checkpoints. Triggers when the user mentions AI search, AEO, LLM visibility, AI discoverability, or asks how their brand shows up in ChatGPT. Requires web access or the user pasting query results to test platforms beyond the one Claude can answer from its own knowledge.
How to install AI Discoverability Audit
git clone --depth 1 https://github.com/BrianRWagner/ai-marketing-claude-code-skills.git /tmp/ai-discoverability-audit-src
mkdir -p ~/.claude/skills
cp -R /tmp/ai-discoverability-audit-src/ai-discoverability-audit ~/.claude/skills/ai-discoverability-audit
# No deps, no API keys, no scripts. Pure-prompt skill.
# Bundles references/query-bank.md (copy/paste query library) and SKILL-OC.md alongside SKILL.md.
# To run a real multi-platform audit you need web access OR must paste ChatGPT/Perplexity/Gemini results back in;
# without that, only the Claude-knowledge portion of the audit is empirical.
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger AI Discoverability Audit
-
/ai-discoverability-auditAudits how a brand appears in AI search (ChatGPT, Perplexity, Claude) and scores gaps
It also activates on plain-language prompts like these:
-
Audit how our brand shows up in ChatGPT -
Check our AI discoverability across LLMs -
Improve our visibility in AI-powered search
Frequently asked questions
- Is the AI Discoverability Audit skill free?
- Yes. The skill itself is free from BrianRWagner/ai-marketing-claude-code-skills. SkillProof publishes the install command and an independent test verdict at no cost.
- Does AI Discoverability Audit work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Fetched SKILL.md via raw GitHub: frontmatter parses with name+description, no scripts referenced, no security smells; bundled references/query-bank.md and SKILL-OC.md both return HTTP 200. Trigger phrasings tested (3 should-fire: "how does my SaaS show up when people ask ChatGPT for recommendations", "run an AEO / AI discoverability audit on my brand", "is my company visible to LLMs like Perplexity and Claude"; 2 should-not: "do a technical SEO audit of crawlability and Core Web Vitals", "write me a ChatGPT prompt to generate blog ideas") — all 5 judged correctly. For output I audited Plausible Analytics against my own Claude knowledge: baseline (110 words) was unstructured prose ending "strong presence, keep publishing comparisons"; the skill-followed artifact (442 words) produced a pre-audit entity-clarity hypothesis that surfaced a genuine miss (the dictionary word "plausible" diluting non-branded queries), a 6-dimension 24/30 score, a same-query-set competitor matrix, tiered gaps, dated 30/60/90-day re-audit checkpoints, and a self-critique flagging that only 1 of 3 platforms was actually queried. Output scored 7 not higher because the multi-platform empirical testing that is the audit's core promise cannot run without web access or manual result-pasting.
- What is the AI Discoverability Audit SkillProof Score?
- 8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.
- How do I install AI Discoverability Audit?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use AI Discoverability Audit with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.