SkillsAEO Prompt Audit: Agent Skill
AEO Prompt Audit: Agent Skill
Clean up a tracked AI-visibility prompt list: keep, rewrite or remove every prompt with a written reason, plus a coverage table and a safe retire plan.
Get full access to this skill and the tools to run it
For agents
Your AI gets this skill, your clients' context and the research tools, in Claude or any MCP client.
Connector URL: https://mcp.unilytics.ai/mcp
What you get
A two-sheet workbook: every prompt with its decision (keep, rewrite, remove or review), the reason and any rewrite beside the old wording, then a summary sheet with the counts and the prompts left for the owner to review. It also gives a table of which topics the prompts cover, and a plan for dropping the ones you remove.
Deliverable: Workbook
When to use it
Cleaning up a list of tracked prompts that has grown messy.
The steps
The skill takes your agent through these steps, in order. Each step's full instructions come with the skill when you run it through Unilytics.
- Why this audit, in one line
- Freeze the live set
- Scope the audit with the owner's words
- Provenance: join every prompt to where it came from
- The decision rules
- Hand decisions, at scale
- Harmonize across batches
- Coverage check on what survives
- The deliverable
- Retire safely
The full skill also covers: File map · Before you start · Definition of done · Gotchas · Rules for this skill.
Tools it needs, with or without Unilytics
Straight from the skill: the data each step needs and the tools that can supply it. Unilytics is one option, never a requirement.
| Capability | Ways to get it |
|---|---|
| Export the tracked prompt set (ids, text, tags, visibility, citations) | The prompt-tracking platform's export or API |
| Search Console long tail for grounding and the echo check | Your own Search Console connector or export |
| Keyword volume for seed keywords | Keywords Everywhere, DataForSEO, Ahrefs or Semrush; or the Unilytics MCP keyword_research |
| Modelled prompt volume | The tracking platform's volume field; or the Unilytics MCP aeo_prompt_volume |
| Spot-check how engines answer a prompt or describe the brand | The tracking platform, or the engines directly; or the Unilytics MCP brand_visibility |
| Automated first-pass triage of a prompt list (keep / cut / rewrite hints) | Optional; the Unilytics MCP aeo_audit_prompts (a keep, cut or rewrite hint per prompt) |
| Prior keyword research and its keyword map | The client's keyword research workbook; or the Unilytics MCP kb_search if it was stored there |
| Build the workbook | Any spreadsheet tool; in Python, openpyxl |
Without the Unilytics MCP
Every step runs without Unilytics. Without it, what you lose is one connection for several of the capabilities above: each one then comes from the other ways listed for it (a tool or account you already have, a vendor API, or a manual export). The Unilytics MCP is one optional way to get several of these tools in a single connection: https://unilytics.ai
New accounts start with 50 credits. Connecting, and reading your skills, projects and client context, costs nothing; research tools and some writes use credits.