agentleFS
frontmost-aifrontmost-ai/aeo-skills/skills/scan-review/SKILL.md

scan-review

Skill1 starsChanged 3 days agoMITView on GitHub

Review one Frontmost AI scan: what changed since the last scan, which rivals gained, and the first thing to do. Use for "what changed in AI search this week", a metric that moved, or a short team update. Needs a Frontmost AI project.

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 7 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this guidance to review one scan of a Frontmost AI project, to explain why a metric moved, or to write a team update.

    line 8
  2. Very specific:

    If a tool returns setup_required, give the person the url from the result.

    line 14
  3. Very specific:

    If a tool returns plan_required, say that this data needs a paid Frontmost AI plan, and stop.

    line 15
  4. Very specific:

    If the Frontmost AI tools are not available, repeat the mention-check skill each month and compare the counts.

    line 16
  5. Distinctive:

    Never invent the data, and never fill a gap with a guess.

    line 17
  6. Very specific:

    Call get_scan for the project and the scan in the request.

    line 21
  7. Distinctive:

    Read the four KPIs: AI Visibility, Win Rate, Position, and Sentiment.

    line 22
  8. Distinctive:

    Read the KPIs for each AI app.

    line 23
  9. Distinctive:

    Read the questions. List the questions that changed result since the previous scan, with the AI app for each.

    line 24
  10. Distinctive:

    Read the rivals. List the rivals whose mentions went up, with the counts for both scans.

    line 25
  11. Distinctive:

    Do not promise a result. Each recommendation is a bet that the data supports, not a guarantee.

    line 36

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Scan review

Use this guidance to review one scan of a Frontmost AI project, to explain why a metric moved, or to write a team update.

Before you start

This skill reads a Frontmost AI project through the Frontmost AI tools that this plugin connects.

  • If a tool returns setup_required, give the person the url from the result. Stop until they say that set-up is done.
  • If a tool returns plan_required, say that this data needs a paid Frontmost AI plan, and stop.
  • If the Frontmost AI tools are not available, repeat the mention-check skill each month and compare the counts. It needs no account. To read scheduled scans, the person connects Frontmost AI: https://frontmost.ai/connect
  • Never invent the data, and never fill a gap with a guess.

Steps

  1. Call get_scan for the project and the scan in the request. It compares the scan with the previous scan.
  2. Read the four KPIs: AI Visibility, Win Rate, Position, and Sentiment. Take each value, its counts, and its change.
  3. Read the KPIs for each AI app. A change in the total usually comes from one or two AI apps. Name them.
  4. Read the questions. List the questions that changed result since the previous scan, with the AI app for each.
  5. Read the rivals. List the rivals whose mentions went up, with the counts for both scans.
  6. Open the evidence before you explain a change. Copy the row's answers_filter into get_answers. Do not build a filter.
  7. Choose the first thing to do. Use the scan's recommendations when it has them. If it has none, pick the largest gap: the questions where AI apps mention rivals and not the business.

Rules

  • Report each number with its counts, for example "22% · 8 of 36".
  • A change needs two scans. If the scan has no previous scan, say that and report the current state only.
  • Small counts are not a trend. A move of 1 or 2 answers is a move of 1 or 2 answers. Say the count.
  • Give a cause only when the answers show it. If they do not, say "the data does not show why".
  • Link the url of each screen that you describe.
  • Do not promise a result. Each recommendation is a bet that the data supports, not a guarantee.

Output

For a review, write three parts:

  1. What changed: up to 5 points, largest change first.
  2. Who gained: the rivals that gained, with counts.
  3. Do this first: one action. Name the page or site, the action, and the reason in one sentence each.

For a metric question, write one short block for each metric that moved: the AI apps and the questions behind the move.

For a team update, write fewer than 150 words. Start with the largest change. End with the one action. Use no jargon.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.