agentleFS
frontmost-aifrontmost-ai/aeo-skills/skills/placement-tracker/SKILL.md

placement-tracker

Skill1 starsChanged 3 days agoMITView on GitHub

Build and refresh a spreadsheet of the cited pages that do not list the business: outreach status, quote, cost per citing answer, and the answers that name the business after a listing goes live. Use to track listicle outreach. Needs a Frontmost AI project.

The file

Show its rules and text

We split this skill into the rules it gives an agent

15 rules. About 0 are common, 8 are distinctive, and 7 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 7

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this guidance to build a working sheet of the cited pages that do not list the business.

    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, use the source-map skill.

    line 16
  5. Distinctive:

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

    line 17
  6. Very specific:

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

    line 21
  7. Very specific:

    Add the working columns: Contact, Status, Quote, Paid, Go-Live Date, Note.

    line 35
  8. Distinctive:

    Add two calculated columns:

    line 36
  9. Distinctive:

    Do this when the person asks to refresh or update the sheet.

    line 44
  10. Very specific:

    Read the Page column. Call get_sources with page_urls for those pages, 50 in each call.

    line 46
  11. Distinctive:

    Keep every other cell as the person typed it.

    line 48
  12. Very specific:

    Call get_sources with no page_urls, for all questions.

    line 50
  13. Distinctive:

    Keep the two question scopes in two columns.

    line 57
  14. Distinctive:

    Never suggest paid links, fake reviews, fake accounts, or a promised result.

    line 60
  15. Distinctive:

    Ask before you change anything in Frontmost AI.

    line 61

≈ “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

Placement tracker

Use this guidance to build a working sheet of the cited pages that do not list the business. The person works one row from first contact to a listing, then sees if AI apps name the business after it.

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, use the source-map skill. It needs no account, and it works from a web search. To read the pages that AI answers cite, with counts, the person connects Frontmost AI: https://frontmost.ai/connect
  • Never invent the data, and never fill a gap with a guess.

Build the sheet

  1. Call get_sources for the project and the scan in the request. Then call it with page_urls for the pages in pages_to_get_on and questions: "unbranded", 50 pages in each call.
  2. Make one row for each page in pages_to_get_on. The row key is the page url. Never change it.
  3. Fill the Frontmost AI columns from the data:
ColumnValue
Pageurl
Typetype
Answers Citing Itanswers from the first call
Unbranded Answers Citing Itanswers for the same url in the second call
Rivals Listedthe names in rivals where listed is true
Lists Youyou: Present, Not present, or Check needed. A refresh can also write No current read
Listing Checked Onchecked_on
  1. Add the working columns: Contact, Status, Quote, Paid, Go-Live Date, Note. Leave them empty. The person fills them in, or the listicle-outreach skill does. Status uses the states of that skill. This skill never changes a working column on a refresh.
  2. Add two calculated columns:
    • Cost per Citing Answer = Paid ÷ Answers Citing It. Leave it empty when Paid is empty.
    • Answers Naming You Since Go-Live. For a row with a Go-Live Date, copy the row's answers_filter into get_answers, set since to that date, and add named: true. Write total.
  3. Above the table, write the counted period from counted.window: the rule, then from and to as dates, then the number of scans in counted.scans.
  4. Sort by Answers Citing It, largest first.

Refresh the sheet

Do this when the person asks to refresh or update the sheet.

  1. Read the Page column. Call get_sources with page_urls for those pages, 50 in each call. Do it for both question scopes.
  2. Match each returned row to a sheet row by url. Rewrite only the Frontmost AI columns and the two calculated columns.
  3. Keep every other cell as the person typed it. Keep the row order.
  4. A page in not_found keeps its row. Write "No current read" in Lists You.
  5. Call get_sources with no page_urls, for all questions. Add a row for each page in pages_to_get_on that the sheet does not have.
  6. Rewrite the counted period above the table.

Rules

  • A page with you equal to Check needed is not confirmed. Never tell the person to pitch it before a check.
  • Report each count with its total, such as "16 of 160 answers".
  • Keep the two question scopes in two columns. Never add them.
  • "Answers Naming You Since Go-Live" shows what happened after the date. It does not prove that the listing caused it. Say so once below the table.
  • Say the date in checked_on when it is more than 7 days old.
  • Never suggest paid links, fake reviews, fake accounts, or a promised result. A quote for a sponsored listing is the person's decision. Never ask a publisher to hide that a listing is paid.
  • Ask before you change anything in Frontmost AI. This sheet reads only.

Output

A spreadsheet file with one table, the counted period above it, and a link to the url of the Sources tab. If the AI app cannot make a file, return the same table as CSV.

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.