Counts the fields of ad and store copy against the published limit of each platform (Google responsive search ads, App Store product page, Google Play listing, X and LinkedIn posts) and returns a line only for each field that is over, with the exact count, the limit, the unit and a shortened version that fits - or exactly No findings. It counts by the platform's own rule: double-width characters in Google Ads, bytes for the App Store keywords, the fixed length of a link and the double weight of an emoji on X. Fields that fit are left out, including a field exactly at the limit. Use before pasting copy into an ad account, an app store console or a scheduler, to find which field a platform rejects or cuts, or when copy written for one platform has to be reused on another.
Platform Text Limits is a tested SKILL.md that counts the fields of ad and store copy against the published limit of each platform (Google responsive search ads, App Store product page, Google Play listing, X and LinkedIn posts) and returns a line only for each field that is over, with the exact count, the limit, the unit and a shortened version that fits - or exactly No findings; an agent buys it once for $0.01 over x402.
Not for
Ad policy, the persuasiveness or tone of the copy, banned words, translations, image sizes, the optional fields of each platform and any platform that is not in its table. A platform or field outside the table gets one line saying so, with no count and no invented limit.
Tested, honestly
Tested 2026-10-19 with a strong and a weak model.
- SonnetStrong model, claude-sonnet-5-5
- Right on all 3 cases, read by hand. On the search ad it reported headline 2 at 35 of 30 and description 2 at 114 of 90, with shortened texts of 25 and 85 characters, and left out the headline of exactly 30 characters. On the App Store listing it counted the keywords as 110 bytes and left out the subtitle of exactly 30. On the X post it answered exactly No findings.
- HaikuWeak model, claude-haiku-5-5
- Right on all 3 cases, read by hand. It gave the same two counts for the search ad with shortened texts of 25 and 90 characters, the byte count of 110 for the keywords, and exactly No findings for the X post. The longest shortened text sat exactly on the limit of 90, which is allowed. Both models kept the numbers, the prices and the sixty-day returns promise of the original description, and neither invented a claim.
Full test summary
Example
Our own test text, before and after the skill ran. Excerpts only.
English · claude-sonnet-5-5
Before
Platform: Google Ads, responsive search ad
Headline 1: Handmade Leather Wallets Today
Headline 2: Free Delivery On Orders Over 40 USD
Description 1: Slim wallets and card holders cut from full-grain leather, made by hand in our workshop.
Description 2: Full-grain leather wallets, made by hand in our workshop. Free returns for 60 days. Free delivery over 40 dollars.
Path 1: wallets…
After
OVER-CHARS — Google responsive search ad, headline 2 — 35 of 30 characters — "Free Delivery Over 40 USD"
OVER-CHARS — Google responsive search ad, description 2 — 114 of 90 characters — "Handmade full-grain wallets. Free returns for 60 days. Free delivery over 40 dollars."
What is in the file
- The answer
- The fields (as published by each platform on 19 October 2026)
- The codes
- How to count
- Rules
- Work in this order
- Short example
Languages
English. Tried in: English.
License
Perpetual, non-exclusive; use and modify for yourself incl. paid work; no resale or republishing. Holder: Georgi Kalchev, aiskills402.com. Full terms.
Versions
Current version 1.0.0, updated 2026-10-19. Whoever bought an earlier version gets new ones free through the same re-download token.
v1.0.0 · 2026-10-19
First release, written in the light-test batch of 19 October 2026 (three cases, price $0.01). The idea is ours; no foreign skill was opened, facts come from public pages (see notes/ideas.md). Output: one line per finding with a fixed code, or exactly `No findings.`
Test: three cases written by hand (a Google search ad with two fields over, French App Store keywords counted in bytes, and an X post that fits once the link counts 23), one run on Claude Sonnet and one on Claude Haiku, no run without the skill, no iteration on the skill text after the runs. `test/control.mjs` shows that the checks pass on the ideal answers and fail on realistic wrong ones. See `test-summary.json` for the verdicts read by hand.
FAQ
Where does a field exactly at the limit appear in the answer?
Nowhere. A headline of exactly 30 characters or a subtitle of exactly 30 fits, so it stays out of the answer. Only fields that are over get a line, each with the count, the limit, the unit and a shortened text that the skill counts again before it answers, so that a person can paste it straight into the field.
Why does the App Store keywords field get its own code?
Apple counts that field in bytes, not characters, so a list of 100 characters with accented letters can be 110 bytes, which is the French example in the test. The skill counts the bytes, and the commas between keywords count too.
What was counted in the trial?
A search ad with a headline of 35 characters and a description of 114, French App Store keywords of 100 characters that weigh 110 bytes, and an X post of 339 characters whose weighted count is 271. Claude Sonnet and Claude Haiku each ran once, and both answers were right when every count was checked by hand with a script.
What does copy that fits return?
The one sentence No findings., never a table of the fields that fit. Every other line is a field to fix, so a script can read the answer line by line.