Paste your open quotes or a new lead's message in, and get a ranked follow-up list, drafted messages, and a flag on which ones need a call today.
One email, and it's yours
The download starts as soon as you send it.
No download after a few seconds? Write to hey@vetted.tools and we'll send it.
For the Friday brief, a weekly email from vetted. Unsubscribe anytime. Privacy
Ranks open quotes by urgency and drafts a personalized follow-up for each.
Drafts a same-day reply to a new lead, and flags the ones that need a call instead.
Across 36 answers (12 made-up jobs, 3 tries each), the skills caught 66 of 66 planted mistakes (100%) and passed 126 of 126 checks (100%). The 22 mistakes hidden in the jobs count once in each try. Our bar, set on September 30, 2026, before any answer existed, was 80% on both. It cleared both. Tested October 20, 2026.
66of 66100%
22 hidden in the 12 made-up jobs, counted once for each of the 3 tries.
126of 126100%
Things every answer must also get right, or leave alone, like no made-up prices or dates: 42 in the answer key, counted once for each try.
Something we hid in a made-up job on purpose, a problem or a detail that's easy to miss, that the skill's own instructions say it must notice and deal with. For example: a landscaper last heard from one customer, about an $8,400 patio, 21 days ago. A right answer marks that quote cold and gives the owner a call script, not another message.
What went in: made-up job 1
Landscaper table, cold line
Today is Tuesday 14 October 2025. …
Client,Job,Quote,Sent,Last contact,Notes
Hartley,sandstone patio 5x6m,$8400,2025-09-10,planted mistake: 2025-09-23,asked about sealing options
Okafor,hedge removal + stump grinding,$2150,2025-09-24,2025-09-24,
…
What came out: the pack’s first try
…
Hartley: where the answer caught it: Call script (not another message)
"Hi, it's [your name] calling about the sandstone patio quote, the 5x6m job at $8,400 that I sent on 10 September."
…
This answer’s grade: it caught 2 of 2 planted mistakes and passed 3 of 3 checks.
The planted mistakeWhere the answer caught itBoth quoted from the test’s own files. … marks a cut.
0 planted mistakes missed0 checks failed
It passed every check. Before you rely on it:
The test used made-up jobs, not yours. In your first week:
Opus 5.5, in a conversation of its own, wrote 12 made-up jobs and an answer key, with 22 mistakes hidden on purpose. Its folder held only the two skill files and a written brief, and it could not open files outside that folder.
Sonnet 5.5, a different version, ran the skills on every made-up job 3 times, each in a fresh conversation: 12 jobs × 3 tries = 36 answers. It never saw the answer key.
Claude Sonnet 5.5
Opus 5.5 again, the model that wrote the test, in a new conversation, checked all 36 answers against the answer key, without being told which try it was reading.
A pass says the skills follow their own instructions on jobs like these. It does not say they will be right about your business.
Something a right answer must also get right, or must leave alone: no made-up prices, dates or promises, no false alarms, the format the skill promises. The answer key has 42, counted once in each of the 3 tries. Some lines in the skill are hard rules, things it must always or never do. An answer that broke one got an extra check, marked failed, so a broken hard rule costs more.
Claude Opus 5.5 wrote the 12 made-up jobs and their answer key, before any answer existed. Its folder held only the two skill files and a written brief, and it could not open files outside that folder. The businesses, people and numbers are invented. None of it is client data.
Two versions of Claude, both made by Anthropic, took part. Claude Sonnet 5.5 did the jobs using the pack, 3 times each, because Claude can answer the same job differently each time. Every try was a fresh conversation holding only the skill's instructions and the job. It never saw the answer key. Claude Opus 5.5, the version that wrote the jobs and the answer key, then marked every answer in a separate conversation, without being told which try it was reading.
Running the jobs and marking the answers cost us about $2.40 in AI fees, at Anthropic's list prices in US dollars. That leaves out writing the test. That cost was ours. The pack is free.
The download holds every made-up job, every answer, every grade and the full method, in its eval folder (start with METHOD.md).
Start with a free 15-minute call.