Skip to content

Client onboarding pack: kickoff and follow-through with Claude

Paste a new client's intake answers in, and get a tailored checklist, a kickoff email, and a flag on anything you need before you can start.

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

What’s inside

  • kickoff-packet

    Turns a new client's intake answers into a checklist, a kickoff email, and a handoff note.

  • onboarding-nudges

    Flags stalled onboarding steps and drafts the nudge, before a start date slips.

How we tested this

Across 36 answers (12 made-up jobs, 3 tries each), the skills caught 62 of 63 planted mistakes (98%) and passed 128 of 138 checks (93%). The 21 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.

Tested

Planted mistakes caught

Above our 80% bar

62of 6398%

21 hidden in the 12 made-up jobs, counted once for each of the 3 tries.

Checks passed

Above our 80% bar

128of 13893%

Things every answer must also get right, or leave alone, like no made-up prices or dates: 44 in the answer key, counted once for each try, plus 6 for answers that broke a hard rule.

What a planted mistake is

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 client writes that she'll sign the contract once she sees the final price. A right answer lists the signed contract as missing before kickoff, and the kickoff email asks her to sign it.

What went in: made-up job 1

Kitchen remodel, forwarded email

Fwd: Re: kitchen quote

…

> - Full kitchen remodel at 41 Larkspur Lane, Millbrook: …

> - I sent the 25% deposit by bank transfer this morning.

…

> planted mistake: I'll sign the contract once I see the final number with the island plumbing included.

What came out: the pack’s first try

Subject: Next steps for your Larkspur Lane kitchen remodel

…

Once you've reviewed that number, where the answer caught it: please sign the contract and send it back to us.

…

4. Missing-info flag

Missing before kickoff can start:

Signed contract. where the answer caught it: Renata has not signed. She says she'll sign once she sees the final number.

…

This answer’s grade: it caught 3 of 3 planted mistakes and passed 4 of 4 checks.

The planted mistakeWhere the answer caught itBoth quoted from the test’s own files. … marks a cut.

Where it fell short

1 planted mistake missed10 checks failed

What it still gets wrong:

  • Its reminders ask the client to do things "today" or "tomorrow" when nobody set that deadline. The grader marked it down on one job, but the same ask shows up on 3 others.
  • A few small made-up details: "no deposit" when the intake never said, a referral who "spoke highly" of the client, an invite "not sent" when the step was only under way.
  • Once, it counted the deadline day itself as a working day left. It still called the risk right.
  • One answer named a blocked step in two places, which cost 2 checks. Another answer did the same and passed.

Try it on your own jobs first

The test used made-up jobs, not yours. In your first week:

  • Run the skills on a few jobs you've already handled.
  • Compare their drafts with what you actually sent.
  • Read every draft before it goes to a customer: you decide what goes out.

How the test ran

  1. Claude Opus writes the test

    Opus 5.5, in a conversation of its own, wrote 12 made-up jobs and an answer key, with 21 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.

    Claude Opus 5.5

  2. Claude Sonnet does each job 3 times, using the pack

    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

  3. Claude Opus grades every answer

    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.

    Claude Opus 5.5

Read the details
What it does not prove

A pass says the skills follow their own instructions on jobs like these. It does not say they will be right about your business.

  • The jobs are made up, and 36 answers from one model on one day is a small test.
  • We tried to leave out jobs where the skills' own instructions don't clearly say what to do, so this test can't tell you how they handle those. The list is in METHOD.md, in the download.
  • The grader is also an AI, the same model that wrote the jobs and the answer key, so the two can share blind spots, and no person checked its grades.
  • Every answer and every grade is in the download, so you can check them yourself.
What a check is

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 44, 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. That happened 6 times.

Where the made-up jobs came from

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.

Who answered, and who graded

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.

What the test cost us

Running the jobs and marking the answers cost us about $2.64 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 full detail

The download holds every made-up job, every answer, every grade and the full method, in its eval folder (start with METHOD.md).

Want this set up for your business?

Start with a free 15-minute call.

Talk to usPick a 15-minute slot(opens our calendar in a new tab)