A thank-you note that only you could have written.
A short thank-you note built from what the person did, when, and what changed because of it.
Most thank-you notes could be sent to anyone: thanks so much, really appreciate it. The reader files them as a courtesy and forgets them, because nothing in them proves you noticed.
Thank-You Note asks for the act, the date, and the effect, then writes two to five sentences around those details. It keeps requests out of the note, and a believability check replaces any phrase that could appear in someone else's note with a detail only you know.
What it produces.
- →A one-sentence statement of exactly what the person did
- →The effect it had, in your honest terms
- →A note sized to the channel and relationship, from two sentences to about 90 words
- →A flag for any hidden ask, split into a separate message
- ✦Job seekers after an interview or a referral
- ✦Professionals thanking a mentor, a referrer, or a colleague who covered for them
- ✦Account managers acknowledging a client renewal
- →thank-you-note.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →thank-you-note-skill.md: plain markdown. Works in ChatGPT Custom GPTs, Gemini, Claude Projects, agent system prompts, anywhere
- →A README inside the zip with install steps for Claude, ChatGPT, and Gemini
What it does with a real question.
My manager, Dana Okafor, spent about three hours last Thursday helping me rebuild the pricing model for our Q3 renewal with a mid-size logistics client. She walked me through the discount tiers and caught a formula error that would have cost us roughly $12,000. I want to thank her in a short email.
Keep it to about 70 words, and let the $12,000 do the work. Dana already knows she helped you. What she may not know is how it landed, so the note should tell her.
The three hours on Thursday and the caught formula error are the two details only you could write, so both go in. The dollar figure is the effect, and it should appear once, plainly, without dressing it up. Skip "I really appreciate your support." It could be sent to any manager about anything, and she would read it as a courtesy.
One caution: do not tuck in a request, such as asking her to review the next model. Save that for a separate message later, or the thanks will read as a setup.
Here is a draft you can send today:
Subject: Thank you for Thursday
Dana, thank you for the three hours you spent with me on the Q3 logistics renewal. Walking me through the discount tiers made the model make sense, and your catch on the formula error would have cost us roughly $12,000. I rebuilt the tiers on your logic, and I will send you the final version before it goes to the client.
Your next move: send this as an email today rather than waiting for a card or a better moment. Prompt thanks reads as sincere, and the closing line gives her a small, real update to expect.
The full Playbook runs the whole procedure and writes the complete deliverable, not this excerpt.
Written by claude-sonnet-5-5 with this Playbook loaded, 2026-10-11. Checked automatically for length and for copied framework text.
No subscription · free updates within v1.x
Works as a Claude Skill (.zip) and as a plain .md for ChatGPT, Gemini & every LLM
Delivered to your email within 60 seconds · Secured by Stripe
Price includes UK VAT where applicable
Before you buy.
How is this different from just asking Claude directly?
Asked cold, Claude writes a warm and fluent note that is mostly general gratitude. This Playbook demands the specific act and effect first, then tests every line to see whether anyone else could have written it.
How is this different from a Tool?
Playbooks are systematically produced to a fixed template and priced accordingly ($12.99). Tools are hand-built, one at a time, and go deeper ($39 to $199). A Playbook gives you a reliable method for routine work; a Tool is for when the judgment matters more than the format.
Will this work with ChatGPT, Gemini, and other LLMs?
Yes. You get a native Claude Skill (.zip) that auto-invokes in Claude, plus a plain .md you can paste into a ChatGPT Custom GPT, a Gemini system prompt, or any LLM. The procedure travels with the file.
Can I share this with my team?
It's licensed for your own personal and professional use. The output it produces is yours to circulate. To put the Playbook itself in the hands of a whole team, email hello@authority.md about team licensing.
What if it doesn't work for me?
If the file hasn't been delivered, or arrives defective or empty, we refund in full: see our refund policy.