A thank-you note that tells the person exactly what to do again.
A short recognition note built from the specific action, its real effect, and why it mattered to you.
Most thank-you notes say great job and really appreciate it. They are kind and forgettable. The person does not learn what you noticed, and nobody who reads the note learns what good looks like.
Recognition Note asks for the actual action, the effect it had, and the stake for you. It names the behavior to repeat, strips the padding and any buried request, and fits the length to the channel, whether a private message, a card, or a public thread.
What it produces.
- →A finished note of three to five sentences
- →A shorter version for chat or a card
- →The one behavior named so it can be repeated
- →A check that the note could not have been sent to anyone else
- ✦Managers who mean to say thanks and send something vague
- ✦Team members recognizing a colleague outside their reporting line
- ✦Leaders who want praise to teach the team what good looks like
- →recognition-note.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →recognition-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.
I need to write a note to Priya, an analyst on my team, after she caught a pricing error in the Q3 vendor contract on October 14 that would have cost us about $42,000. She flagged it in a two-line email before signing, and it saved us a hard renegotiation later. I want her to keep doing that.
Name the behavior, not the save. The $42,000 is real, but it is the result. What you want repeated is that Priya read the contract closely, found the error, and flagged it before signing, in two lines, without waiting to be asked. If the note only celebrates the money, she learns that big catches get noticed. If it names the habit, she learns that checking before signature is what you value, which includes the times she finds nothing.
Keep it to four or five sentences and send it privately first. Leave out "amazing" and "above and beyond," and do not tack a request onto it. Whether to mention her in a team channel can wait until you have asked her.
Here is a draft:
"Priya, on October 14 you caught the pricing error in the Q3 vendor contract and flagged it in a two-line email before we signed. That error would have cost us about $42,000, and it spared us a hard renegotiation later. I want you to know I noticed how clean the catch was: you found it, told us plainly, and gave us time to fix it. Reading the contract that closely before signature is exactly what I want to keep seeing. Thank you. [Your name]"
Next move: send it today, while the October 14 detail is still fresh, and keep the next contract request in a separate message.
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 paragraph full of adjectives. This starts from what the person did and what changed, keeps it short and proportionate, and removes anything that would make the note sound generic or insincere.
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.
People Playbooks are structuring aids. They are not legal or HR advice. Employment law differs between the US and the UK and between states and countries, so check anything touching dismissal, performance plans, pay, or protected characteristics with a qualified HR professional or employment lawyer.