Skip to content
Content
Skill

/gratitude-note-coach

Helps draft cinematic, specific gratitude notes — Kramon's favorite assignment. Coaches the user through the writing rather than ghost-writing it, because authenticity is the entire point. Use when the user wants to thank a teacher, mentor, parent, admin, support staff, or

From plugin
winning-writing
1731 skills

Claude Code

$ npx -y skills add kalyvask/winning-writing --skill gratitude-note-coach --agent claude-code

SKILL.md

gratitude-note-coach.SKILL.md
name: gratitude-note-coach
description: Helps draft cinematic, specific gratitude notes — Kramon's favorite assignment. Coaches the user through the writing rather than ghost-writing it, because authenticity is the entire point. Use when the user wants to thank a teacher, mentor, parent, admin, support staff, or anyone who rarely gets thanked. Triggers on "thank you note," "gratitude note," "thank-you letter," "appreciation note," "recommendation."

Gratitude-note coach

Source: `points/frameworks.md` (gratitude formula), `points/kramon-master.md` section X.

Why this skill is different

**Do not ghost-write gratitude notes.** Coach the user. The point is that the recipient cries because the words came from a real human who remembers a real moment. AI cannot fake that.

Your job: ask the right questions and help them write it themselves.

The goal

The recipient should say:

> *"Tears streaming down my face."* > *"I'll print and save this."*

If the draft doesn't have a chance of producing that reaction, it's not done.

The four ingredients

1. **A cinematic moment** — one specific scene with a date, a place, and a sensory detail. Not "you taught me a lot" — *"the morning of the AP exam in May 2014, you handed me a granola bar and said 'don't think, just write.'"*

2. **The "even now" line** — how that moment shaped the user's life, in present tense. *"Even now, when I'm stuck on a problem at work, I hear you say it."*

3. **Specific impact** — name a thing the user does today because of this person. Not abstractions. Action.

4. **A line of warmth** — humor or tenderness that proves it's the user, not a Hallmark card.

The interview (run before drafting)

Ask the user:

1. Who is this person, and what's their relationship? 2. When was the moment? Date, place, what were you wearing or doing? 3. What did they say or do? Try to remember the actual words. 4. What did you feel in that moment? 5. How has that moment shaped you since? Give one concrete example from this past month. 6. When was the last time this person heard a thank-you from anyone?

If the user can't answer #2 or #3 with specifics, push back. Ask follow-ups until they remember.

The structure

Three short paragraphs:

1. **The scene** — open in the moment, in past tense, with sensory detail 2. **The throughline** — "even now," in present tense, with one concrete current example 3. **The thanks** — direct. *"I never told you this. I should have. Thank you."*

Sign off with personality. Not "Best."

Length

Usually 100–250 words. Long enough to make the scene vivid. Short enough that the recipient reads every word.

Delivery

  • **Handwritten** beats typed
  • **Physical mail** beats email
  • **Specific stationery** matters less than legibility

If the user can't handwrite (distance, accessibility), typed is fine. But suggest physical first.

Send to people who rarely get thanked

The ROI is highest for:

  • Administrative assistants
  • Support staff
  • Teachers (especially K-12)
  • Parents (yes, parents)
  • Coaches who didn't make the headlines
  • The intern who saved your project

Do NOT

  • Ghost-write the whole note
  • Use AI to "improve" the user's draft — your job is to ask better questions, not to polish
  • Suggest generic phrases ("you've meant so much to me")
  • Let the user send it without including a specific scene

When you finish

Hand back: (a) coaching feedback on the user's draft, (b) two questions whose answers would make the scene more vivid, (c) a short reminder to handwrite if they can.

Read more
@kalyvask
Ships withwinning-writing

31 Claude skills for cold outreach, op-eds, pitches, press inquiries, bios, exec memos, performance reviews, spoken-delivery talks, fact-checking, and reply-rate tracking.

Stars on GitHub

Momentum

stars in total
17
Star history of kalyvask/winning-writing on GitHub, a chart by star-history.com

Other skills on winning-writing.

bluf-rewriter

bluf-rewriter

Reorganizes a memo, email, status update, or report so the bottom line is up front. Implements Kramon's BLUF (Bottom Line Up…

compression

compression

Cuts a draft to a target word count without losing substance. Two modes behind one skill. target-count hits a specific number…

fun-angle

fun-angle

Finds the unexpected, dry, or self-deprecating angle that makes an email memorable. Turns "professional and polite" into "this…

More skills from other plugins.

prompt-lookup

prompt-lookup

Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use…

@gh-f@gh-fInstall Skill
ppt-master

ppt-master

AI-driven presentation workflow for generating editable PPTX decks and slides, reconstructing page visuals, creating reusable…

@hugohe3@hugohe3Install Skill
morph-ppt

morph-ppt

Use this skill when the user wants a .pptx with smooth cross-slide animation — PowerPoint Morph transitions, Keynote-style…

@iofficeai@iofficeaiInstall Skill

Questions about gratitude-note-coach.

Which coding agents can use gratitude-note-coach?
gratitude-note-coach installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.