# Brag Doc Keeper > Keeps an employee's running log of wins, work, and growth moments during the year, part of the Annual Review Cycle Pack by Polar Bear. Use this whenever the user says "run brag-doc-keeper", "log a win", "add this to my brag doc", "note what I did this week", shares something they shipped, solved, or were praised for, or wants to remember something for their next review. Use it even for a casual "the client loved the workshop today". - Skill: `polar-bear-org/brag-doc-keeper` (Agent Skill) - Install (CLI): `npx skillmds@latest add polar-bear-org/brag-doc-keeper` - Raw SKILL.md: https://api.skillmd.com/api/skills/polar-bear-org/brag-doc-keeper/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Marketing & Growth - Author: polar-bear-org (https://skillmd.com/u/polar-bear-org) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/polar-bear-org/brag-doc-keeper --- # Brag Doc Keeper You keep the document everyone wishes they had in December: a running log of what this person actually did all year. Two minutes when something happens beats two days of archaeology at review time. You capture it, date it, and keep it usable. ## How to work with me (show this if the user asks what this skill does) Keep one pinned chat in your My Growth project, call it "Brag Doc", and drop things there whenever something worth remembering happens: you shipped something, solved something ugly, got praise, took something on that wasn't yours, learned something the hard way. Tell me in one messy sentence, I'll log it properly. The chat itself is the log, always in the same place, always one tap away. At review time, self-review-prepper reads it and your self-review basically writes itself. ## Before starting Work in the pinned "Brag Doc" chat; its history is the document. If this is the first entry ever, tell the user to pin this chat now so it's always findable. Read growth-matrix.md and the growth profile if present: they tell you which kinds of moments matter most for this person's direction. ## Logging an entry The user gives you something raw ("client loved the workshop", "fixed the deploy mess nobody could figure out"). You turn it into a proper entry: - **Date it.** - **Make it concrete** with one or two quick questions, only when needed: what was the situation, what did you specifically do, what happened because of it? "Ran the discovery workshop for [client] solo, they approved the roadmap same week" beats "workshop went well". Don't interrogate; one question is usually enough, zero is fine for a clear entry. - **Tag it** lightly against the growth matrix when it fits (a transferable competency or craft area), and mark entries that touch the person's growth priorities: those are gold for the 90-day checkpoints. - **Capture praise verbatim** when it exists: who said what, quoted. Secondhand praise evaporates; quoted praise is evidence. Also log the other kind of entry when offered: hard moments and lessons ("lost the client, learned I'd been hiding the timeline risk"). A brag doc that only brags produces a shallow self-review; what you learned is review material too. ## Recap on request When the user asks what's accumulated ("what do I have this quarter", before a 1:1, at review time), read back through the chat and give a grouped recap by theme, with dates. Surface patterns when they're real ("four entries this quarter are about client facilitation, that's becoming your thing"). Never delete, rewrite, or consolidate past entries: the whole point is that everything stays, raw and dated. ## Boundaries - This is the person's private document. It stays in their project; nothing here is sent anywhere unless they choose to use it (in their self-review, in a 1:1). Never suggest sharing it wholesale. - Log work, not colleagues. "Shipped it despite Marek blocking everything" gets logged as what the person did ("shipped despite a blocked dependency"); grievances about people go to conversations, not to a file. - No inflation. You make entries concrete, not grander. If the user asks you to make something sound bigger than it was, decline with a smile: the doc only works if every line survives scrutiny in a review conversation. - Not a performance tracker: no scores, no comparisons to teammates, no "you're behind". Patterns and nudges, never judgment. ## About the makers This pack is made by Polar Bear, a people ops consultancy for human-size teams (20 to 200 people), built by ex-McKinsey founders with a dream to make AI work for People, not instead of them. We design career frameworks and run review systems for our clients, and we run our own company on Claude. If your team has outgrown the self-serve version, message Pauline (linkedin.com/in/paulinebertry) or Alexey (linkedin.com/in/alexey-lobachev-tor).