Brag Doc

Brag Doc Skill

Nobody remembers in December what they shipped in March — so good work goes uncredited at review time. A brag doc is the fix: a running, dated log of what you did and the impact it had, captured while it's fresh. This skill turns a pile of "stuff I did" into impact-first entries you can paste straight into a [self-review](../self-review/SKILL.md) or [promotion-packet](../promotion-packet/SKILL.md).

Required Inputs

Ask for these only if they aren't already provided:

• The win(s) — what you did (rough notes are fine; the skill structures them).
• Impact — the outcome and any metric (before → after, time saved, revenue, users) — even a rough one.
• Scope & role — your specific contribution vs. the team's, and who it affected.
• Date / period and any evidence (PR, doc, dashboard, kudos, ticket link).

Output Format

Brag Doc — [your name], [period]

Entries newest-first, grouped by theme (or quarter). Each entry is impact-first:

> [Verb-led headline — the outcome, not the task] · [date] > - What I did: [the specific action and your role in it] > - Impact: [metric / outcome — before → after where possible] > - Scope: [who/what it affected — team, org, customers] > - Evidence: [link] > - Maps to: [the competency / ladder level it demonstrates — e.g. "cross-team influence"]

Example:

> Cut onboarding drop-off 18% → 9%, unlocking ~$140k ARR · Mar 2026 > - What I did: led the redesign of the 3-step signup flow; wrote the PRD, drove eng + design alignment. > - Impact: activation 41% → 52%; drop-off halved (measured over 6 wks, 20k users). > - Scope: owned end-to-end; affected all new signups. > - Evidence: [PRD] · [dashboard] > - Maps to: drives measurable product outcomes; cross-functional leadership.

End with a "Themes this period" summary — the 3–4 narrative threads your wins ladder up to.

Quality Checks

• [ ] Every entry leads with impact/outcome, not the activity
• [ ] Metrics include the baseline (before → after), not a bare percentage
• [ ] Your specific contribution is distinguished from the team's
• [ ] Each entry links real evidence
• [ ] Entries are tagged to a competency/ladder level, so the doc feeds a review or promo case directly

Anti-Patterns

• [ ] Do not log tasks ("attended planning", "wrote code") — log outcomes ("shipped X, which moved Y")
• [ ] Do not wait until review season — capture wins within a week, while the metrics and context are fresh
• [ ] Do not inflate or claim team wins as solo — overstated credit is worse than none when a manager checks
• [ ] Do not omit the metric because it's imperfect — a rough, labelled estimate beats "improved things"
• [ ] Do not bury the evidence — an unlinked claim is one a busy manager can't verify or champion

Based On

Brag-document practice (Julia Evans) and impact-first accomplishment tracking.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: mohitagw15856
• Source: mohitagw15856/pm-claude-skills
• License: MIT
• Homepage: https://mohitagw15856.github.io/pm-claude-skills/

Install and usage instructions live in the source repository linked above.