# Skill

> Walks into the 1:1 knowing what you owe them, which is the half most prep skips.

- Skill: `kesslernity/skill` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx get-skill add kesslernity/skill`
- Raw SKILL.md: https://api.skillmd.com/api/skills/kesslernity/skill/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: kesslernity (https://skillmd.com/u/kesslernity)
- Updated: 2026-11-19
- Page: https://skillmd.com/skills/kesslernity/skill

---


# One-to-One Prep

Walks into the 1:1 knowing what you owe them, which is the half most prep skips.

## Inputs
- **Email**, **Meetings** and Teams traffic between the user and that person
- `references/config.md` for the window and what counts as a commitment
- The prior brief, if one exists, so items do not reappear as new

## Procedure
1. **Scope to the two people.** Threads where both are present. A group thread counts only if the
   person contributed to it.
2. **Build four lists, in this order:**
   - **What you owe them.** Commitments the user made, quoted and linked. **This section is
     first, deliberately.** Most 1:1 prep covers what the report owes the manager and the
     inversion is the useful part.
   - **What they owe you.** Same treatment.
   - **What they raised** that received no substantive reply.
   - **What changed** in their work since the last 1:1, from evidence, not inference.
3. **Carry forward** anything from the prior brief still unresolved, marked as carried, with the
   count of times it has carried. An item carried three times is the agenda.
4. **Stop there.** No suggested questions, no coaching prompts, no tone advice.

## Output
Four lists, every item quoted and linked, with carried items marked and counted.

## Definition of done
Both directions of commitment are covered, carried items show their count, and nothing is
inferred about the person.

**An empty brief is a good sign.** "Nothing outstanding in either direction since the last 1:1"
is a complete and useful answer.

## When there is no data
- No traffic in the window: say so with the date of the last exchange.
- No prior brief: say this is the first, so nothing carries.
- Group threads only: say the direct channel has been quiet, which is itself worth noticing.

## Boundaries
- 🔴 **Never assess, rate, or characterize the person.** No performance language, no sentiment
  read, no "seems disengaged". This skill reports commitments and questions, and nothing about
  how someone is doing. That line is absolute: a drafting tool that editorialises about a
  colleague is a liability to the user who runs it.
- Never read 1:1 notes about this person written by someone else.
- Never draft feedback, and never prepare anything for a performance process.
- **Draft only**, and the brief is for the user alone.

## Self-check
- Is "what you owe them" first?
- Is every item quoted with a link rather than summarised?
- Did I avoid every characterisation of the person?

