# Principle Explain The Number

Apply before you trust, report, or act on a number you measured: a speedup, a...

- Repository: https://github.com/nightly-labs/openbot (4509 stars)
- Category: Engineering
- License: see repository
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add nightly-labs/openbot --skill principle-explain-the-number -g -a claude-code -y`
Codex: `npx skills add nightly-labs/openbot --skill principle-explain-the-number -g -a codex -y`
Cursor: `npx skills add nightly-labs/openbot --skill principle-explain-the-number -g -a cursor -y`
Gemini CLI: `npx skills add nightly-labs/openbot --skill principle-explain-the-number -g -a gemini-cli -y`

## Description

Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Explain the Number

- **Ask "why not double?"** Name the resource or code path that bounds the result, such as a core, a lock, the disk, the network, or the load generator itself. Get it from a profile or from system counters taken during a run, then map it to source. A guess from reading the code is not a limiter. If you cannot say why the number is not twice as good, you do not know what you measured.
- **List what else the number could be measuring, and rule out each one with evidence.** The usual suspects are errors, skipped or cached work, code that never ran, an untuned side (one left on default settings), noise, and a piece too small to matter end to end.
- **Keep the evidence with the number.** Put the run count, the spread, and the limiter in the notes or a linked artifact.

For a performance number, run the full procedure with the [benchmark-checklist](../benchmark-checklist/SKILL.md) skill. For an eval result, ask the same of the trials: did every run do the task, does the gap hold across trials and models, and does the scenario matter.

You skipped this when the evidence behind a number has no run count, no spread, or no named limiter, or when the time saved is larger than the time the changed piece took.

Distinct from [Prove It Works](../principle-prove-it-works/SKILL.md), which checks that an output is real.