Back

Principle Explain The Number

Research & search7.2K installs

What it does

Apply before you measure, and 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.

Install

npx skills add https://github.com/backnotprop/pstack --skill principle-explain-the-number

Website

www.skills.sh/backnotprop/pstack/principle-explain-the-number

Details

From the skill’s SKILL.md or README, by its authors. View the original

Explain the Number

  • Write the decision before you run. Name the result that would change a decision, and the noise floor. Stop when the run-to-run spread is larger than the effect.
  • 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 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 a run started without the result that would change a decision, 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, which checks that an output is real.

More Research & search skills

See all

  • Research & search

    Research

    Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

    npx skills add https://github.com/mattpocock/skills --skill research
    783.1K installs

  • Research & search

    Azure AI

    Build and troubleshoot Azure AI Search, Speech, OpenAI, and Document Intelligence apps. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, Speech SDK logs, session ID, result ID, OCR, convert text to speech.

    npx skills add https://github.com/microsoft/azure-skills --skill azure-ai
    651.7K installs

  • Research & search

    Azure Resource Lookup

    List, find, and show Azure resources across subscriptions or resource groups. Handles prompts like \"list the websites in my subscription\", \"list my web apps\", \"show my app services\", \"list virtual machines\", \"list my VMs\", \"show storage accounts\", \"find container…

    npx skills add https://github.com/microsoft/azure-skills --skill azure-resource-lookup
    649.6K installs

  • Research & search

    Caveman Stats

    Show recorded output and cache-read token usage and mode attribution for the current Claude Code session, or locate the host's native usage report. Trigger: /caveman-stats.

    npx skills add https://github.com/juliusbrussee/caveman --skill caveman-stats
    373.3K installs

Skills are shared by members and not reviewed by us. Read a skill’s code before you install it.