mcpField
P
principle-attack-the-premise

principle-attack-the-premise

github.com/mariusflorescuAgent workflows1294 installsUpdated 4d ago
Repository

About principle-attack-the-premise

A development skill for diagnosing repeated failed fixes by testing the assumption they share. It guides developers to gather evidence before trying another fix and to address the underlying condition.

Key features

  1. 01Record the shared premise
  2. 02Test the premise before another fix
  3. 03Use failure patterns as evidence
  4. 04Remove causes instead of compensating

Use cases

  1. 01Investigating repeated build or test failures
  2. 02Choosing whether to pursue another fix
  3. 03Finding the condition behind recurring failures

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/mariusflorescu/pstack-t3 --skill principle-attack-the-premise

After installing, type/principle-attack-the-premisein Claude Code to confirm it loaded.

Bundled filesagents/openai.yaml

Details

From the project README

Attack the Premise

When two or more fixes that share one premise have failed the same gate, suspect the premise, not the fixes.

Why: Each failed fix is evidence against the belief it assumed. A third fix on the same premise spends effort where the evidence already says the cause is not.

Pattern:

  • Write the premise down. The premise is the one sentence that every failed fix assumed.
  • Test the premise before the next fix. Find an observation that would come out differently if the premise were false, and make it. Look at how the failures are distributed, not only at how large they are. Make the check rerunnable per Build the Lever.
  • Follow the evidence. If it contradicts the premise, the cause is elsewhere. Look for what the failures have in common that the premise did not predict. If it confirms the premise, ask the next "why" per Fix Root Causes. The earlier fixes may have treated a consequence instead of the cause.
  • Remove the condition instead of compensating for it, per the Laziness Protocol. If the evidence shows that one part always lands on the losing side, change what puts it there. A mechanism that cleans up after it leaves the cause in place and adds work on every run.

Stop: Do not start the next fix before the premise is written down and tested.

This principle is distinct from Redesign from First Principles, which rebuilds a design around a new requirement. It questions a fact the current design assumes.

Comments

Markdown supported