agentleFS
Sign inStart free
fullerzzfullerzz/agent-skills/skills/principle-attack-the-premise/SKILL.md

principle-attack-the-premise

Skill2 starsChanged 29 days agoMITView on GitHub

Apply when two or more fixes sharing a premise fail the same gate. Write down and directly test that premise before another fix assumes it.

We split this skill into the rules it gives an agent

2 rules. 1 is common, 1 is distinctive, and 0 are very specific to this project.

  • 1

    Common

    Most of the 31 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Common:

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

    line 9
  2. Distinctive:

    Stop: Write down and test the premise before another fix assumes it.

    line 19

“Common” is measured: kept by at least 6 in 10 of the 31 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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 failure under a shared premise is evidence about the premise.

Pattern:

  • Write the premise down. The premise is the one sentence that every failed fix assumed.
  • Test it directly. Choose an observation that would differ if the premise were false. Examine failure distribution across relevant actors, inputs, or times; a per-actor census is one possible check. Make the check rerunnable per Build the Lever.
  • Follow the evidence. Contradictory evidence redirects the investigation. Supporting evidence calls for the next "why" per Fix Root Causes: earlier fixes may have addressed a consequence. An inconclusive check does not settle the premise.
  • Remove the demonstrated cause within scope, per the Laziness Protocol, rather than adding recurring compensation. For example, if a fixed coordinator assignment overloads the same worker, address that assignment.

Stop: Write down and test the premise before another fix assumes it. Keep the observation and its limits as evidence.

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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free