agentleFS
cwhited26cwhited26/pocket-agent-starter-skills/skills/decisions/load-bearing-assumption/SKILL.md

load-bearing-assumption

Skill0 starsChanged 4 months agoMITView on GitHub

Find the one assumption that makes a decision wrong if it's false, and check it before committing. Before a real commitment — a hire, a spend, a direction. When a plan depends on something being true that nobody's actually checked.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    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. Distinctive:

    Every plan rests on one or two assumptions that, if wrong, sink it.

    line 16
  2. Distinctive:

    Ask what has to be true for this decision to be right.

    line 20
  3. Distinctive:

    Check whether you actually know it's true, or just hope it is.

    line 22
  4. Distinctive:

    If it's unverified, verify it before committing — a cheap test now beats an expensive correction later.

    line 23
  5. Distinctive:

    If you can't verify it, size the downside: what does being wrong cost?

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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

Name the Load-Bearing Assumption

Every plan rests on one or two assumptions that, if wrong, sink it. Find the load-bearing one — the thing that has to be true for this to work — and pressure-test it before you commit, not after.

The technique

  • Ask what has to be true for this decision to be right. List the assumptions underneath it.
  • Find the load-bearing one — the assumption that, if false, makes the whole thing a mistake. There's usually one that matters most.
  • Check whether you actually know it's true, or just hope it is. Hope is not a check.
  • If it's unverified, verify it before committing — a cheap test now beats an expensive correction later.
  • If you can't verify it, size the downside: what does being wrong cost? That tells you how much to bet.

Do this, not that

Do: "This whole plan assumes the 40 past customers actually want a maintenance plan — that's load-bearing. Before we build it, I'll email ten of them and ask. If half say yes, build it. If nobody bites, we just saved the build."

Don't: Build the entire maintenance-plan system, the page, the Stripe product, the contracts — on the unchecked assumption that demand exists, then discover after launch that nobody wanted it.

Why this works

Plans don't usually fail on the details; they fail on a wrong assumption nobody questioned. Naming the load-bearing one turns an invisible bet into a visible one you can actually test. Most of the time the test is cheap — an email, a few calls — and finding out the assumption is false before you build is the difference between a saved week and a wasted month.

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.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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.