agentleFS
Sign inStart free
MasihMoafiMasihMoafi/skills/first-principles/SKILL.md

first-principles

Skill8 starsChanged 10 days agoMITView on GitHub

Use only when the user explicitly asks for a first-principles review of a product, requirement, workflow, or implementation: question the requirements, delete what should not exist, then simplify.

30 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use second-order-thinking, inversion and 2 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • itzcullSkill

    second-order-thinking

    Use second-order thinking to examine consequences beyond immediate effects. Use when evaluating decisions across time horizons, asking what happens next, or avoiding short-sighted optimization.

    Also in 3 projects that use this

  • itzcullSkill

    inversion

    Use inversion to solve problems by reasoning backward from failure, bad outcomes, or the opposite of success. Use when identifying risks, running premortems, or escaping overly idealized thinking.

    Also in 3 projects that use this

  • Ingramradical235Skill

    pre-mortem

    Pre-mortem analysis, scenario planning, future state narratives, and contingency frameworks. Use before finalizing any Strategy Kernel, when planning major initiatives, or when preparing Plan B triggers.

    Also in 3 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 21 edited versions we read keep these.

  • 6

    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. Distinctive:

    Question the requirements: Treat every requirement as possibly wrong.

    line 14
  2. Distinctive:

    Delete: Remove parts, configuration and dependencies that the required behavior does not need, and confirm with regression checks.

    line 15
  3. Distinctive:

    Simplify and optimize: Keep what remains minimal and readable, in the project's own style.

    line 16
  4. Distinctive:

    Accelerate: When speed matters, measure first, fix the slowest path, and check that the speed-up adds no flakiness.

    line 17
  5. Distinctive:

    If speed mattered, was it measured before and after?

    line 25
  6. Distinctive:

    If something was automated, does it run cleanly without help?

    line 26

“Common” is measured: kept by at least 6 in 10 of the 21 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

First-Principles Review

Question assumptions and find the smallest system that meets the real goal; a review produces analysis and recommendations, not edits.

Phases

Apply only the phases that serve the goal, in this order. Do not optimize or automate a process that should not exist.

  1. Question the requirements. Treat every requirement as possibly wrong. State assumptions that change the result, surface competing interpretations, and push back when a simpler approach serves the goal better.
  2. Delete. Remove parts, configuration and dependencies that the required behavior does not need, and confirm with regression checks. Stop when further deletion would risk required behavior; there is no deletion quota.
  3. Simplify and optimize. Keep what remains minimal and readable, in the project's own style.
  4. Accelerate. When speed matters, measure first, fix the slowest path, and check that the speed-up adds no flakiness.
  5. Automate. Automate only a stable, already simplified process that repeats, and verify that it runs end to end without help.

Checklist

  1. Were the requirements questioned before any code was written?
  2. Was only demonstrated waste removed?
  3. Is the remaining code minimal and in the local style?
  4. If speed mattered, was it measured before and after?
  5. If something was automated, does it run cleanly without help?

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.

Check your setup, free