Index of every page on this site: llms.txt
All skills
masihmoafi avatar

/first-principles

@c0a5d13
by Masih Moafimasihmoafi/skills10 stars
Run it yourself

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.

Use this Skill: https://skilld.dev/gh/masihmoafi/skills/first-principles

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈54 tokens for metadata: the name and description. ≈346 when used: this file.

Description uses 2.7% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈215 characters, or 2.7%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

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?

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts4mo3 checks · Risk SAFE
  • Gen Agent Trust Hub4mo

    The skill defines a structured problem-solving methodology for AI agents based on first-principles engineering. It provides guidelines for validating requirements, minimizing codebases, and automating optimized processes. No malicious patterns or security risks were detected.

  • Socket4mo

    No alerts

  • Snyk4mo

    Risk: LOW · No issues

Signed by skilld at c0a5d13. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last week.

Activeupdated 3 weeks ago

README badge

README badge for masihmoafi/skills/first-principles