agentleFS
Sign inStart free
syangasyanga/astack/skills/principles/SKILL.md

principles

Skill0 starsChanged 53 days agoMITView on GitHub

Engineering principles index.

16 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ketchup, benchmark-checklist and 5 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.
  • instructureSkill

    ketchup

    Rebuild context after /clear by analyzing uncommitted changes across Canvas LMS and all plugin repositories

    Also in 5 projects that use this

  • Xia-AtaraxiaSkill

    benchmark-checklist

    Vets performance measurements for the limiter, tuning, physical limits, errors, repeatability, relevance, and proof that timed work happened. It applies to 'check this benchmark', 'report this speedup', measured regressions, and choosing a library or configuration from numbers. It reports spread and gaps before drawing a conclusion. Not for general testing policy or choosing test oracles - use principle-testing.

    Also in 6 projects that use this

  • tristanphvnSkill

    ketchup-video

    Catch the user up like /keel:ketchup, with a short silent video of slides for what happened and the waiting calls as text under it. Use for /keel:ketchup-video.

    Also in 3 projects that use this

  • jaydubya818Skill

    interrogate

    Use when a change's assumptions, evidence, or design need adversarial review.

    Also in 9 projects that use this

  • jaydubya818Skill

    figure-it-out

    Use when novel or multi-phase work needs an auditable workflow and no narrower playbook fits.

    Also in 6 projects that use this

  • drafaelSkill

    sharpen

    Deepen a task without broadening its scope, then rewrite its prompt. Manual invocation only; use when the user explicitly invokes sharpen or requests this prompt-sharpening workflow. Do not execute the rewritten task or decide choices the user owns.

    Also in 4 projects that use this

  • +1 more from jaydubya818

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 15 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. Distinctive:

    Before applying a principle, read its file in full.

    line 9

“Common” is measured: kept by at least 6 in 10 of the 15 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

Principles

Before applying a principle, read its file in full. In the reply, name the decision the principle changed.

Shaping a change

  • laziness-protocol.md. Refactoring, sizing a diff, or adding a layer.
  • foundational-thinking.md. Choosing core types and data structures, or sequencing setup before feature work.
  • subtract-before-you-add.md. Sequencing an addition or a refactor.
  • redesign-from-first-principles.md. Integrating a new requirement into an existing design.
  • attack-the-premise.md. Repeated fixes for an imbalance across actors share one premise and have failed the same check.
  • outcome-oriented-execution.md. Planned rewrites and migrations with explicit phase boundaries.
  • experience-first.md. Product, UX, or feature-scope tradeoffs.
  • exhaust-the-design-space.md. Novel interactions or architectural choices with no established precedent.
  • minimize-reader-load.md. Reviewing code that is hard to trace, or adding a layer or a piece of state.
  • build-the-lever.md. Work beyond a couple of obvious edits.
  • encode-lessons-in-structure.md. Writing the same instruction twice, or handling a correction from the user or a failed test.

Designing structure

  • deep-modules.md. Designing module interfaces, choosing seams, or evaluating abstraction depth.
  • model-the-domain.md. Stateful logic, or code that branches a lot or repeats a shape assumption across files.
  • boundary-discipline.md. Validation, error handling, framework adapters.
  • type-system-discipline.md. Designing a type or a signature in a typed language.
  • make-operations-idempotent.md. Commands and loops that must survive crashes and retries.
  • migrate-callers-then-delete-legacy-apis.md. A new internal API while old callers still exist.
  • separate-before-serializing-shared-state.md. Concurrent actors that might write the same file, branch, or key.

Verifying the work

  • prove-it-works.md. Before you call the work done.
  • fix-root-causes.md. Debugging.
  • sequence-verifiable-units.md. Multi-step work, and stacking commits and PRs.
  • test-behavior-not-implementation.md. Writing, changing, or keeping a test.

Managing the work

  • guard-the-context-window.md. Large outputs, long files, repeated reads, or plans for parallel work.
  • never-block-on-the-human.md. Deciding whether to ask for permission during an authorized task.

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