laulauland/dotfiles/engineering-principles

Claude Code and agent skill by laulauland/dotfiles

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Execution principles for scoping, sequencing, debugging, and verifying engineering work. Use when planning or sizing a change, driving an autonomous run, deciding what done means, or auditing a codebase for architecture that should be deepened.

Install

npx vskill@latest install laulauland/dotfiles/engineering-principles

SKILL.md

Engineering Principles

These are execution principles: how to drive a piece of work from request to verified result. They are orthogonal to code-design taste. When a decision is about naming, types, modules, parsing, errors, or tests, that is the apply-coding-standards skill, and these files defer to it rather than restating it.

Each principle is one file with one idea. Read the leaf in full when it applies; this index is only the router. They are referenced by name, not invoked as commands, and they apply the same whichever harness is driving (Claude, Pi, Codex, Cursor).

How this relates to apply-coding-standards

apply-coding-standards answers "is this code well-designed?" These principles answer "am I working on it the right way?" Where they touch the same ground, the principle points at the standard:

  • Verification of a finished task lives here (PROVE_IT_WORKS.md); what a good test looks like lives in ../apply-coding-standards/TESTING_AND_VERIFICATION.md.
  • Diff size and deletion bias live here; module and interface design lives in ../apply-coding-standards/DESIGNING_MODULES.md.
  • Target-state-not-migration sequencing lives here; the no-backwards-compat design rule lives in apply-coding-standards's non-negotiables.

If a leaf ever duplicates a standard, cut the leaf down to the part the standard does not own.

Principles

Read the matching leaf before applying it.

When you are...Read...
Refactoring, sizing a diff, or tempted to add a layer or thread a new signal through typesLAZINESS_PROTOCOL.md
Sequencing an addition or rewrite and there is dead weight to remove firstSUBTRACT_BEFORE_YOU_ADD.md
Reviewing code that is hard to trace; counting layers, hidden state, one-caller wrappersMINIMIZE_READER_LOAD.md
Doing any non-trivial or repeated work that a script, codemod, or generator could do and proveBUILD_THE_LEVER.md
Finishing a task and about to declare it donePROVE_IT_WORKS.md
Debugging a symptom and tempted to patch where it surfacedFIX_ROOT_CAUSES.md
Diagnosing a hard bug or performance regression without a reliable reproductionDIAGNOSE_HARD_BUGS.md
Stacking commits or PRs across a sweep or migrationSEQUENCE_VERIFIABLE_UNITS.md
Context is filling with large outputs, long files, or fan-out planningGUARD_THE_CONTEXT_WINDOW.md
Tempted to ask "should I do X?" on reversible workNEVER_BLOCK_ON_THE_HUMAN.md
Facing a novel decision with no precedent in the codebaseEXHAUST_THE_DESIGN_SPACE.md
About to write logic before settling the core data shapesFOUNDATIONAL_THINKING.md
Catching yourself writing the same instruction a second timeENCODE_LESSONS_IN_STRUCTURE.md
Auditing a codebase for shallow modules and deepening opportunitiesARCHITECTURE_AUDIT.md and ARCHITECTURE_REPORT.md

Every principle in the table has its leaf file.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/laulauland/dotfiles/engineering-principles/badge)](https://verified-skill.com/skills/laulauland/dotfiles/engineering-principles)

Something wrong with this skill or its page? Tell us.