skills.rest
IgorGanapolsky
IgorGanapolskyCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

principle-encode-lessons-in-structure

Converts recurring corrections into lint rules, metadata flags, runtime checks, or automation scripts.

1|Updated Aug 27, 2025
Search Tags:#automation#feedback loop#engineering principles#runtime checks#code conventions#ci enforcement#lint rules
One-click install
npx skills add https://github.com/IgorGanapolsky/Random-Timer --skill principle-encode-lessons-in-structure-igorganapolsky
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: principle-encode-lessons-in-structure
Source: https://github.com/IgorGanapolsky/Random-Timer/tree/main/.cursor/skills/principle-encode-lessons-in-structure
Command: npx skills add https://github.com/IgorGanapolsky/Random-Timer --skill principle-encode-lessons-in-structure-igorganapolsky

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Repeatedly writing the same instruction or correction wastes effort and relies on readers noticing, remembering, and complying. This Skill replaces fragile textual instructions with structural mechanisms that enforce the rule automatically. ## Core Features & Use Cases - Mechanism Selection: Guides you to encode a recurring fix as a lint rule, metadata flag, runtime check, or script, choosing the strongest mechanism available. - Feedback Loop: Captures every correction, routes it to the right layer (brain note, skill, lint rule, or principle), and closes the loop with a concrete action. - Anti-Pattern Detection: Flags failures like acknowledging without recording, recording without routing, and fixing one instance without generalizing. - Use Case: You notice you have told the AI twice not to use a deprecated API. Instead of repeating the instruction, you add a lint rule that fails CI when the API appears, then delete the instruction. ## Quick Start Ask the AI to apply the encode-lessons-in-structure principle to turn a repeated correction into a lint rule, runtime check, or script.

Frequently Asked Questions about principle-encode-lessons-in-structure

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I stop repeating the same instruction to an AI coding assistant?▼

Encode the instruction as a structural mechanism instead of text. If the rule can be expressed as a lint rule, metadata flag, runtime check, or script, implement that mechanism and delete the instruction so enforcement no longer depends on the reader.

What is the difference between a lint rule and a runtime check for enforcing conventions?▼

A lint rule fails at build or CI time before code merges, making it stronger. A runtime check catches violations during execution and is used when the condition cannot be detected statically. Prefer the strongest mechanism the situation allows.

When should a correction become a lint rule versus a written guideline?▼

Make it a lint rule when the violation is mechanically detectable and recurs. Keep it as a written guideline only when compliance requires human judgment, and in that case make the instruction prominent with an example of the failure mode.

Why do textual coding conventions fail in teams and AI workflows?▼

Text requires the reader to notice, remember, and comply, and agents copy whatever surrounding code already does. A weaker guard becomes the next template, so structural enforcement outperforms documentation for recurring rules.

What are common mistakes when encoding lessons into structure?▼

Three anti-patterns: acknowledging a correction without recording it, recording it without routing it to implementation, and fixing one instance while leaving the recurring pattern intact. Each breaks the feedback loop.

Related Skills

Explore More Software Engineering Skills→
ReefBytesReefBytes
1

antipattern-detect

Collect lint, test, and review failures to classify and document antipatterns.

Community
Advanced
gar-aigar-ai
1

rust-code-quality

Enforce rustfmt and clippy standards in pre-commit and CI pipelines.

Official
Advanced
anyprotoanyproto
514

claudemd-maintainer

Reviews and optimizes CLAUDE.md files for effective LLM instruction structure.

Official
Intermediate
yanochka11yanochka11

write-judge-prompt

Design LLM-as-Judge prompts with criteria, examples, and binary verdicts.

Community
Advanced