skills.rest
yersonargotev
yersonargotevCOMMUNITY
Explore all skills by this author →
GitHub

principle-encode-lessons-in-structure

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

1|Updated Jul 5, 2026
Search Tags:#code quality#automation#feedback loop#engineering principles#ci enforcement#lint rules
One-click install
npx skills add https://github.com/yersonargotev/packy --skill principle-encode-lessons-in-structure-yersonargotev
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: principle-encode-lessons-in-structure
Source: https://github.com/yersonargotev/packy/tree/main/bundle/skills/principle-encode-lessons-in-structure
Command: npx skills add https://github.com/yersonargotev/packy --skill principle-encode-lessons-in-structure-yersonargotev

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Repeatedly writing the same textual instruction wastes effort and fails because readers must notice, remember, and comply. This Skill replaces recurring instructions with structural mechanisms that enforce the rule automatically. ## Core Features & Use Cases - Structural Encoding: Turn repeated corrections into lint rules, metadata flags, runtime checks, or automation scripts instead of more documentation. - Strongest-Rung Selection: Choose the strongest available mechanism, from unrepresentable states that cannot compile down to runtime checks. - Feedback Loop: Capture every correction, route it to the right layer (brain note, skill, lint rule, or principle), and close the loop with concrete action. - Use Case: When you catch yourself telling an agent a second time not to use a deprecated API, encode it as a CI lint rule that fails the build and delete the instruction. ## Quick Start Ask the agent to apply the encode-lessons-in-structure principle whenever it notices a repeated correction, converting the rule into a lint, 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 agent?▼

Encode the rule as a structural mechanism instead of text: a lint rule, metadata flag, runtime check, or script. Structural enforcement works without requiring the reader to notice, remember, or comply with written instructions.

What is the best way to enforce coding rules automatically?▼

Pick the strongest mechanism the situation allows: an unrepresentable state that cannot compile, then a lint or banned API that fails CI, then a canonical helper, then a runtime check. Agents copy surrounding code, so weak guards become bad templates.

When should a correction become a lint rule versus a note?▼

Route by recurrence: one-off issues go to a brain note, recurring fixes become skills or lint rules, and systemic issues become principles. If you write the same instruction twice, it is a candidate for structural encoding.

Why do textual coding guidelines fail in practice?▼

Textual instructions require the reader to notice, remember, and comply, which fails at scale. Structural mechanisms like CI lint rules and runtime checks enforce the rule without cooperation, so the instruction itself can be deleted.

What are common mistakes when encoding lessons into tooling?▼

Common anti-patterns include acknowledging without recording, recording without routing the fix to implementation, and fixing one instance without generalizing the pattern. Also avoid papering over symptoms with instructions when a structural fix exists.

Related Skills

Explore More Software Engineering Skills→
RB-chrismandichRB-chrismandich
1

antipattern-detect

Identifies recurring antipatterns from linting, test, and review feedback into knowledge_base.yml.

Community
Advanced
microsoftmicrosoft
190.1k

fix-ci

Diagnose and resolve failed CI checks for the current session.

Official
Basic
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