skills.rest
Shtian
ShtianCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

principle-encode-lessons-in-structure

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

4|1|Updated Dec 16, 2023
Search Tags:#code quality#automation#best practices#feedback loop#conventions#ci enforcement#lint rules
One-click install
npx skills add https://github.com/Shtian/AuthentiClash --skill principle-encode-lessons-in-structure-shtian
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: principle-encode-lessons-in-structure
Source: https://github.com/Shtian/AuthentiClash/tree/main/.claude/skills/principle-encode-lessons-in-structure
Command: npx skills add https://github.com/Shtian/AuthentiClash --skill principle-encode-lessons-in-structure-shtian

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 rules automatically. ## Core Features & Use Cases - Mechanism Selection: Guides you to encode a recurring fix as a lint rule, metadata flag, runtime check, or automation script, choosing the strongest mechanism available. - Feedback Loop: Provides a capture-route-close workflow for every human correction or test failure, routing one-offs to notes, recurring fixes to skills or lint rules, and systemic issues to principles. - Anti-Pattern Detection: Flags common failures like acknowledging without recording, recording without routing, and fixing one instance without generalizing the pattern. - Use Case: When you catch yourself telling an AI 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 Apply this principle whenever you notice a repeated correction by asking whether the rule can become a lint, flag, check, or script instead of more text.

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, and comply with written instructions.

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

Choose the strongest mechanism the situation allows: first make bad states unrepresentable so they cannot compile, then a lint or banned API that fails CI, then a canonical helper, then a runtime check. Weaker guards become templates agents copy.

When should a fix become a lint rule versus a written instruction?▼

If the rule can be checked mechanically, encode it as a lint rule or script and delete the instruction. Only keep textual instructions when the rule requires human judgment, and then make it prominent with a failure-mode example.

Why do textual coding guidelines keep getting ignored?▼

Textual instructions require the reader to notice, remember, and comply, which fails at scale. Agents and developers copy whatever the surrounding code already does, so conventions must be enforced structurally through lints, checks, or unrepresentable states.

What are the limitations of structural enforcement for code quality?▼

Structural mechanisms only work for mechanically checkable rules. Fixes requiring judgment cannot be encoded as lints or checks, so they must remain instructions, made more prominent and paired with concrete examples of the failure mode.

Related Skills

Explore More Software Engineering Skills→
mujtaba3Bmujtaba3B
2

address-pr-feedback

Address pull request review comments one by one into code fixes.

Community
Advanced
cursorcursor
6.6k

principle-encode-lessons-in-structure

Converts recurring corrections into lint rules, runtime checks, and automation scripts.

Official
Basic
Sma1lboySma1lboy
136

principle-encode-lessons-in-structure

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

Community
Basic
yanochka11yanochka11

write-judge-prompt

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

Community
Advanced