principle-encode-lessons-in-structure

What problem does it solve? Repeatedly writing the same instruction or correction wastes effort and relies on readers remembering textual rules. This Skill turns recurring fixes into structural mechanisms that enforce the rule automatically. ## Core Features & Use Cases - Structural Encoding: Converts repeated instructions into lint rules, metadata flags, runtime checks, or automation scripts instead of more text. - Feedback Loop Discipline: Captures every correction, routes it to the right layer (one-off note, skill, lint rule, or principle), and closes the loop with a concrete action. - Guarded Application: Requires intake evidence before acting, returns a HOLD when the trigger is unproven, and refuses decorative citations that change no decision. - Use Case: You notice you have told the agent three times not to use a deprecated API. Instead of repeating the instruction, encode it as a lint rule that fails CI and delete the textual instruction. ## Quick Start Apply this principle to turn my repeated correction about the deprecated API into a lint rule or runtime check instead of another instruction.