Agent Skills › sediman-agent/OpenSkynet › principle-encode-lessons-in-structure

principle-encode-lessons-in-structure

GitHub

将重复性修正转化为代码、Lint规则或自动化脚本，避免依赖文本指令。通过捕获错误并建立反馈闭环，实现从人工纠正到结构性约束的自动化转变，提升开发流程的鲁棒性。

skills/cursor_plugins/pstack/skills/principle-encode-lessons-in-structure/SKILL.md sediman-agent/OpenSkynet

Trigger Scenarios

发现需要重复编写相同的指令或修正遇到可被工具化或自动化的重复性错误模式

Install

npx skills add sediman-agent/OpenSkynet --skill principle-encode-lessons-in-structure -g -y

More Options

Non-standard path

npx skills add https://github.com/sediman-agent/OpenSkynet/tree/main/skills/cursor_plugins/pstack/skills/principle-encode-lessons-in-structure -g -y

Use without installing

npx skills use sediman-agent/OpenSkynet@principle-encode-lessons-in-structure

指定 Agent (Claude Code)

npx skills add sediman-agent/OpenSkynet --skill principle-encode-lessons-in-structure -a claude-code -g -y

安装 repo 全部 skill

npx skills add sediman-agent/OpenSkynet --all -g -y

预览 repo 内 skill

npx skills add sediman-agent/OpenSkynet --list

SKILL.md

Frontmatter

{
    "name": "principle-encode-lessons-in-structure",
    "description": "Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the rule as a lint, metadata flag, runtime check, or script instead of more text.",
    "disable-model-invocation": true
}

Encode Lessons in Structure

Encode recurring fixes in mechanisms (tools, code, metadata, automation) instead of textual instructions. Every error, human correction, and unexpected outcome is a learning signal. Capture it, route it, and close the loop.

Why: Textual instructions are easy to miss. They require the reader to notice, remember, and comply. Structural mechanisms (lint rules, metadata flags, runtime checks, automation scripts) enforce the rule without cooperation.

Pattern: When you catch yourself writing the same instruction a second time:

Ask: can this be a lint rule, a metadata flag, a runtime check, or a script?
If yes, encode it. Delete the instruction
If no (genuinely requires judgment), make the instruction more prominent and add an example of the failure mode

Corollary: Don't paper over symptoms. If the fix is structural, ONLY use the structural fix. The instruction IS the symptom.

Feedback loop:

Capture every correction. When the human intervenes or tests fail, decide if it's a one-off or a pattern.
Route to the right layer. One-off -> brain note. Recurring fix -> skill or lint rule. Systemic issue -> principle.
Close the loop. Don't just record. Apply now or create a concrete todo.

Anti-patterns:

Acknowledging without recording ("I'll keep that in mind" does not persist)
Recording without routing (a brain note about a lint rule that should exist is wasted unless the lint rule gets implemented)
Fixing without generalizing (fixing one instance while leaving the recurring pattern intact)