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结构（如Lint规则、脚本或元数据），而非依赖文本指令。通过自动化机制强制执行规范，减少人为疏忽，建立从错误捕获到结构修复的闭环反馈。

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

触发场景

发现需要重复编写相同指令时遇到可被自动化工具处理的 recurring correction

安装

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

更多选项

非标准路径

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

不安装直接使用

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)