← All skills

self-framing

100 / 100 · Low risk

Fine to try.

By LearnPrompt/laoyeye (GitHub) · other · 103 stars · scanned at commit 32bd33d

自建框架再自查提示语原文。用户觉得直接要答案会漏、嫌套用现成框架、想让 AI 先为这一个问题现写分析框架再自查盲点时使用。触发词包括 自建框架、再自查、元认知、元认知自校、你漏了什么、分析框架、别用套话、盲点、自查一下、先定框架再答、别直接给结论。先说清问题类型和好答案要满足什么，亮出自己写的框架，按框架跑，再查漏掉的假设、视角、数据和失败方式，以及懂行的人会攻击哪里，最多改两轮。最后交最终答案、用过的框架、还剩下的已知未知。要几个角色互相质疑用 expert-panel，要核实说法真假用 fact-check，要拆回基本事实重推用 first-principles，要列保证失败的做法用 inversion，要反过来追问用户用 socratic-inquiry。

Works with any agent that supports SKILL.md skills.

What this skill can do

We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'self-framing' ] || [ -L ~/.agents/skills/'self-framing' ]; then echo 'A skill folder named self-framing already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/LearnPrompt/laoyeye' "$d" && git -C "$d" checkout --quiet '32bd33d26ba69cbe715a06a2714ef16aa861a082' -- 'skills/solving/self-framing' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/solving/self-framing' ~/.agents/skills/'self-framing' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'self-framing' ~/.claude/skills/'self-framing' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for LearnPrompt/laoyeye shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/LearnPrompt/laoyeye.svg)](https://zalavijaysinh.github.io/skilltrust/repos/LearnPrompt/laoyeye/)

Score history