SkillTrust

← All skills

no-fluff-output

100 / 100 · Low risk

Fine to try.

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

直给输出法提示语原文。用户抱怨 AI 说话啰嗦绕圈子、想要更直接可执行的回答、看长篇容易走神时使用。触发词包括 别废话、直接说重点、说结论、别绕弯子、有话直说、别来虚的、先说怎么做、拒绝废话、ADHD 友好、专注力不够。整段挂在会话开头,约束之后所有回答的结构,说恢复正常模式才关掉。

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/'no-fluff-output' ] || [ -L ~/.agents/skills/'no-fluff-output' ]; then echo 'A skill folder named no-fluff-output 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 "$d" checkout --quiet '32bd33d26ba69cbe715a06a2714ef16aa861a082' -- 'skills/asking/no-fluff-output' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/asking/no-fluff-output' ~/.agents/skills/'no-fluff-output' && 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/'no-fluff-output' ~/.claude/skills/'no-fluff-output' (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 badge for LearnPrompt/laoyeye

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

Score history

DateVersionScore
2026-11-0732bd33d100