惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

雷峰网
雷峰网
WordPress大学
WordPress大学
MyScale Blog
MyScale Blog
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
T
The Blog of Author Tim Ferriss
U
Unit 42
罗磊的独立博客
G
Google Developers Blog
Microsoft Azure Blog
Microsoft Azure Blog
The Cloudflare Blog
aimingoo的专栏
aimingoo的专栏
Vercel News
Vercel News
N
Netflix TechBlog - Medium
H
Hackread – Cybersecurity News, Data Breaches, AI and More
云风的 BLOG
云风的 BLOG
Hugging Face - Blog
Hugging Face - Blog
大猫的无限游戏
大猫的无限游戏
F
Fortinet All Blogs
博客园 - 聂微东
Stack Overflow Blog
Stack Overflow Blog
小众软件
小众软件
博客园 - 【当耐特】
H
Help Net Security
The GitHub Blog
The GitHub Blog

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant
A Claude Skill That Turns Long AI Answers Into Short Notes
Amir Reza Dalir · 2026-06-26 · via DEV Community
Cover image for A Claude Skill That Turns Long AI Answers Into Short Notes

Amir Reza Dalir

An AI gives a long answer. You read fast and skip most of it. Every time.

🤔 Why

Your eyes don't read the whole reply. They look for one thing: the line that says do this, not that. The other 400 words are extra. So I wanted a way to turn any answer into short notes — the kind you write in the margin of a book.

✂️ What

toot turns a long answer into short notes. A few words per line. Symbols do most of the work.

The name is Persian: toot (توت) means mulberry — the small berry you eat in one bite. That is the idea: take something big and make it small enough to take in at once.

Here is a real answer about adding a database index:

Adding an index on user_id makes these lookups faster, but it is not free. Every index must be updated on each INSERT, UPDATE, and DELETE, so tables with many writes pay a cost. Your table has many reads and always filters on user_id, so it is worth it. One warning: if user_id has very few different values, the planner may skip the index. Also, a composite index on (user_id, created_at) would cover both the filter and the sort.

The same answer, after toot:

index on user_id → faster reads ✓
every write updates it → write cost ↑
many reads + filters user_id → worth it ✓
⚠ few different values → planner skips it → useless
composite (user_id, created_at) ≡ covers filter + sort

About 110 words become 5 lines. Nothing important is lost — the cost, the warning, and the advice are all still there. Two rules keep it safe:

  • Code is never changed. Commands and code stay exactly the same, in their own block. A changed command is a broken command.
  • Only one word is translated. If you set a language, toot translates only the one hard word, on its own line below the note. Words you already know — like cache or rollback — stay in English.

The skill is just one SKILL.md file with rules written in plain English. There is no script. Claude does the work; the file tells it how.

🚀 How

1. Install — go to your skills folder, then clone the gist:

cd ~/.claude/skills
git clone https://gist.github.com/dalirnet/26bc7f57a13f13a030afb78ed17f7d71.git toot

Claude finds it in your next session. To update later: cd ~/.claude/skills/toot && git pull.

2. Use it — say toot (or /toot) after any answer. To always translate into one language, add this line to your project's CLAUDE.md:

toot default language: Persian