Tested Popular GPT Shortcuts: What Works in Real Tasks
When you work with GPT every day, the first thing you want to do is speed up the process. For this, people invented shortcuts: short commands like EL5 or /BULLET that suggest to the model a style and response priorities. Over a month, I tested the most popular ones on real tasks: analyzing code, simplifying articles, finding logic errors. The results turned out to be curious — not all shortcuts are equally useful. ## Workhorse Shortcuts EL5 (Explain Like 5) turns any complex concept into an explanation for a five-year-old. In practice, this means: no jargon, just the essence, concrete examples. Works reliably on 95% of attempts — a high score for prompt tools. Saves the day when you need to quickly understand something unfamiliar or explain to a colleague without extra words.
AI-processed from Habr AI; edited by Hamidun News
When you work with GPT every day, the first thing you want to do is speed up the process. For this, people invented shortcuts: short commands like EL5 or /BULLET that suggest to the model a style and response priorities. Over a month, I tested the most popular ones on real tasks: analyzing code, simplifying articles, finding logic errors. The results turned out to be curious — not all shortcuts are equally useful.
Workhorse Shortcuts
EL5 (Explain Like 5) turns any complex concept into an explanation for a five-year-old. In practice, this means: no jargon, just the essence, concrete examples. Works reliably on 95% of attempts — a high score for prompt tools. Saves the day when you need to quickly understand something unfamiliar or explain to a colleague without extra words.
/BULLET formats the response into a bulleted list. Never lets you down, works like clockwork. Simple and the structure is immediately visible.
/CHAIN shows a step-by-step chain of reasoning: slower than others, but more reliable for logic tasks than anything else.
- EL5 — simplifying complex ideas to a basic level
- /BULLET — formatting into a bulleted list
- /CHAIN — step-by-step reasoning for logic
- /SCIENCE — backing up with facts and research
Shortcuts That Work Hit or Miss
/REDTEAM offers to criticize an idea, find weak points. Sounds useful, but in reality delivers mixed results: from constructive criticism to petty complaints — depends on the day and model version.
/LAWYER analyzes like a lawyer: looks at context, finds contradictions, warns about risks. Works fine on standard situations, but on complex questions can miss the main point and get stuck on details. Useful as an initial check, but not as a final answer.
What You Shouldn't Touch at All
/JOKE — the command to add a joke — is so unstable that forget about it altogether. Tried it ten times in a row: five times weird and inappropriate, three times not funny, two times okay. That's 20% usefulness at 100% cost.
/METAPHOR and /HAIKU look beautiful in descriptions, but take more time in real work than they save.
What This Means in Practice
Better to master three or four stable shortcuts than chase the perfect one for every situation. The main discovery: shortcuts combine well together. /BULLET + EL5 work better together than each one separately. And don't believe promises about tools — test them yourself on your tasks for two weeks, then decide.
- Oct 28, 2026Anthropic reveals how it builds Claude with Claude: the brain separate from the hands
- Oct 28, 2026Bayer Launches Multi-Agent Engine on AgentCore: 80% of Questions Handled Without Engineers
- Oct 28, 2026Liquid AI releases LFM2.5-24B-A2B: an agent model with 2B active parameters
- Oct 28, 2026NVIDIA Releases 120B Nemotron 3.5 Super VL and Bolt Models for Local Agents
Key Questions Answered
What are the key details on Workhorse Shortcuts?
EL5 (Explain Like 5) turns any complex concept into an explanation for a five-year-old. In practice, this means: no jargon, just the essence, concrete examples. Works reliably on 95% of attempts — a high score for prompt tools. Saves the day when you need to quickly understand something unfamiliar or explain to a colleague without extra words. /BULLET formats the response into a bulleted list. Never lets you down, works like clockwork. Simple and the structure is immediately visible. /CHAIN shows a step-by-step chain of reasoning: slower than others, but more reliable for l
What are the key details on Shortcuts That Work Hit or Miss?
/REDTEAM offers to criticize an idea, find weak points. Sounds useful, but in reality delivers mixed results: from constructive criticism to petty complaints — depends on the day and model version. /LAWYER analyzes like a lawyer: looks at context, finds contradictions, warns about risks. Works fine on standard situations, but on complex questions can miss the main point and get stuck on details. Useful as an initial check, but not as a final answer.
What You Shouldn't Touch at All?
/JOKE — the command to add a joke — is so unstable that forget about it altogether. Tried it ten times in a row: five times weird and inappropriate, three times not funny, two times okay. That's 20% usefulness at 100% cost. /METAPHOR and /HAIKU look beautiful in descriptions, but take more time in real work than they save.
Build & Ship Production AI Agents Without Boilerplate Code
Start your free 72-hour trial at Hamidun Academy (academy.hamidun.com) — interactive lessons on Claude Code & Cursor, live Tech Radar, and production agent templates.
The AI world, distilled — once a week
Seven stories that actually mattered, hand-picked. No noise, no reposts, no press releases.
Done! Check your inbox for a confirmation.