Free skill for ChatGPT and Claude

Write instructions nobody has to reread.

Add STE to ChatGPT or Claude. It turns tangled procedures, warnings, and error messages into short, ordered instructions. The reader sees the condition, the action, and the stop point before a bad guess costs time, data, or safety.

Download STE

Three plain-text files. Free, no signup, works in ChatGPT and Claude.

See the boundary in 30 seconds.

Same source facts. STE wins when ambiguity has a cost. It loses when voice carries the value.

Use STE here

A technician must act without guessing.

The condition, action, and stop point must survive noise, pressure, and translation.

Prompt Write the reset instruction for conveyor fault E-17.

Without STE

Once you have checked that the guard is closed and made sure nobody is in the conveyor area, go ahead and reset the E-17 sensor fault.

If the light happens to come back on, avoid trying again and get maintenance involved.

With STE

Better fit

WARNING: Make sure that no person is in the conveyor area.

Close the safety guard.

Press RESET once.

If fault E-17 returns, do not restart the conveyor.

Call maintenance.

Skip STE here

A buyer must feel why the object is worth wanting.

Clarity still matters. So do rhythm, texture, and a human point of view.

Prompt Write the product copy for a handmade ceramic mug.

Without STE

Better fit

The Ridge mug keeps the small irregularities that prove a person made it: a thumbprint at the handle, a glaze line that breaks differently on every piece.

Made in Portsmouth in batches of 24.

With STE

The Ridge mug is made by hand.

The handle can have a thumbprint.

The glaze can have an irregular line.

Each batch contains 24 mugs.

Use it when a wrong reading has a cost.

Choose strict STE when a wrong reading can cause harm, downtime, rework, or bad data. Choose STE-flavored writing for technical explanations that still need some natural rhythm. Skip STE when voice is part of the job.

Use it for

Safety warnings and work instructions: Put the warning first. Give one action per sentence. Put the stop condition where the reader cannot miss it.
Maintenance procedures and runbooks: Turn source facts into an ordered sequence a trained reader can carry out without untangling the sentence.
Error messages and tool descriptions: Tell the reader what failed, what to do next, and what information support needs.
Agent-facing tool text: Keep tool calls, field descriptions, and machine-parsed instructions consistent enough to execute and test.
Technical text that crosses a language line: Short sentences and stable words give non-native readers and translation tools fewer ways to misread the instruction.

Not for

Marketing copy: Use a copywriting skill. STE removes the rhythm and texture that give a buyer a reason to care.
Fiction and story: Use a writing skill. A story needs ambiguity, cadence, and surprise.
Exploratory thinking and strategy: Use normal prose when the reader needs nuance, competing interpretations, or an argument that unfolds.

How to use this

Install once. Then ask in plain words.

"Write the daily check for the air compressor, using STE." "Rewrite this work instruction so a non-native reader can follow it." "Make this error message one idea per sentence." That is the whole workflow.

ChatGPT

Skills are live on Business, Enterprise, Edu and Healthcare plans; an admin may need to switch them on. On Plus or Free, use a project instead: paste the guide into its instructions and add the two example files. Same result.

01
Open the Skills page: pick Plugins in the sidebar and switch to the Skills tab, or go straight to chatgpt.com/skills.
Plugins → Skills
02
Click the plus button, then upload from your computer.
+ → Upload from your computer
03
Select ste100-skill.zip exactly as downloaded.
ChatGPT expects a zip holding one folder with SKILL.md inside. That is exactly what the download is.
04
Ask for the procedure in any chat.

Claude (web or desktop)

Works on Free, Pro, Max, Team and Enterprise plans.

01
In settings, open Capabilities and check that cloud code execution is on. Skills need it.
Settings → Capabilities → Cloud code execution and file creation
02
In the sidebar, click Customize. It opens on your Skills list.
Customize → Skills
03
Click Add, then Upload a skill.
Add → Upload a skill
04
Select ste100-skill.zip.
Upload the zip exactly as downloaded. Do not unzip it first.
05
Start a new chat and ask for the procedure.

On Claude Code? Unzip the download into your skills folder (~/.claude/skills) and it loads on the spot.

We use this on our own procedures.

Maintenance runbooks, work instructions, and the error messages behind our own tools all go through it. The guide got sharp because the procedure had to survive an owner who quits reading at the first buried clause. Take it, run it on your next draft, and cut whatever does not fit.

Who made this

GraniteAI builds and runs AI for small and midsized businesses, out of Manchester, New Hampshire. Follow-ups that stop slipping, a feed that stays alive, and a ChatGPT that knows the market a business actually works in. That last one is the Mica Intelligence Engine: an owner asks what to charge or which town to work next, and the answer arrives backed by verified facts about their own county and trade, each carrying a source and a date. See the engine

The next free file

STE settles how the procedure reads. What goes in it still has to come from the business and the equipment, and the AI you ask does not have those facts. Send us your website and the equipment list. We email back a context kit that makes ChatGPT or Claude answer from your business instead of guessing about it. Free, and every file is yours to read before you load it.

Build my free context kit See what we build

When a local trades company runs a feed of its own work, the daily post slips to every other Tuesday. Mica takes that end of the job for trades like cleaning and roofing. It drafts and publishes on a steady schedule, so the page and the feed stay alive through the months nobody has an hour to sit down and write. See Mica