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.

The download is free. What we sell is at the bottom of the page, with prices.

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.

The paid part

Here is what we sell.

Everything above this line is free and stays free. Below it is what we sell. The prices are the prices, and the two subscriptions carry 30 days money back on the first month.

The readiness audit, done for you

Send us access to your repo. We run the nine-lane review, change nothing, and hand back the report with a 30 minute call on the three gaps to close first.

Who it is for: You have a product you charge for, or want to, and you would rather read the verdict than run the agents.
Price: $349One week
What you get: The report at docs/commercial-readiness.md: a verdict, a scorecard, every gap with the file to open and how to verify it
Legal, security, billing, support, marketing, operations and the rest, checked at once
A 30 minute call on the three gaps to close first
Nothing in your repo changed. The workflow prompt is yours to run afterward
The facts: The review is the one in the video. On our own product it found 87 gaps. The overnight run that followed was 148 commits and one pull request.
Our guarantee: If the review finds no gap worth your time, you pay nothing.

The first run, with Jason

We run the review on your repo together, on a call, and you leave with the report in your repo and the three gaps to close first.

Who it is for: You have the kit and a repo, and you would rather do the first run with someone who has done it.
Price: $9960 minutes
What you get: The review running on your machine, in your Claude Code
The verdict read together, and the three gaps picked
The workflow prompt set up so you can run it that night
The call recording
The facts: New. You would be one of the first. The run itself is the one in the video: 190 agents, 148 commits, one pull request.
Our guarantee: If the review will not run on your setup during the call, there is no charge.

Mica Social Media Analyzer

Your Instagram, answered by the ChatGPT or Claude you already use. Connect the account once, then ask in plain words what worked and what to post next.

Who it is for: You post on Instagram and you are done guessing from the Insights tab.
Price: $29/ month
What you get: Which Reels held attention, ranked, without opening Insights
Readings at 1, 24 and 72 hours after every post, so you see what happened while it was moving
Next captions written in the style of your most saved posts
Read only. It never posts or changes anything
The facts: 7 days free with a card on file. About a dollar a day after that.
Our guarantee: 30 days money back on the first month. Email guru@graniteai.co and we refund it.

Start 7 days free

Mica Social

An AI that writes, designs, checks and publishes a post to your Facebook and Instagram every day. You send a photo when you have one. It does the rest.

Who it is for: You know the feed should be alive every day and it is not.
Price: $49/ month
What you get: A finished post every day, with a photo made for it. Nothing to shoot
Timed to your local weather, season and county numbers
Five checks before anything publishes. No approvals, no calendar, no logins
Every photo you send becomes its own extra post
The facts: An agency running a daily feed bills $500 to $1,500 a month. 3 days free with a card on file.
Our guarantee: 30 days money back on the first month. Email guru@graniteai.co and we refund it.

See Mica Social

GraniteAI builds and runs AI systems for small and midsized businesses, out of Manchester, New Hampshire.

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