ste-writing
Skill448 starsChanged 12 days agoApache-2.0View on GitHub
Simplified Technical English (ASD-STE100) makes text exact for readers who skim, read in a second language, or act on it later. Our goal: a reader understands the result in 10 seconds and finds the evidence in 30. 1. One idea per sentence. Procedure: max 20 words. Description: max 25 words. 2. Active voice. "The reviewer found 2 bugs." Not "2 bugs were found." 3. Imperative for instructions. "Top up wallet B." Not "Wallet B should be topped up." 4. Present…
13 other projects use a version of this.
Adopted by
Most recently taken up by
- LeonardiFranco/skillstheir own version, first seen Nov 8, 2026
- xiduzo/wtftheir own version, first seen Nov 8, 2026
- vstorm-co/agenticostheir own version, first seen Oct 16, 2026
- norton77930/understanding-ai-outputstheir own version, first seen Oct 11, 2026
- berkeley-humanoids/skillstheir own version, first seen Oct 9, 2026
- berkeley-humanoids/Skillstheir own version, first seen Oct 9, 2026
Used with
Projects with it also use prototype and grilling.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
GoogleSkillprototype
Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
Also in 3 projects that use this
GoogleSkillgrilling
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
Also in 3 projects that use this
Other versions13 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 13
- vstorm-co/agenticos★ 315same name
- ahonn/dotfiles★ 62same name
- xiduzo/wtf★ 7same name
- berkeley-humanoids/skills★ 4same name
- berkeley-humanoids/Skills★ 4same name
- norton77930/understanding-ai-outputs★ 3same name
- 1fc0nfig/ste-writing★ 2same name
- joshua-noel/skills★ 2same name
- TrimVis/skills★ 2same name
- HarveyZgit/agents★ 1same name
3 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository3 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- tk-qa-verify-webSkill
- ui-component-testsSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 13 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 26
No idioms, no filler: Delete "basically", "it seems", "in order to", "please note", "as mentioned".
- Distinctive: line 60
Every claim has evidence (path, line, value, video)?
“Common” is measured: kept by at least 6 in 10 of the 13 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
STE for plans and reports
Simplified Technical English (ASD-STE100) makes text exact for readers who skim, read in a second language, or act on it later. Our goal: a reader understands the result in 10 seconds and finds the evidence in 30.
Sentence rules
- One idea per sentence. Procedure: max 20 words. Description: max 25 words.
- Active voice. "The reviewer found 2 bugs." Not "2 bugs were found."
- Imperative for instructions. "Top up wallet B." Not "Wallet B should be topped up."
- Present or simple past tense. No "would", "might", "should be able to".
- One word, one meaning. Pick a term and keep it: wallet A, wallet B, case, finding, gate. Never swap to a synonym.
- Concrete subjects. Name the screen, file, button, value. "The Send button stays disabled at 0.01 TON", not "the issue persists".
- No idioms, no filler. Delete "basically", "it seems", "in order to", "please note", "as mentioned".
- Numbers with units. "3 attempts", "0.05 TON", "42 s". Use digits.
- Lists for steps. Number steps. One action per step. Put the condition first: "If the gate fails, retry once."
- Warnings before the step they apply to, with the reason: "WARNING: This step signs a transaction. It sends 0.05 TON from wallet A to wallet B."
Words to prefer
| Use | Not |
| do, make, show, find, stop, start | perform, carry out, facilitate, leverage |
| use | utilize, employ |
| fail / pass | not succeed / succeed |
| before / after | prior to / subsequent to |
| because | due to the fact that |
| can / cannot | is able to / is unable to |
| about | approximately (unless you give a range) |
Make it readable, not boring
- Verdict first. Line 1 says the result:
PASS,FAIL,BLOCKED,HANDOFF, and why in one clause. - Tables for comparison, lists for sequence, prose only for a reason.
- Show, do not describe. Paste the exact error line, the file:line, the value on screen.
- Empty section = one word. "None." Do not delete required sections, do not pad them.
- Bold the one thing the reader must act on per section. Only one.
- End with the next action and its owner. "Next: the ticket owner checks the preview at
<url>."
Check before you send
- Each sentence ≤ 25 words? Passive voice gone?
- Every claim has evidence (path, line, value, video)?
- Same term for the same thing everywhere?
- First line = verdict? Last line = next action?
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

