simple-english
Skill1 starsChanged 16 days agoMITView on GitHub
Write or rewrite text in plain, layman-readable English in the spirit of ASD-STE100 Simplified Technical English: short sentences, active voice, simple tenses, one word one meaning, condition before command, every technical term defined at first use, no AI slop. Default mode is Plain. Strict mode applies full STE vocabulary compliance when the user names STE, ASD-STE100, or compliance. Use for documentation, READMEs, runbooks, procedures, error messages, release notes, incident reports, API guides, and explanations for readers outside the field. Also use when the user says "STE", "Simplified Technical English", "ASD-STE100", "plain English", "layman's terms", "explain it simply", "no jargon", "de-slop", "make this readable", "write for non-native readers", or asks for docs that translate well. The same rules govern the reply: answer first, prose only.
27 other projects use a version of this, 11 of them edited.
Adopted by
Most recently taken up by
- lihbr/skillstheir own version, first seen Nov 15, 2026
- miklschmidt/archboardedited, first seen Nov 8, 2026
- zalando-incubator/agentic-identity-brokertheir own version, first seen Nov 8, 2026
- danielvm-git/bigpowerstheir own version, first seen Nov 6, 2026
- dio-az/dotfilesedited, first seen Nov 2, 2026
- nightscout/nocturnetheir own version, first seen Nov 2, 2026
Used with
Projects with it also use xsai, pnpm and 8 more.
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.
alint-devSkillxsai
Use this skill when the user is building with `xsai` or any `@xsai/*` package, or is evaluating xsAI for a small OpenAI-compatible workflow with text generation, streaming, tool calling, structured output, embeddings, image generation, speech synthesis, or transcription.
Also in 4 projects that use this
JetBrainsSkillpnpm
Node.js package manager with strict dependency resolution. Use when running pnpm specific commands, configuring workspaces, or managing dependencies with catalogs, patches, or overrides.
Also in 3 projects that use this
PydanticSkilli-have-adhd
Shape every response for an ADHD reader who reviews the work but does not do the coding — the agent does. Use whenever responding to ANY message — coding, debugging, planning, casual. Lead with the result or the decision. Surface anything needing the user's input as a structured question, never buried in prose they'll skim past. No preamble, no recap, no closers. State errors matter-of-factly. Make finished work visible. Trigger even on casual messages and even when brevity wasn't requested.
Also in 5 projects that use this
AWSSkillwait-what
Stop. That last message did not land: re-pitch it.
Also in 4 projects that use this
AWSSkillwizard
Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.
Also in 4 projects that use this
GoogleSkillsetup-matt-pocock-skills
Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
Also in 4 projects that use this
- +2 more from aws
Other versions27 projects use a version of this.
Word for word · 0
None found.
Edited · 11
- chromedp/chromedp★ 13k95% same
- xo/usql★ 10k85% same
- AminBlg/SimpleEnglish★ 4.5k90% same
- moeru-ai/xsai★ 66785% same
- microsoft/oxidizer★ 19392% same
- samson-art/transcriptor-mcp★ 2483% same
- ivanrvpereira/.agents★ 1991% same
- miklschmidt/archboard★ 1195% same
- chryzsh/claude-skills★ 285% same
- kwaa/skills★ 295% same
1 more not listed
Wrote their own version · 16
- moeru-ai/airi★ 51ksame name
- TanStack/ai★ 3.4ksame name
- danielvm-git/bigpowers★ 292same name
- moeru-ai/auv★ 207same name
- nightscout/nocturne★ 163same name
- vinta/hal-9000★ 143same name
- alint-dev/alint★ 137same name
- moeru-ai/alint★ 137same name
- zalando-incubator/agentic-identity-broker★ 79same name
- United-Codes/uc_ai★ 49same name
6 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 repository95 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- agent-architectureSkill
- agentic-evalSkill
- agent-owasp-complianceSkill
- agent-skill-stackSkill
- ai-readySkill
- ai-team-orchestrationSkill
- answer-me-with-htmlSkill
- anti-ui-slopSkill
- archifySkill
- autoresearchSkill
- batch-script-progressSkill
- cli-creatorSkill
- codebase-designSkill
- code-exemplars-blueprint-generatorSkill
- copilot-instructions-blueprint-generatorSkill
- create-agentsmdSkill
- create-architectural-decision-recordSkill
- create-github-action-workflow-specificationSkill
- create-github-issues-feature-from-implementation-planSkill
- create-readmeSkill
- create-specificationSkill
- create-technical-spikeSkill
- create-tldr-pageSkill
- docs-sync-auditSkill
- folder-structure-blueprint-generatorSkill
- gh-fix-ciSkill
- github-actions-hardeningSkill
- github-repo-careSkill
- impeccableSkill
- launchd-automationSkill
- mcp-security-auditSkill
- notion-cliSkill
- opencode-model-routerSkill
- playwright-cliSkill
- python-pypi-package-builderSkill
- refactorSkill
- swiftui-expert-skillSkill
- technical-documentationSkill
- workshop-driverSkill
- xerj-hubSkill
- xerjSkill
- anti-ui-slopSkill
- autoresearchSkill
- batch-script-progressSkill
- calling-frontend-from-tauri-rustSkill
- calling-rust-from-tauri-frontendSkill
- cli-creatorSkill
- codebase-designSkill
- code-exemplars-blueprint-generatorSkill
- configuring-tauri-appsSkill
- configuring-tauri-capabilitiesSkill
- configuring-tauri-cspSkill
- configuring-tauri-permissionsSkill
- configuring-tauri-scopesSkill
- copilot-instructions-blueprint-generatorSkill
- create-agentsmdSkill
- create-architectural-decision-recordSkill
- create-github-action-workflow-specificationSkill
- The first 60 shown.
The file
Show its rules and text
We split this skill into the rules it gives an agent
18 rules. 0 are common, 15 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 27 edited versions we read keep these.
15
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 30
When asked to write or rewrite documentation, apply these rules to the prose:
- Distinctive: line 33
Never touch code, identifiers, commands, flags, file paths, quoted errors, product names, or facts.
- Distinctive: line 35
Use simple tenses and active voice.
- Distinctive: line 37
Use complete grammar. No contractions, keep articles, keep "that".
- Distinctive: line 38
No semicolons and no em-dashes.
- Distinctive: line 42
Use formatting only where it carries structure.
- Very specific: line 45
Use American spelling. references/word-swaps.md maps the overused words to plain ones.
- Distinctive: line 51
After (procedural, headed, numbered):
- Distinctive: line 62
Every chat reply, in every mode, follows these rules:
- Distinctive: line 66
No em-dashes. Name the relation ("because", "but", "for example") or write two sentences.
- Distinctive: line 68
No contractions. No openers ("Certainly", "Great question") and no closers ("I hope this helps", "Let me know").
- Distinctive: line 69
Do not shorten quoted error text, security warnings, or confirmations before a destructive action.
- Distinctive: line 71
Before: The failure stems from control-plane leader election during pod churn — nothing to worry about!
- Distinctive: line 72
After: The pods restarted and the queue lost its leader for a short time.
- Very specific: line 78
If you kept a longer sentence on purpose, add one line under the text.
- Distinctive: line 80
When the user asks which rules the text broke, give a table instead.
- Very specific: line 86
Document: count the words in your three longest sentences.
- Distinctive: line 89
Read each step: does it name a host, a flag, or a prior step the reader must already have?
“Common” is measured: kept by at least 6 in 10 of the 27 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
Simple English
Write plain English that a smart reader outside your field understands on one read. The rules come from ASD-STE100, the controlled language that aerospace uses for maintenance manuals. Two registers exist: the document you write or rewrite, and the reply you type in chat. Each has its own short rule set below.
The Document
When asked to write or rewrite documentation, apply these rules to the prose:
- Classify each passage. Procedural text tells the reader what to do: imperative mood, 20 words per sentence, one instruction per sentence. Descriptive text explains: simple tenses, 25 words per sentence, one topic per paragraph, six sentences per paragraph at most.
- Never touch code, identifiers, commands, flags, file paths, quoted errors, product names, or facts. When the source gives no number or cause, keep the general statement.
- Condition before command, with a comma: "If the build fails, read the log."
- Use simple tenses and active voice. No present perfect ("has completed" → "completed"). No "-ing" verb after a comma (", making it easy" → new sentence). Name the actor: "You run the migration."
- Modals. Use can, will, must. If the action is required, change "should" to "must". If the action is optional, delete "should". Never use "would". In a procedure, delete "may", "might", and "could", because the reader must act on the text. In an error message, a status report, or any text that tells what a person or an agent does not know, keep the hedge. Keep "may have" and "might have" for an uncertain past event. Never turn a hedge into a fact.
- Use complete grammar. No contractions, keep articles, keep "that". Write short sentences, not telegraph style.
- No semicolons and no em-dashes. Write two sentences, or name the relation.
- One word, one meaning, for the whole document. Use
make sure thatfor check, verify, confirm, validate, ensure. Useconfigurationfor config, settings, options. Break noun chains over three words with a preposition ("the timeout value for the connection pool"). - Give the reader each term and each fact before the step that needs it. Define a concept term at its first use, under ten words, one per sentence. Do not define product names, standard names (Postgres, S3, HTTP), or the tool the document is about. Also name the host, the flag, or the prior step that a command depends on. "Restart the service" becomes "Restart the
syncservice on the host that runs the job." - State the fact, not its importance. Delete words that carry no fact: simply, seamlessly, robust, powerful, comprehensive, leverage, crucial, "in order to", "it is worth noting". No "not just X, it is Y". No decorative triplets. No "in conclusion".
- Use formatting only where it carries structure. No bold lead-ins, no bold as emphasis, no emoji, no heading over two sentences. A vertical list is for three or more parallel items or steps: colon on the lead-in, uppercase start, one instruction per item.
- Warnings: command or condition first, then the risk. "Do not run this against production. The command deletes rows."
Use American spelling. references/word-swaps.md maps the overused words to plain ones. For an error message, a runbook, an incident report, release notes, a commit message, or UI copy, read references/use-cases.md first. It names the mode and the pattern for each.
Before (AI output):
Connection timeouts. If sqlpipe hangs or fails with
dial tcp: i/o timeout, check that the host running sqlpipe can reach the Postgres port (usually 5432) — this is often a security group or firewall rule blocking the connection. If you're connecting to a managed database (RDS, Cloud SQL, etc.), confirm the instance allows connections from sqlpipe's IP.
After (procedural, headed, numbered):
Connection timeouts
sqlpipe stops with
dial tcp: i/o timeoutwhen it cannot connect to the Postgres port (5432 by default).
- Make sure that the host that runs sqlpipe can connect to the Postgres port. A firewall or security group usually blocks it.
- If the database is managed (RDS, Cloud SQL), make sure that the instance accepts connections from the IP of sqlpipe.
The Reply
Every chat reply, in every mode, follows these rules:
- Answer in prose. No headers, no bullet lists, no bold, no tables. A code block is legal when the reader must copy it.
- The first sentence gives the answer or the result. Do not restate the question.
- No em-dashes. Name the relation ("because", "but", "for example") or write two sentences.
- Define a concept term in a few words the first time you use it: "idempotent (safe to run twice)". Do not define product names.
- No contractions. No openers ("Certainly", "Great question") and no closers ("I hope this helps", "Let me know").
- Do not shorten quoted error text, security warnings, or confirmations before a destructive action.
Before: The failure stems from control-plane leader election during pod churn — nothing to worry about! After: The pods restarted and the queue lost its leader for a short time. It recovered without help. You do not have to do anything.
Output
Give the rewritten document. Do not add a preface, a count of the changes, or a closing offer.
If you kept a longer sentence on purpose, add one line under the text. Start the line with Kept as-is: and name the phrase and the meaning it protects. If there is nothing to report, leave the line out.
When the user asks which rules the text broke, give a table instead. Use these columns: rule, original text, rewritten text. End with the mode and the number of findings.
Self-Check Before You Deliver
- Machine pass. Run
scripts/ste-lint.py. Use--type replyfor a reply,--type proceduralfor a procedure, and--type descriptivefor explanation. Add--gateto fail on any finding. Fix each finding. The linter reads a word table as prose, so ignore a finding in a file that lists banned words. The linter counts "may", "might", and "could" as banned in every text. If rule 5 tells you to keep such a hedge, keep it and ignore the finding on that word. - Reply: search for
—,**,#, and a line that starts with-. Remove each one. - Document: count the words in your three longest sentences. Over 20 or 25, split. Search for
',has been,should,;,—,, making,**,check,verify,config, and any heading that covers fewer than three sentences. Fix each hit. - Modality: read each sentence that tells what nobody knows. Keep its hedge. Restore any hedge that the rewrite turned into a fact.
- Content: compare every number, unit, flag, path, and product name in the rewrite with the source. Each one must survive.
- Read each step: does it name a host, a flag, or a prior step the reader must already have? If not, add it or point to it.
Modes
Plain is the default and is all of the above. Strict applies when the user names STE, ASD-STE100, or compliance: read references/strict-vocabulary.md before you draft the document, and say once that no tool guarantees compliance. The reply stays Plain in every mode.
When asked to CHECK text instead of writing it, first open references/rule-catalog.md. Then report each violation as: rule number quoted from that file, the offending text, a compliant rewrite. Never cite a rule number from memory. When the user asked for compliance, end with one sentence: no tool can guarantee ASD-STE100 compliance, and the standard is a free download at asd-ste100.org.
What This Skill Can Check
The structural rules describe sentence shape. They stand on their own. The linter checks them: sentence length, active voice, one instruction per sentence, no semicolon, no em dash, no contraction, condition before command, simple tenses, and repeated synonyms.
The lexical rules come from the ASD dictionary of about 900 approved words. This skill does not ship that dictionary. Without it, apply the lexical rules as a direction of travel. Do not claim that a word is approved.
If you need the dictionary, build it on your own machine. Request the free standard at asd-ste100.org. Convert the PDF to text with pdftotext -layout. Run python3 scripts/dictionary/parse_dict.py ste9.txt in that folder. Then run python3 scripts/dictionary/emit.py scripts/dictionary to write approved.txt and not-approved.tsv where ste_dict_lint.py reads them. Run python3 scripts/dictionary/ste_dict_lint.py FILE to check the word choice in one file. The generated files are ignored by git. Do not commit them. Read scripts/dictionary/README.md for the full steps.
Limits
These rules are for facts and instructions, not marketing copy or brand writing, because they delete persuasion. Say so, and offer them for the docs instead.
References
references/rule-catalog.md: the 53 rules of Issue 9 with software examples, for CHECK modereferences/strict-vocabulary.md: the dictionary discipline for Strict modereferences/word-swaps.md: a map from overused words to plain onesreferences/slop.tsv: 69 words that read as machine writing, each with a plain swapreferences/use-cases.md: the mode and the pattern for error messages, runbooks, incident reports, release notes, commits, agent prompts, UI copy, and translation prepscripts/ste-lint.py: the machine pass. Run it before you deliverscripts/dictionary/: build the ASD word lists from your own copy of the standardscripts/VENDOR-NOTES.md: where each file came from and what this install changed
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.

