simple-english
Skill142 starsChanged 22 days agoMITView on GitHub
Use when the user explicitly asks for simple English, plain English, or for text a non-native English speaker can read easily — rewrites docs, READMEs, issues, comments, or UI text into plain words and translation-friendly grammar, still native-sounding. Prose the user signs in their own voice goes to write-like-me instead
26 other projects use a version of this.
Adopted by
Most recently taken up by
- taixuann/development-spacetheir own version, first seen Nov 8, 2026
- miklschmidt/archboardtheir own version, 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/dotfilestheir own version, first seen Nov 2, 2026
- nightscout/nocturnetheir own version, first seen Nov 2, 2026
Used with
Projects with it also use xsai, pnpm and 10 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 versions26 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 26
- moeru-ai/airi★ 51ksame name
- chromedp/chromedp★ 13ksame name
- xo/usql★ 10ksame name
- AminBlg/SimpleEnglish★ 3.9ksame name
- TanStack/ai★ 3.3ksame name
- moeru-ai/xsai★ 667same name
- danielvm-git/bigpowers★ 288same name
- moeru-ai/auv★ 207same name
- microsoft/oxidizer★ 184same name
- nightscout/nocturne★ 163same name
16 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 repository14 other files it gives its agents.
- AGENTS.mdAGENTS.md
- publish-pluginsSkill
- upgrade-playbooksSkill
- audit-agent-settingsSkill
- best-practicesSkill
- blindspotSkill
- commitSkill
- differenceSkill
- fuck-over-engineeringSkill
- prSkill
- refactor-agents-mdSkill
- refactor-memorySkill
- refactor-skillSkill
- write-like-meSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 26 edited versions we read keep these.
5
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 15
Meaning is untouchable: Every fact, value, condition, and caveat in the source survives the rewrite.
- Distinctive: line 16
Never invent specifics: Keep each fact at its original precision and flag gaps.
- Distinctive: line 22
Load the rules: Read references/writing-rules.md in full: sentence structure, word choice, the clarity helpers, tone, and the substitution …
- Distinctive: line 36
Every pronoun's referent unambiguous, every abbreviation defined at first use.
- Distinctive: line 38
No idioms, culture-specific references, Latin abbreviations, or directional cross-references ("above", "below").
“Common” is measured: kept by at least 6 in 10 of the 26 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 or rewrite the given text in Global English: the global-audience tier that Google, Microsoft, MDN, Red Hat, and GitLab documentation follows. Clear structure, unambiguous words, translation-friendly grammar, no controlled dictionary, no hard word caps. The rewrite must give the same technical facts as the source and still sound like a native speaker wrote it.
Ground rules
- Meaning is untouchable. Every fact, value, condition, and caveat in the source survives the rewrite. Softened obligations stay soft: "should" stays a recommendation unless the source means a requirement.
- Never invent specifics. Keep each fact at its original precision and flag gaps. Do not fabricate values, names, or conditions.
- Quoted text is frozen. Code spans and blocks, commands, config keys, file paths, UI labels, error messages, and identifiers stay exactly as they are. Rewrite the prose around them.
- Voice survives. Clarity edits that flatten prose into choppy fragments are regressions. Filler drops freely ("it should be noted that"), personality stays.
Workflow
- Load the rules. Read references/writing-rules.md in full: sentence structure, word choice, the clarity helpers, tone, and the substitution table.
- Collect the source. Take the text from the conversation, or Read the files or sections the user pointed at. When the user wants new text drafted instead of existing text rewritten, collect the facts to state (from the conversation, code, or files) and treat them as the source for every later step. Done when you hold every passage to rewrite or every fact to state.
- Sort each passage into procedure (imperative work steps), description (declarative prose), or micro-text (headings, UI labels, error messages). Procedures get imperative mood and condition-first ordering. Micro-text gets a verb when clarity needs one.
- Map the terminology. List each concept that appears under more than one name, pick one term per concept (prefer the project's established names), and use it everywhere. Done when no concept has two names and no word carries two meanings.
- Rewrite sentence by sentence. Subject-verb-object with the subject early, one idea per sentence, active voice and present tense, conditions first, small words kept ("that", "who", articles), pronouns with more than one possible referent replaced by their nouns, noun stacks broken at two modifiers, hidden verbs uncovered ("install", not "perform an installation"), idioms and phrasal-verb bloat swapped per the substitution table. Kohl's main rule decides every edit: no change that sounds unnatural to a native speaker.
Verify every paragraph and sentence against the checklist:
- One topic per paragraph, the point stated in its first sentence.
- Subject and verb early, at most three linked clauses, no "there is/are" openers.
- Procedures imperative with conditions first.
- Every pronoun's referent unambiguous, every abbreviation defined at first use.
- Terminology consistent with the map from step 4, parallel ideas in parallel form.
- No idioms, culture-specific references, Latin abbreviations, or directional cross-references ("above", "below").
- The sentence still reads naturally aloud.
Done when every sentence passes, or its deviation is deliberate and appears in the report.
- Deliver. Present the rewrite. Edit files in place only when the user asked for the files to change. After the rewrite, report only what applies:
- The terminology map, so the user can veto term choices.
- Judgment calls where the source was ambiguous and the rewrite picks one reading.
- Gaps where the source lacks specifics the reader will need.
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.

