plain-english
Skill2 starsChanged 8 days agoMITView on GitHub
Writes plain prose for readers of any language: READMEs, release notes, design docs, records. Use when writing text for a person.
15 other projects use a version of this.
Adopted by
Most recently taken up by
- niksavis/handilyword for word, first seen Nov 8, 2026
- sorawit-w/agent-skillstheir own version, first seen Nov 1, 2026
- ptrandev/claude-skillstheir own version, first seen Oct 29, 2026
- meowdiocre/meowpitheir own version, first seen Oct 27, 2026
- fedemelo/agent-configtheir own version, first seen Oct 17, 2026
- MounirDhahri/skillstheir own version, first seen Oct 13, 2026
Other versions15 projects use a version of this.
Word for word · 1
- niksavis/handily★ 2100% same
Edited · 0
None found.
Wrote their own version · 14
- b1rdmania/claude-plain-english-skill★ 46same name
- Tradelord223/plain-english★ 14same name
- fedemelo/agent-config★ 4same name
- naticorrea-03/claude-code-skills★ 4same name
- Harish-here/maddog★ 3same name
- meowdiocre/meowpi★ 3same name
- CorySchulz/skills★ 2same name
- JoseArron/skills★ 2same name
- sorawit-w/agent-skills★ 2same name
- dstotijn/agent-skills★ 1same name
4 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 repository58 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- best-practices-auditSkill
- catalog-authoringSkill
- cli-toolsSkill
- conventional-commitsSkill
- councilSkill
- decompose-planSkill
- falsify-firstSkill
- find-skillsSkill
- harness-clientSkill
- harness-loopSkill
- hill-climbSkill
- interface-factsSkill
- no-commentsSkill
- nodeSkill
- pythonSkill
- release-processSkill
- repair-in-placeSkill
- retention-probeSkill
- root-causeSkill
- session-finishSkill
- skill-creatorSkill
- swarmSkill
- test-disciplineSkill
- tier-injectionSkill
- validate-as-consumerSkill
- work-trackerSkill
- worktree-isolationSkill
- best-practices-auditSkill
- catalog-authoringSkill
- cli-toolsSkill
- conventional-commitsSkill
- councilSkill
- decompose-planSkill
- falsify-firstSkill
- find-skillsSkill
- harness-clientSkill
- harness-loopSkill
- hill-climbSkill
- interface-factsSkill
- no-commentsSkill
- nodeSkill
- plain-englishSkill
- pythonSkill
- release-processSkill
- repair-in-placeSkill
- retention-probeSkill
- root-causeSkill
- session-finishSkill
- skill-creatorSkill
- swarmSkill
- test-disciplineSkill
- tier-injectionSkill
- validate-as-consumerSkill
- work-trackerSkill
- worktree-isolationSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 14 edited versions we read keep these.
4
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 13
Write ASD-STE100 Simplified Technical English:
- Distinctive: line 18
One idea per sentence: Do not join two facts with a dash, a colon or a semicolon.
- Distinctive: line 61
Read each sentence as a person with a different first language.
- Distinctive: line 62
Check each claim. Every quoted command must exist, every path must resolve, and every transcript must be one you ran.
“Common” is measured: kept by at least 6 in 10 of the 14 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
<!-- Generated by `basicly skills-build` from skill.yaml. Do not edit; edit the source. -->Plain English
Write prose that a reader with a different first language and culture understands on the first pass. The skill covers a README, a landing page, a release note, a design document, a commit body, a tracker record and an error message. For a catalog guidance body, use the catalog-authoring skill.
Rules
Write ASD-STE100 Simplified Technical English:
- One word, one meaning. A synonym reads as a second thing.
- Active voice. "The gate refused the commit", not "the commit was refused".
- Short sentences. 20 words or fewer for an instruction, 25 or fewer for a description.
- One idea per sentence. Do not join two facts with a dash, a colon or a semicolon.
- Keep
a,an,theandthat. Without them the reader reads the sentence twice. - Three nouns together at most. "the cost of a lane", not "lane token cost floor".
- No idiom, slang or metaphor, unless this repository defines the term. Idiom does not survive translation.
- No
-ingverb where a plain verb works. "the gate refuses", not "the gate is refusing". - Write an abbreviation in full the first time.
- Put bad news first. A correction, a limit, an overrun or a broken assumption goes above the good news.
- Mark every number as measured, sourced or assumed. Name the command for a measured number and the source for a sourced one.
Delete marketing
| Delete | Write |
Four pillars, not a bundle of files | Four pillars |
Read the design, not just the pitch | Read the design |
One command, into any git repo | Install into any git repo |
The process is code, and so is the enforcement | The workflow and the gates are code |
What is unusual here is that … | the fact |
The pattern is "X, not Y". Test it: name Y and ask who believed it.
- Keep it when Y is a misreading that a careful reader would make. "A lane claim is a lease, not ownership" removes an error.
- Delete it when Y is a strawman, an unnamed competitor or nothing. Then it only adds emphasis.
- In a title, delete it almost always. A title names the section.
Also delete:
- A comma that joins a second clause to a title to make it sound important. Put that clause in the body.
Plenty of projects …,What is unusual …,The only harness that …. A comparison is a claim and needs evidence. Measure it or delete it.
Structure
| Form | Use |
| Table | Compares two or more things |
| List | Counts things |
| Code block | Real output that you copied, never output that you imagined |
| Paragraph | Explains one thing |
A paragraph that describes a shape does not show it. Draw the shape.
Before you commit the text
- Read each sentence as a person with a different first language. Replace a word that works only in your culture.
- Check each claim. Every quoted command must exist, every path must resolve, and every transcript must be one you ran.
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.

