plain
Skill31 starsChanged 31 days agoMITView on GitHub
Re-expresses a dense response in plain English while preserving its substance. Use for /plain, "say that in plain English", "de-jargon this", "unpack that", or "explain that like a normal person". Targets the previous assistant message unless the user supplies another passage. Picture mode, only when asked (/plain show, or "show me" about an answer), re-explains with the smallest plain-text picture - pseudocode, a call tree, a component or file tree, or a diff of a tree.
7 other projects use a version of this.
Adopted by
Most recently taken up by
- andeeplus/aplustheir own version, first seen Oct 15, 2026
- michele-orsini-71/claude-skillstheir own version, first seen Oct 13, 2026
- rolandtolnay/llm-toolkittheir own version, first seen Oct 11, 2026
- petekp/claude-code-setuptheir own version, first seen Sep 23, 2026
- trebaud/skillstheir own version, first seen Aug 18, 2026
- rizukirr/vibekittheir own version, first seen Jul 31, 2026
Used with
Projects with it also use debug and create-pr.
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.
AnthropicSkilldebug
Structured debugging session — reproduce, isolate, diagnose, and fix. Trigger with an error message or stack trace, "this works in staging but not prod", "something broke after the deploy", or when behavior diverges from expected and the cause isn't obvious.
Also in 3 projects that use this
SentrySkillcreate-pr
Create pull requests following Sentry conventions. Use when opening PRs, writing PR descriptions, or preparing changes for review. Follows Sentry's code review guidelines.
Also in 3 projects that use this
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- petekp/claude-code-setup★ 48same name
- rizukirr/vibekit★ 20same name
- selfishprimate/plain★ 16same name
- andeeplus/aplus★ 2same name
- rolandtolnay/llm-toolkit★ 1same name
- trebaud/skills★ 1same name
- michele-orsini-71/claude-skills★ 0same name
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.
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Look up unfamiliar project codes, tags, acronyms, and phase names in their source files.
- Distinctive: line 17
Use short paragraphs or a clear list.
- Distinctive: line 23
Use enough space to explain the meaning.
- Distinctive: line 35
Put one or two plain sentences before each picture saying what it shows.
- Very specific: line 36
Use plain monospace text in a fenced block: ASCII only (|--,
--`, indentation), lines under about 60 characters so a phone terminal …
“Common” is measured: kept by at least 6 in 10 of the 5 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
Plain English
- Identify the target passage; ask only if the target is ambiguous.
- Look up unfamiliar project codes, tags, acronyms, and phase names in their source files. Do not guess. If a meaning is unavailable, say that explicitly.
- Re-express all the substantive content in ordinary sentences. Expand compressed clauses and define unavoidable technical terms at first use.
- Use short paragraphs or a clear list. Preserve qualifications, uncertainty, and actionable details; add no new analysis or next steps.
Example with fictional terminology:
- Dense: "The F027 gate blocks the B13 rung until the file hashes reconcile."
- Plain: "A check prevents the next build step until the two copies of the file match. They currently differ."
Use enough space to explain the meaning; brevity must not erase it.
Picture mode (only when asked)
Runs only on /plain show or when the user says "show me" about an answer; otherwise the output stays prose. Adapted from the show-me skill in humanlayer/skills (MIT).
- Resolve every code first (step 2 above). Labels inside a picture are words too; a tree node named
F027fails the same way a sentence does. - Pick the smallest picture that makes the point, usually one, rarely two:
- steps or logic: pseudocode in plain words, numbered or indented
- what runs what, in order: an indented call tree
- how parts or files are arranged and who owns what: a shallow component or file tree
- what changes: a
diffblock of the tree or list (-removed,+added) when the shape already exists; show the whole thing when most of it is new
- Put one or two plain sentences before each picture saying what it shows. Keep only the parts that answer the point.
- Use plain monospace text in a fenced block: ASCII only (
|--,`--, indentation), lines under about 60 characters so a phone terminal does not wrap them. - No Mermaid in a terminal or phone session, because it prints as raw text there. Do not write an HTML file or open a viewer. If plain text cannot carry the point (a screen layout, a dense comparison), say so and offer a rendered diagram instead.
- Everything above still holds: what the picture cannot hold goes in plain sentences under it, so no substance is lost and no new shorthand or analysis comes in.
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.

