plain
Skill1 starsChanged 3 months agoMITView on GitHub
Rephrase an explanation in plain language without losing substance. Use when a synthesis is too dense to act on — legal, tax, accounting, product research, or technical — and the reader needs to understand it well enough to decide.
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
- dtiger1889-ops/claude-harness-toolboxtheir own version, first seen Oct 12, 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.
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
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
- dtiger1889-ops/claude-harness-toolbox★ 31same name
- rizukirr/vibekit★ 20same name
- selfishprimate/plain★ 16same name
- andeeplus/aplus★ 2same 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.
In this repository29 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docxSkill
- pdfSkill
- app-icon-studioSkill
- audit-promptSkill
- bootstrap-goal-projectSkill
- boy-scoutSkill
- brand-namingSkill
- create-engineering-skillSkill
- create-prSkill
- elevenlabsSkill
- firebase-adminSkill
- firebase-hosting-basicsSkill
- gmailSkill
- linearSkill
- nano-banana-app-iconSkill
- new-projectSkill
- product-researchSkill
- pr-qa-browserSkill
- publish-researchSkill
- readme-best-practicesSkill
- researchSkill
- ripple-checkSkill
- roadmap-pageSkill
- scopeSkill
- searchexaSkill
- slackSkill
- triage-pr-commentsSkill
- write-loopSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
6
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 17
Keep a term of art when the reader will encounter it again — on forms, in laws, in contracts, in vendor docs, in error messages — and …
- Distinctive: line 23
every obligation, requirement, or action item, and who it falls on
- Distinctive: line 24
every number: deadlines, amounts, thresholds, prices, limits
- Distinctive: line 25
every condition that changes the outcome ("this applies only if…")
- Distinctive: line 26
every material risk, penalty, or trade-off
- Distinctive: line 29
If simplifying would collapse a distinction that changes the decision, keep the distinction and explain it plainly instead.
“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
Rephrase the target explanation for an intelligent reader with no background in this domain. They are not reading out of curiosity: they need to understand the material well enough to make a decision and act on it themselves, so the rewrite succeeds only if it is both understandable and complete enough to act on.
Target: $ARGUMENTS — if empty, rephrase your most recent substantive explanation in this conversation, or the material the user just referenced.
Style
Write in the style of the SEC Plain English Handbook, at roughly an 8th-grade reading level: short sentences, one idea per sentence, active voice with a named actor ("you must file X by Y", not "a filing obligation arises"), everyday words over terms of art, concrete examples over abstractions.
Lead with the answer — what this means for the reader and what they should do. Explanation and evidence come after. Default to plain paragraphs; use lists or tables only when the content is a genuine comparison or enumeration.
Keep a term of art when the reader will encounter it again — on forms, in laws, in contracts, in vendor docs, in error messages — and define it in plain words the first time, in the same sentence. Otherwise replace it.
Substance
Plain language must not cost substance. Preserve every fact that changes what the reader would decide or do:
- every obligation, requirement, or action item, and who it falls on
- every number: deadlines, amounts, thresholds, prices, limits
- every condition that changes the outcome ("this applies only if…")
- every material risk, penalty, or trade-off
- the citations and sources behind factual claims
If simplifying would collapse a distinction that changes the decision, keep the distinction and explain it plainly instead.
If sources disagree, or the answer depends on a fact about the reader's situation you don't have, say so plainly and name the fact that decides it. Do not average disagreement into a vague middle ground, and do not let missing evidence silently become a "no".
Before answering
Compare the rewrite against the original. If a decision-relevant fact from the list above was dropped, put it back. A rewrite that survives this check is done — do not pad it back toward the original's length or density.
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.

