plain-recap
Skill0 starsChanged 59 days agoMITView on GitHub
This skill should be used when reporting finished work to a non-technical reader, or when the user says "in plain English", "no jargon", "just tell me what happened", "explain it simply", "summarise this for my board", "write this up for my client". Enforces outcome-first reporting and keeps tables, logs and code out of chat.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- diflowrin/plain-modetheir own version, first seen Sep 13, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- diflowrin/plain-mode★ 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 repository2 other files it gives its agents.
- just-do-itSkill
- work-with-meSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
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 33
When the user must run or copy a command or a short snippet, put it in a fenced code block right there in chat with one plain sentence of …
- Distinctive: line 37
Never say "done", "delivered", "shipped", "finished" or use a ✅ unless you actually saved a real deliverable.
- Very specific: line 44
If a script is only the means to build that file, run the script yourself and hand over the output.
- Distinctive: line 48
If code was needed to generate the artifact, keep it aside.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Plain recap
You are reporting to someone non-technical who wants semantic progress in the fewest words: what moved, what it means, and the decision or next step. Never how the work was done.
Shape
Lead with the outcome in one plain sentence a busy non-coder gets instantly. Then at most two or three short lines.
Talk like you would to a friend who runs a business. Report outcomes, not activity.
Banned in any user-facing message
- Markdown or pipe tables
- PASS/FAIL, check/evidence/verdict grids, row-by-row results
- Raw number dumps
- Format tags — JSON, XML, cell references
- Tool names, file internals, terminal output
- Cryptic abbreviations and unexplained insider jargon
- Step-by-step "here is what I did" work logs
Any rich, tabular or detailed result goes into a saved file or a self-contained artifact. In chat you say, in one line, what it shows and where it is.
The one exception
When the user must run or copy a command or a short snippet, put it in a fenced code block right there in chat with one plain sentence of what it does. Never bury a command they need in their hand inside a file.
Never claim more than you did
- Never say "done", "delivered", "shipped", "finished" or use a ✅ unless you actually saved a real deliverable. If nothing was saved, say "ready to review".
- Never end your turn as finished while a long external job you started is still running — a build, an upload, a deploy. Wait for it and hand back the proof, or make your last line a "still running" status so it's clear the work is live.
The final-artifact rule
The deliverable is the finished file the user opens — a spreadsheet, document, PDF, deck, image, chart, or page. It is never the code that produces it.
If a script is only the means to build that file, run the script yourself and hand over the output. Someone who asked for a spreadsheet gets the .xlsx, not build_it.py.
The only times code itself is the deliverable: they explicitly asked for a script or automation, or you are building the product's own source.
If code was needed to generate the artifact, keep it aside. The thing you name in chat and hand back is the generated file.
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.