de-ai-prose
Skill2 starsChanged 4 months agoMITView on GitHub
Use when about to show any prose a human will read - docs, README, commit bodies, UI copy, store text.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- eisbaw/mped-skillstheir own version, first seen Aug 21, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- eisbaw/mped-skills★ 11same 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 repository19 other files it gives its agents.
- build-release-mindsetSkill
- critical-thinkingSkill
- entry-point-auditSkill
- feasibility-guardSkill
- fix-in-the-shared-layerSkill
- fix-the-root-causeSkill
- independent-review-gateSkill
- logging-for-remote-diagnosisSkill
- no-duplicate-logicSkill
- opportunistic-fixesSkill
- performance-at-scaleSkill
- plan-with-teethSkill
- project-onto-all-systemsSkill
- question-the-premiseSkill
- tests-with-teethSkill
- user-action-edge-casesSkill
- using-instinctsSkill
- ux-designer-mindsetSkill
- verify-against-codeSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
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 32
Keep bold for genuinely key terms, not decoration.
- Distinctive: line 34
Read it back and ask: "would a tired engineer writing this actually phrase it this way?" If it sounds like a polished AI explainer, flatten …
≈ “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
The rule
Readers can tell when a machine wrote the text, and it costs trust the same way sloppy code does. After you write any prose a person will read, read it back once and cut the tells. Plain words, varied sentences, say the thing instead of announcing you're about to say it.
Fires when
About to show a human a README, a doc page, a commit or PR body, a changelog entry, a UI string, store copy — anything a person will read as writing rather than run as code.
Tells to cut
- Signposting sentences: "Here's the thing.", "That's the point.", "This is the important part.", "By the end you'll know what, why, and how."
- Closers like "That's it." or "And that's all there is to it."
- Em-dash overuse as the default connector. The constant em-dash rhythm is a fingerprint.
- Parallel triads everywhere ("a texture, a config, a script"), over-balanced sentences, the list-of-three cadence.
- Arrow constructions in prose ("write one function -> the whole thing appears").
- A table for everything; bold sprinkled on every other phrase as decoration.
- Bullet lists where every item opens with a bold label ("Fast: ...", "Simple: ..."), parallel from top to bottom.
- Cutesy section names and peppy filler ("the payoff", "the ones that bite").
- Paragraphs that are all the same length and shape. Too tidy.
How to apply
Plain, varied sentences. Some short. Let one run long and a little uneven, like a person typing.
Say it directly instead of signposting it. Use em-dashes rarely. Prefer periods, commas, "and". Vary connectors. Cutting an em-dash means rebuilding the sentence (a comma, a colon, parentheses, or two sentences), not swapping a different mark into the same joint.
Keep bold for genuinely key terms, not decoration. Drop a table where a sentence reads more naturally.
Read it back and ask: "would a tired engineer writing this actually phrase it this way?" If it sounds like a polished AI explainer, flatten it.
Before / after
Before (AI voice):
Here's the thing about our caching layer — it's fast, it's simple, and it's reliable. The payoff? Sub-millisecond reads.
After (human):
The cache keeps reads under a millisecond. It's a plain in-memory map with a TTL, nothing clever.
What changed: dropped the signpost, dropped the triad, dropped the rhetorical question, said the concrete thing.
Red flags
| Thought | Reality |
| "It's just a commit message" | A commit body is prose someone will read. Same pass. |
| "The user asked for polish" | Polish means clear, not machine-shiny. |
| "A table makes this clearer" | Sometimes. A table for everything is a tell. |
This skill must obey its own rule. The read-back pass applies here too. If this file sounds like AI, it has failed on its face.
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.