prose-quality
Skill12 starsChanged 38 days agoMITView on GitHub
Use when the deliverable is authored or edited prose whose wording matters (docs, READMEs, release notes, public copy) or when the user asks to tighten, de-AI, or review writing. Not for chat answers, code review, or explanations of current work.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- skyf0xx/hedgehog-core-copywriting-prose-engineeringtheir own version, first seen Oct 25, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- skyf0xx/hedgehog-core-copywriting-prose-engineering★ 20same 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 repository4 other files it gives its agents.
- chart-integritySkill
- improve-codebase-architectureSkill
- performance-tradeoffSkill
- skill-auditSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Keep each claim at its original strength and scope.
- Distinctive: line 12
Add no facts, numbers, or benefits the source lacks.
- Distinctive: line 14
When the text describes code or a tool you can read, check its behavioral claims against it.
≈ “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
Prose quality
An edit succeeds only if readers draw the same conclusions from the new text, with less effort.
Keep meaning fixed
- Keep each claim at its original strength and scope. Carry over hedges, conditions, sample sizes, units, hardware, baselines, and "experimental" or "may not" limits. Never turn "did not measure X" into "X was unchanged."
- Add no facts, numbers, or benefits the source lacks. Ask, or leave a marked gap.
- Preserve commands, paths, flags, symbols, quotations, and normative text (MUST, SHOULD) exactly.
- When the text describes code or a tool you can read, check its behavioral claims against it. Fix or flag mismatches and say what you checked.
Edit to the requested depth
- Review only: return findings ranked by reader impact, errors (wrong, ambiguous, out of order) before style. No rewrite.
- Editing: keep the author's voice, terms, structure, and the document's conventions (heading case, quote style, spelling). One name per concept.
Remove generated-sounding patterns
Cut puffery, signposting, filler, stacked hedges, summary closers, and decorative bold, emoji, or headers. Thin out em-dash chains, "not X but Y" contrasts, and forced triplets without substituting another tic. Keep a negation that states a real limit or hazard.
Before returning
Compare old and new for any claim that got stronger, weaker, or lost a qualifier. Name material ambiguities instead of writing around them.
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.