avoid-ai-tropes
Skill0 starsChanged 29 days agoMPL-2.0View on GitHub
Use when writing or editing any prose the user will read or publish - blog posts, essays, READMEs, docs, code comments, docstrings, commit bodies, PR and MR descriptions, app store listings, replies. Catalogues the two things that mark text as AI-written: the sentence, tone and formatting patterns (the whole contrastive family - negative parallelism "it's not X, it's Y", preferential contrast "Y rather than X", tailing negation "..., not Y" - em dashes as pauses, punchy fragments, bold-first bullets, title case headings, signposted conclusions, "it's worth noting", "serves as", promotional adjectives) and the vocabulary (plainly, quietly, genuinely, nobody, deliberately, indistinguishable, load-bearing, asymmetry, premise, and objects given human verbs - X carries Y, X buys Y, X asserts Y, X refuses to). Ships a scanner. Use it whenever the user asks to clean up, tighten, de-slop or de-AI writing, and before drafting documentation, a commit message or a PR description.
- Installs packages
1 other project uses a version of this.
Adopted by
Most recently taken up by
- nunomen/claude-skillstheir own version, first seen Mar 18, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- nunomen/claude-skills★ 1same 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 repository7 other files it gives its agents.
- d2-diagramsSkill
- fdroid-publishSkill
- html-deckSkill
- nextcloud-web-appSkill
- standalone-web-appSkill
- ticketSkill
- translateSkill
The 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.