Anti slop
Kill generic AI patterns before they ship — filler prose, over-commenting, defensive over-engineering, unnecessary abstractions, emoji headers. Apply on any UI, copy, or code that will be read by a human. Use when reviewing or writing UI text, code comments, READMEs, or any output a human will read.From its SKILL.md
npx -y skills add youcisla/Agent-Foundry --skill anti-slopAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its file declares
Copied from the file, not written here
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
2.3 KB, as published. Nobody here has run it
Anti-Slop
Generic AI output has tells. Catch them before the user does.
The five categories
- Filler prose. "It's worth noting that...", "In this implementation, we...", "Let me explain how this works..." — delete on sight. If a sentence doesn't add information, cut it.
- Over-commenting. Code that explains what it does (
// loop through arrayabovefor (const x of arr)). The code is the comment. Comments should explain why, not what. - Defensive over-engineering. Try/catches around things that can't throw. Null checks on values that just got validated. Validation of external API inputs you control. If a failure mode can't happen, don't code for it.
- Unnecessary abstractions. Helper functions called once. Config objects for two settings. Factory classes with one implementation. If it's only used once, inline it.
- Emoji headers. "🚀 Quick Start", "✨ Features", "💡 Tip" — emoji in docs screams "AI wrote this." Strip them.
The test
Before declaring done, read your output and ask: "If a human wrote this, would their coworker assume they were trying too hard?"
If yes, cut.
When in doubt
Show your output to a fresh pair of eyes (a subagent with no context). If they say "this is generic AI," trust them and rewrite.
When to skip
- The user is asking for a specific style and slop is what they want (rare, but it happens — internal brainstorming, first drafts).
- The output is throwaway (a debug print, a test).
Anti-patterns
- Skipping verification when the change "feels small"
- Reasoning by analogy without a real example
- Acting on a claim you have not verified this session
- Choosing speed over accuracy when accuracy is what the task requires
Verification Checklist
- The claim or action has been verified against a live source
- The output matches the request's scope (no scope creep)
- Slop markers are absent (filler, hedging, emoji headers)