agentleFS
youcislayoucisla/Agent-Foundry/skills/core/anti-slop/SKILL.md

anti-slop

Skill1 starsChanged 23 days agoMITView on GitHub

Kill generic AI patterns before they ship — filler prose, over-commenting,

33 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use research and handoff.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • NVIDIASkill

    research

    Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.

    Also in 3 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 32 edited versions we read keep these.

  • 1

    Distinctive

    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
  1. Distinctive:

    Before declaring done, read your output and ask: "If a human wrote this, would their coworker assume they were trying too hard?"

    line 30

“Common” is measured: kept by at least 6 in 10 of the 32 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Anti-Slop

Generic AI output has tells. Catch them before the user does.

Procedure

The five categories

  1. 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.
  2. Over-commenting. Code that explains what it does (// loop through array above for (const x of arr)). The code is the comment. Comments should explain why, not what.
  3. 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.
  4. Unnecessary abstractions. Helper functions called once. Config objects for two settings. Factory classes with one implementation. If it's only used once, inline it.
  5. 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).

Worked example

One review note, before and after the five categories.

Before
  // Loop over each row and push it into the result array
  // It's worth noting that this implementation is straightforward.
  for (const row of rows) result.push(row);

After
  for (const row of rows) result.push(row);

Anti-patterns

  • A sentence that restates the heading without adding information.
  • A comment that narrates the next line of code.
  • A helper, config object, or factory used once.
  • Emoji headings or "Get started in seconds" filler.

Verification Checklist

  • Every sentence adds information or a decision. (step 1)
  • Comments explain why, not what. (step 2)
  • No abstraction exists without a second caller. (step 4)
  • No emoji headers or marketing filler remain. (step 5)
  • Error handling covers failures that can actually happen. (step 3)

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.