agentleFS
taljeontaljeon/plzdo/skills/anti-slop/SKILL.md

anti-slop

Skill9 starsChanged 18 days agoMITView on GitHub

Use for code changes in any language. Preserve behavior, types and boundary validation, keep edits scoped, and verify with the project's declared checks and fresh evidence.

31 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use research.

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

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 30 edited versions we read keep these.

  • 2

    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:

    Avoid unnecessary type escapes.

    line 12
  2. Distinctive:

    Do not add inline disables or weaken configuration to make checks pass.

    line 14

“Common” is measured: kept by at least 6 in 10 of the 30 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

Code quality

Preserve behavior unless the request changes it. Use the language's types and runtime input validation, keep changes within scope, and retain error handling. Increase an existing dependency's minimum supported version only when requested; otherwise report manifest and lockfile mismatches.

Run the project's declared checks in their required order. Where applicable, check lint, types or build (syntax for shell), then targeted tests. Read every exit code. A missing required tool or failed stage leaves the task incomplete. Distinguish lint, syntax checks and compilation; one does not prove another passed.

Avoid unnecessary type escapes. Validate boundary inputs at runtime and use cohesive typed objects when the domain calls for them. Apply language-specific rules only to that language. Before rewriting an expression, check presence versus falsy values, evaluation order and the type contract.

Do not add inline disables or weaken configuration to make checks pass. If semantics require a policy exception, request a narrow review specifying the rule, path, source hash, reason, owner and expiry; do not grant it yourself.

A removed, skipped or loosened test, including a dropped assertion or lowered threshold, is a behavior change. Report the reason and the check that now covers it; if the requirement itself was removed, identify that requirement. Passing checks after weakening them is not evidence that the original behavior remains covered.

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.