Skip to content
SkillModel-led550 tokens in use

Stop Slop

Cut the predictable AI tells from drafts: filler openers, adverbs, formulaic structures and passive voice.

19,089 stars on the repository MIT Licensehardikpandya/stop-slop

Skill label

measured from its files

What installing Stop Slop costs

26tokens idle
550tokens in use
3,043tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter12/15
  • Structure16/25
  • Examples3/15
  • Output5/15
  • Size15/15
  • Resources11/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Needs attention
  • Development activity0
  • Maintenance0
  • Community48
  • Maturity32
  • Momentum40

Stop Slop is an agent skill for editing prose. It gives the assistant eight core rules and a quick-check list for removing the patterns that make text read as machine-written: throat-clearing openers, emphasis crutches, business jargon, adverbs, vague declaratives, passive voice and em dashes.

After editing, the assistant scores the draft from 1 to 10 on directness, rhythm, trust, authenticity and density, and revises anything below 35 out of 50.

What You Get

  • Eight core rules for direct, active, specific prose
  • Reference files with phrases to remove, structures to avoid and examples
  • A five-part score with a pass mark

Common Use Cases

  • Editing AI-assisted drafts
  • Reviewing marketing and blog copy
  • Checking your own writing against a list of tells

What Makes It Unique

It names the tells one by one, down to sentence starters and the quotable one-liner, and it ends with a numeric score so the assistant knows when to revise again. The author keeps the whole skill to a few short files.

Under The Hood

The skill is a SKILL.md with three reference files and no scripts. It loads the reference files on demand and edits text you give it. It runs no commands and reaches no network.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers