Individual skill

anti-slop

Remove AI slop from any voice-bearing prose — original posts, threads, articles, long-form, emails, docs, READMEs, marketing copy, bios, scripts. Use when drafting text meant to sound like a specific person or brand, when rewriting text that reads generic, corporate, or AI-generated, or when asked to humanize, de-slop, audit, or "make this sound like me / like us." Works in any agent (Claude Code, Codex, Cursor, custom) — no tools required. NOT built for X/Twitter reply batches: those need target selection on top of this skill's gate, which is out of scope here.

anti-slop/SKILL.md

Read pinned source

Source commit 8896899097c6b169699d93fb63f17312cb0b13d9

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: No
Repository scan complete: Yes
Skill scan complete: Yes
Observed behavior: Not checked yet
Last checked: Nov 5, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 21
Repository last updated: Aug 6, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

ai-agents Repository topic
ai-detection Repository topic
ai-slop Repository topic
ai-writing Repository topic
anthropic Repository topic
chatgpt Repository topic
claude Repository topic
claude-code Repository topic
claude-skills Repository topic
content-writing Repository topic
marketing Derived category
security Derived category
docs Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 10,890 bytes
references/audit-rubrics.mddoc · 5,194 bytes
references/generation.mddoc · 2,863 bytes
references/master-list.mddoc · 17,405 bytes
references/tells.mddoc · 5,992 bytes
references/voice-binding.mddoc · 3,920 bytes

Read excerpt


# anti-slop

Slop is not a vocabulary problem. It is manufactured upstream: alignment training collapses output toward the statistical mean (mode collapse, driven by typicality bias in preference data — arXiv 2510.01171), single-sample generation returns the most typical completion, and a context starved of specifics can only produce the average of everything. Banned-word lists treat the symptom. At adoption scale they mint a new house style — the zero-em-dash, no-adverbs voice is already its own tell, and Wikipedia's own tells-catalog maintainers warn that scrubbing signs "could just make detection harder."

**The job: make the output sound like a specific person with something specific to say.** Both halves are mandatory. This skill intervenes at four layers and measures whether it worked. It is a writing-quality protocol, not a detector-evasion tool.

---

## Modes

| Mode | When | Run |
|---|---|---|
| **DRAFT** | writing new text | Layers 1→2→3→4, ship with score |
| **AUDIT** | handed existing text | Layers 3→4, report score before/after + fix list |