Is the Slop Check skill free?

Yes. The skill itself is free from allanta8/slop-check. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Slop Check SkillProof Score?

9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.

How do I install Slop Check?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Slop Check with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Slop Check

Structured AI-slop audit: quotes every violation, scores 8 dimensions, gives a PASS/REWRITE verdict

by allanta8 · allanta8/slop-check

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.6/10
Tested: Jul 15, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · f5cc98b

Audited the same slop-filled paragraph twice: an unguided review caught about 5 cliches and gave a rough 3-4/10, while following the skill verbatim quoted all 12 Tier-1 violations by name, ran the 3 quality gates (all FAIL), scored 8 dimensions at 1.6/10 overall, and closed with a REWRITE verdict plus 3 concrete rewrite directions.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 9/10
Docs & honesty 5/5

What Slop Check does

Audits a draft for AI-tell patterns — banned vocabulary, filler phrases, fake balance, hourglass closes, forced persona — then runs three pass/fail quality gates and an 8-dimension 1-10 score before returning a PASS / NEEDS REWRITE / REWRITE verdict with concrete rewrite directions. Triggers when checking, scoring, rewriting, or humanizing posts, articles, landing pages, essays, or newsletters before publishing.

How to install Slop Check

git clone https://github.com/allanta8/slop-check
cd slop-check
mkdir -p ~/.claude/skills
cp -r . ~/.claude/skills/slop-check

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Slop Check

/slop-check Structured AI-slop audit: quotes every violation, scores 8 dimensions, gives a PASS/REWRITE verdict

It also activates on plain-language prompts like these:

Can you check this blog draft for AI-sounding phrases before I publish it?
Score this newsletter draft for AI slop and tell me if it needs a rewrite
Does this landing page copy read like it was written by an AI to you?

Frequently asked questions

Is the Slop Check skill free?: Yes. The skill itself is free from allanta8/slop-check. SkillProof publishes the install command and an independent test verdict at no cost.
Does Slop Check work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Tested · Works. Audited the same slop-filled paragraph twice: an unguided review caught about 5 cliches and gave a rough 3-4/10, while following the skill verbatim quoted all 12 Tier-1 violations by name, ran the 3 quality gates (all FAIL), scored 8 dimensions at 1.6/10 overall, and closed with a REWRITE verdict plus 3 concrete rewrite directions.
What is the Slop Check SkillProof Score?: 9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
How do I install Slop Check?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Slop Check with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.