Take all the slop out of your AI writing. The #1 agentic anti-slop skill.
Score your writing 0 to 100 for AI slop, see the exact phrases behind the number, and edit them out without changing a single fact. Free, MIT, scored offline with no account. Worked examples and the full benchmark are at zero-slop.ai.
AI writing has a distinct tell: "It's not X. It's Y." "Here's the thing nobody tells you."
Zero Slop is an Agent Skill and ships no model. Claude, GPT, or another compatible model does the editing; Zero Slop supplies the workflow and the checks that refuse any change to a name, number, quotation or link. It runs in Claude Code, Cowork, Codex, Cursor, Warp, Zed, and any other harness that reads SKILL.md.
Paste this into Claude Code, Codex, Cursor, OpenCode, Warp, or Zed:
Install the Zero Slop skill globally from https://github.com/manavmishra/ZeroSlop
Or install it with npx:
npx skills add manavmishra/ZeroSlop --globalOr from the registry, which also installs the scorer as a command:
npx zero-slop install # add --harness codex|cursor|opencode|zed
npx zero-slop score draft.md # score without installing anythingChatGPT users can download dist/zero-slop-single-file.md.
Claude.ai users can upload dist/zero-slop.zip. npx skills update zero-slop --global updates it later.
/zero-slop (your writing)
You get the edited draft, a before-and-after score, and the flagged phrases quoted with why. /zero-slop inspect (your writing) reviews without rewriting.
For a folder, slopscore.py --batch drafts/ --gate 25 fails the build above the threshold.
290 weighted patterns and a 96-term lexicon, including:
- Binary contrasts: "It's not X. It's Y."
- Throat-clearing openers: "Here's the thing," "Let me be clear"
- Faux-insight setups: "What nobody tells you," "The part everyone misses"
- Colon reveals: "The best part: it learns."
- Dramatic fragments: "That's it. That's the whole thing."
- Superficial analysis: "highlighting the team's commitment to innovation"
- Importance puffery: "marks a pivotal moment," "a testament to"
- Weasel attribution: "experts agree," "studies show"
- Synonym cycling: the agent, the assistant, the tool, all one thing.
- Marketing riders: "robust" and "leverage" score only beside a marketing trigger, so a runbook stays quiet.
A reading pass covers defects of the whole document, which no span pattern reaches: one shape repeated seven times, statistics piled into a paragraph,
paragraphs that shuffle without loss. references/eval.md has all
80 checks.
Human writing scored 9 to 21 in data/corpus/must-not-flag/;
unedited AI drafts averaged 77 across bench/examples.json.
Eight roles form one workflow. Each is a job rather than a service, run as its own pass so nothing grades its own output. The research supports the checks, not the number eight, which is an engineering choice.
| Role | Who does it | What happens |
|---|---|---|
| 1. Scorer | Local tools | Finds the exact wording, rhythm, readability, and formatting problems that raised the writing score. |
| 2. Interpreter | Your AI assistant | Reads the claims, purpose, audience, structure, and voice before changing anything. |
| 3. Rewriter | Your AI assistant | Removes stock language and rebuilds order, rhythm, and tone without inventing detail. |
| 4. Fact gate | Local tools | Rejects any version that changes names, numbers, quotations, links, code, tables, paths, or structure. |
| 5. Copy desk | Fresh AI pass | Corrects grammar, spelling, usage, and consistency in the actual deliverable. |
| 6. Read-aloud editor | Fresh AI pass | Fixes stumbles, repetition, weak transitions, and awkward flow. |
| 7. Verifier | Local tools and your AI assistant | Compares text with source for facts, meaning, qualifiers, voice, format, structure. |
| 8. Fresh-eyes finalizer | Fresh AI pass | Reads the verified text as a first-time reader, applying only safe polish. Any final polish restarts the final checks; the same text must return unchanged before release. |
Studies find predictable wording and overused vocabulary in machine text, and authorship detectors can misclassify non-native English. Local tools use only Python's standard library.
Learning starts only when you hand over both versions: the original output and your edited version. Zero Slop watches nothing on its own: no file monitoring, no browser hooks, no reaching into where you publish.
Private
data stays under $ZERO_SLOP_HOME.
This is human-in-the-loop online learning. It never retrains Claude, GPT, or another model, and involves no neural training or RLHF. A profile can exempt existing watchlist words when selected by name; it does not learn cadence, tone, or a complete writing style.
SKILL.md has the workflow and references/eval.md the
80 checks. scripts/slopscore.py is the meter and fact gate,
with scripts/register.py running the reading pass.
bench/README.md documents every benchmark with its limits.
zero-slop.ai has the same reference as browsable pages, plus the benchmark in full.
We reran Zero Slop, avoid-ai-writing, no-ai-slop and humanizer on the same samples, each with GPT-5.4, high reasoning, batches of three, and its pinned instructions.
| Method | Mean writing score ↓ | Passed all Zero Slop checks | Important details kept | Average length change |
|---|---|---|---|---|
| Original drafts | 76.3 | 0/18 | — | — |
| Zero Slop | 12.8 | 18/18 | 18/18 | -8.9% |
| avoid-ai-writing | 23.3 | 15/18 | 18/18 | -14.6% |
| no-ai-slop | 28.4 | 12/18 | 17/18 | -13.7% |
| humanizer | 35.4 | 9/18 | 17/18 | -7.2% |
Cross-checks the tools didn't build: the AIStoryHub checker's clean rates, and a method-hidden quality ranking.
This is a small LLM-reviewed regression study. It measures neither field accuracy nor a
universal ranking. Drafts, mappings, verdicts, hashes and limits:
bench/incumbent-blind-replay/. On the 38-item
editorial panel (bench/README.md), v2.7.6 matched the prior 84.2% result
with every frozen document score unchanged, all 18 human controls clear and all 18 search
cases still caught: the release moves what the gate asks and leaves the meter
untouched. Median throughput was 3.51% lower across 12 runs, which is local timing
noise and no kind of speed claim.
On one Apple silicon Mac: 1,000 documents in 2.1956 seconds (455.5 per second), a 15,201-word document in 0.3225 seconds, the slowest stress case in 2.2577 seconds, an 8,000-word learning pass in 0.1811 seconds. Editing time is excluded; expect different numbers on different machines.
The pinned RAID+ sample yielded 7,627 usable generations:
| Model | Texts scored | Mean writing score ↓ | At or above 25 |
|---|---|---|---|
| DeepSeek V3 | 1,995 | 14.5 | 10.1% |
| Gemini 3.1 Pro | 1,998 | 17.0 | 18.2% |
| Gemma 3 27B | 1,634 | 21.6 | 30.4% |
| Llama 3.3 70B | 2,000 | 25.5 | 41.7% |
RAID+ labels capture which model produced a text, not how well it reads. In Beemo, raw responses averaged 30.2, expert edits 25.3, human answers 20.0. Neither dataset has quality labels.
Zero Slop enhances work done by no-ai-slop, humanizer, de-slop, stop-slop, unslop-text and avoid-ai-writing, by adding a slop score, source protection, separate editorial passes, private learning, portfolio analysis and release tests.
The chart records which features each project documents. It says nothing about writing quality and is not a claim about which tool writes better. Reproduce by using these tests:
python3 tests/test_all.py
python3 scripts/calibrate.py --selftest
python3 scripts/register.py --selftest
python3 bench/make_charts.py --checkMIT