manavmishra/zeroslop/zero-slop

Zero Slop

A linter for the AI accent. The things that make prose read as machine-written are measurable, so measure them, fix them, and show the numbers.

Zero Slop is a skill, not an AI model. The user's existing AI assistant, powered by Claude, GPT, or another compatible model, reads the draft, understands its context, and performs the editorial work. The bundled local tools handle repeatable checks. They do not replace the assistant, and no separate Zero Slop model or service receives the draft.

The separately invoked npm zero-slop deslop command and hosted MCP/REST endpoints send a draft to Zero Slop's remote service. They are opt-in alternatives, not local checks in this workflow. Do not invoke them as part of an offline skill run without the user's request. The npm score command continues to run locally.

The science in one paragraph: detectors (and readers) key on the post-training register — text that sits at the most-probable phrasing, with uniform sentence rhythm, a few hundred over-represented style words, tidy template structure, and relentless even polish. These signals live in the surface realization of the text and can usually be revised without changing the meaning; the fidelity and semantic checks below enforce that boundary. references/evidence.md has the citations, and the ladder below orders the signals by measured strength.

Hard rules (non-negotiable)

For an explicit character-cleanup request, use the bundled offline text-hygiene helper at scripts/text_hygiene.py when available. It inspects formatting characters and removes only a small reviewed set of embedded artifacts in 16 common ASCII prose words. Only sentence-shaped lines with conservative prose openers are eligible. Recognized code, command syntax, URLs, formulas, quotations and multilingual formatting are excluded; these guards are not a complete code parser. Preserve uncertain text and use inspection when its purpose is unclear. This is a separate local operation, not a replacement for contextual editing. Its change record can reverse the exact cleanup. A scriptless assistant must not claim byte-level cleanup it did not perform. Character cleanup does not verify removal of statistical watermarks from ChatGPT, Claude, Gemini or any other model. Preserve required disclosures and attribution. In a host that routes local checks through the bundled MCP connector, use its clean_text tool with the supplied text and optional inspect: true instead.

1. Fidelity. Meaning, claims, and facts survive exactly. Never invent a

number, name, anecdote, or experience — and experiential/interior claims count ("by test day it felt familiar", "I was terrified"): if the author didn't say it, it's fabrication, even when it would make the piece land better. Preserve the underlying emotion or position when the author states one. A generic promotional intensifier may be reduced only when it is a named delivery defect and the underlying claim remains ("incredibly excited" may become "excited"). A hedge, scope limit, caveat, factual degree, or change of speaker is not promotional padding and must keep its strength. Specificity without source grounding is fabrication — worse than the slop it replaces.

1. Flag hollow spans, don't fill them. Prose that makes no claim cannot be

rescued by rewording. Flag it and ask for the missing substance.

1. No over-correction. Trading AI-slop for edgy-slop (forced hot takes,

fake first person, performed candor, staccato drama) is failure. Read references/overcorrection.md before heavy rewrites.

1. Idempotence in editing. Text that already reads human returns unchanged. "Reads

human" is a two-channel finding, never a score: a draft returns unchanged only after the scorer is clean and the step 2 performed-register pass has run on it and reported zero findings. The best edit is often small. A reader-only review leaves every draft unchanged without certifying that it is clean. In scriptless mode, leave a draft unchanged when direct review finds no grounded edit, but do not certify it as scored or fully clear.

1. Honest use. This skill improves writing quality and voice. Refuse

requests to defeat AI-disclosure requirements (schools, journals, employers that require disclosure) or to impersonate a named individual.

1. Speak to the writer, not the scoring code. User-facing reports must use

ordinary editorial language. Say "writing score," "flagged phrases," "sentence variety," "readability," "facts preserved," and "final checks." Never expose internal labels such as "surface score," "weighted tells," "tell density," "burstiness," "followability," "fidelity gate," "scorecard," "heatmap," "artifact," "candidate," or "overlay." Keep internal field names only in machine-readable JSON or maintainer notes.

1. Tell the writer who did what. Zero Slop is the skill and set of local

tools; the AI assistant running it performs the contextual reading and editing. In every standalone report, name the current assistant or model only when the environment makes that identity certain. Say "Claude," "GPT," or the accurate product name when known; otherwise say "your AI assistant." Never guess. Do not imply that a separate Zero Slop model or service received, read, or rewrote the draft.

1. A clean score is not a completed review. The scorer sees only the

lexically anchored subset of the tells. Every rewrite or slop-inspection draft gets the performed-register pass in step 2 regardless of what the meter says, and that pass reports its counts — including zero — in the step 9 summary. A score in the "clear" band is a reason to look harder at register, not permission to stop: the tell families the meter cannot see are exactly the ones still standing when it comes back empty. A standalone audience reader review is a different diagnostic: it neither runs nor certifies this pass.

Eight roles, one pipeline

Run the rewrite workflow as eight ordered responsibilities. They are editorial jobs, not eight models or services. In an installed assistant, use role-isolated passes when the harness can do that without extra network calls. When a service has a one-request budget, combine the AI responsibilities into one structured editorial response and run the local checks before and after it. Name that consolidation honestly; one model response is not independent review.

Preserve source material rather than sentence count. Delete before rewriting: keep a sentence when it adds a fact, position, reason, example, instruction, or necessary connection. Delete empty sentences instead of replacing their flagged words with milder synonyms. Do not add a takeaway or benefit summary that repeats a nearby point. For example, delete “Efficiency is paramount” instead of changing it to “Efficiency is crucial.” After a measured improvement in setup time, do not append that the change “makes it easier to get started.” Preserve substantive opinions, emotion, and useful transitions even when they contain flagged wording. Leave clear factual statements and qualifications unchanged where possible. Missing knowledge stays missing: “not measured beyond the first month” does not establish that the first month was measured, and a missing feature in a new product does not establish that the old product had it.

Delete attention-directing frames when the fact carries its own weight: “The number I keep coming back to is 119,000” becomes the sentence that states what 119,000 measures. Then apply the removal test to the next sentence too. If “The price cut paid for the extra thinking” only restates that lower token prices offset higher token use, delete it rather than preserving the recap as voice or rewriting its metaphor.

Keep local and AI responsibilities distinct:

1. Scorer — local tools. Point to exact phrases and problems with rhythm,

readability, formatting, and register; explain the writing score.

1. Interpreter — the AI assistant. Read the full draft for claims, support,

audience, genre, structure, and voice before changing it.

1. Rewriter — the AI assistant. Remove stock wording, then rebuild order, rhythm,

and tone while preserving the author's material.

1. Fact gate — local tools. Reject rewrites that add or drop names, numbers,

quotations, or links; among the rest, select the version that best clears the measured checks. This local check cannot certify reframed claims or invented interior meaning; the verifier handles those with contextual comparison.

1. Copy desk — the AI assistant. Correct grammar, spelling, punctuation, usage,

diction, and consistency in the selected text.

1. Read-aloud editor — the AI assistant. Read the complete copy-edited text aloud

and directly fix stumbles, repetition, weak transitions, and awkward flow.

1. Verifier — local tools plus the AI assistant. Check the exact final text

against the source for the writing score, facts, meaning, qualifiers, voice, format, and structure. A warning prevents an unqualified approval; it never erases a source-safe edit or starts an open-ended loop. Apply at most one targeted repair, then rerun the local checks on the exact changed text.

1. Fresh-eyes finalizer — the AI assistant. Read the verified text as a first-time

reader and apply only safe final polish. If it changes the text, rerun the local score and fact checks once. Deliver the safest edit with a plain warning if a remaining concern would require another model request or a guess.

This is an engineering separation of responsibilities, not a claim that research has proved eight to be the uniquely correct number. Studies support several different signal families and several different editorial failure classes; no single score or prompt can cover them all. The local roles provide repeatable measurements. The AI roles supply contextual judgment and editing. A generating role does not certify its own factual safety. Role 7 supplies the local release checks; role 8 confirms that the result reads cleanly to someone seeing it for the first time. In a one-request service, the model's self-check is editorial guidance, not independent verification.

Detailed workflow

Before starting the eight-role pipeline, read and follow the complete detailed workflow in references/detailed-workflow.md. Keep every rule in this entry and the existing references.

Detailed workflow

References