zero-slop

Files (102)

• SKILL.md
• README.md · data/corpus/community-register/
• communicative-drift.txt · data/corpus/community-register/judgment/
• reflexive-agreement.txt · data/corpus/community-register/judgment/
• rhetorical-scale-mismatch.txt · data/corpus/community-register/judgment/
• adjective-inflation.md · data/corpus/must-flag/
• caveat-template.md · data/corpus/must-flag/
• classifier-scaffolding.md · data/corpus/must-flag/
• dangling-thin.md · data/corpus/must-flag/
• label-period-list.md · data/corpus/must-flag/
• manifest.json · data/corpus/must-flag/
• mic-drop.md · data/corpus/must-flag/
• monument-negation.md · data/corpus/must-flag/
• opus-effort-recap.md · data/corpus/must-flag/
• plural-noun-fragment.md · data/corpus/must-flag/
• referent-cycling.md · data/corpus/must-flag/
• unnamed-validator.md · data/corpus/must-flag/
• README.md · data/corpus/must-not-flag-shape/
• aphorism-list.txt · data/corpus/must-not-flag-shape/
• changelog.txt · data/corpus/must-not-flag-shape/
• dialogue.txt · data/corpus/must-not-flag-shape/
• lyrics.txt · data/corpus/must-not-flag-shape/
• poem.txt · data/corpus/must-not-flag-shape/
• sms-transcript.txt · data/corpus/must-not-flag-shape/
• README.md · data/corpus/must-not-flag/
• esl-engineer-email.txt · data/corpus/must-not-flag/
• exec-memo.txt · data/corpus/must-not-flag/
• federalist.txt · data/corpus/must-not-flag/
• gettysburg.txt · data/corpus/must-not-flag/
• grant-abstract.txt · data/corpus/must-not-flag/
• ml-methods.txt · data/corpus/must-not-flag/
• personal-essay.txt · data/corpus/must-not-flag/
• press-release.txt · data/corpus/must-not-flag/
• recipe.txt · data/corpus/must-not-flag/
• sre-runbook.txt · data/corpus/must-not-flag/
• technical-postmortem.txt · data/corpus/must-not-flag/
• terse-engineer-note.txt · data/corpus/must-not-flag/
• README.md · data/corpus/performed-register/
• bare-subject-swap.txt · data/corpus/performed-register/judgment/
• detection-fragile.txt · data/corpus/performed-register/judgment/
• draft-cheap-signal.txt · data/corpus/performed-register/judgment/
• ear-chiasmus.txt · data/corpus/performed-register/judgment/
• fight-against-tagline.txt · data/corpus/performed-register/judgment/
• fine-beat.txt · data/corpus/performed-register/judgment/
• glow-finishing.txt · data/corpus/performed-register/judgment/
• jargon-compression.txt · data/corpus/performed-register/judgment/
• not-perfect-honest.txt · data/corpus/performed-register/judgment/
• punctuation-convict.txt · data/corpus/performed-register/judgment/
• recipe-ingredients.txt · data/corpus/performed-register/judgment/
• replay-lands.txt · data/corpus/performed-register/judgment/
• rhymes-with.txt · data/corpus/performed-register/judgment/
• rhythm-prints.txt · data/corpus/performed-register/judgment/
• same-leak.txt · data/corpus/performed-register/judgment/
• tools-work.txt · data/corpus/performed-register/judgment/
• tuning-gradients.txt · data/corpus/performed-register/judgment/
• whole-product.txt · data/corpus/performed-register/judgment/
• words-cheap.txt · data/corpus/performed-register/judgment/
• argue-with-artifact.txt · data/corpus/performed-register/mechanical/
• bill-lands.txt · data/corpus/performed-register/mechanical/
• billed-to-reader.txt · data/corpus/performed-register/mechanical/
• …and 42 more

SKILL.md (first lines)

# 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.
2. **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.
3. **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.
4. **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.
5. **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.
6. **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.
7. **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.
8. **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.

From manavmishra/ZeroSlop, MIT.

More from manavmishra/ZeroSlop