Advanced Human Writing & AI Humanizer

Reusable multilingual writing SKILLS for natural prose, genre-aware style, and long-form continuity.

Advanced AI humanizer and de-AI writing toolkit for natural rewriting, AI text cleanup, fiction editing, novel continuation, chunked long-form audit, writing style unification, and character consistency review.

中文说明 | English | Español | Português (Brasil) | Français

Advanced Human Writing & AI Humanizer is an open-source, modular skill pack and lightweight prompt compiler for natural multilingual AI-assisted writing. The package, repository, and ClawHub slug remain human-writing-skills for compatibility.

This is not an empty prompt collection. The repository contains two deliberately different capability layers:

• Executable Python tools: humanwriting/ provides the installable human-writing-skills CLI for deterministic lint findings with evidence spans, text statistics, conservative fix previews, protected-content verification, prompt compilation, and staged audit-file generation.
• Model-executed editorial modules: skills/*.md contains genre and review instructions selected on demand by that compiler. These modules guide the writing model; they do not falsely present subjective literary judgment as a deterministic algorithm.

The test suite exercises both the executable layer and module-selection gates.

Agent Orchestration, MCP, And DeepSeek Harness Plugin

For book-length novels, report series, or research coverage that cannot be trusted to one chat window, install the dependency-free human-writing-mcp server. It makes the long-form task graph executable across Codex, Claude Code, OpenCode, DeepSeek Harness, Manus, and Hermes: agents claim bounded tasks, submit coverage receipts, and cannot unlock reconciliation until every required review is complete. The service stays inside a chosen project root and does not call a model or upload drafts.

human-writing-mcp --root C:\writing-project

The repository also ships a native DeepSeek Harness npm/Cordis bundle under plugins/deepseek-harness. It mounts the official DSH MCP client and starts the same verified local coordination service. See the agent orchestration guide and DeepSeek Harness plugin guide.

The MCP server also supports day-to-day single-document work: lint_text, get_style_statistics, verify_protected_content, compile_humanize_prompt, compile_audit_prompt, and compile_ledger_extraction. It advertises a small native prompt menu (humanize-quick, dialogue-audit, continuity-audit, serious-rewrite, and more) for hosts that implement MCP Prompts. These tools stay local and return evidence or compiled instructions; they never send a draft to a model themselves.

Ledger Auto-Extraction And Project Defaults

Long-form continuity should not require hand-maintaining every fact from scratch. extract-ledger compiles an evidence-first prompt for turning existing chapters into a candidate continuity ledger. Its output distinguishes observed facts, inferences, conflicts, and unknowns, and requires a quote or location for every proposed state, object, obligation, injury, resource change, or spatial relation. Review it before making it canonical.

human-writing-skills extract-ledger --draft chapters-01-10.md --context novel-ledger.md --output ledger-extraction-prompt.md

Use .humanwriting.json in a project root to persist only lightweight defaults: style, document type, a relative ledger path, and lint allow-list entries. Explicit CLI flags win, and the file cannot silently activate deep profiles or expensive reference/source passes. See the ledger extraction guide. Pass --no-project-config when a one-off command must ignore the nearest project file.

{
  "style": "fiction",
  "document_type": "fiction",
  "context": "novel-ledger.md",
  "allow": ["END001"]
}

Editor, CI, And Python Distribution

Text-facing commands accept --draft - for standard input. lint --format github emits GitHub Actions annotations, while list --kind rule prints the current rule catalog with severity, category, and repair direction.

git diff -- docs\ | human-writing-skills lint --draft - --style general --format github --source-name docs-change.md
human-writing-skills list --kind rule --format json

Each GitHub Release builds a wheel and source distribution, then attaches them as Release assets. PyPI publication uses GitHub Trusted Publishing only after the repository variable PYPI_PUBLISH_ENABLED=true and the PyPI trusted publisher have been configured; no PyPI token is stored in this repository.

It helps a writing agent move away from generic, template-shaped output and toward prose that has intention, texture, continuity, and genre discipline. The project is especially useful for long-form generation, where characters, settings, arguments, facts, and unresolved threads often drift after several passages.

The goal is not deception. The goal is better writing: clearer instructions, stronger revision habits, and reusable style constraints that make AI-assisted drafts feel edited by a human.

Long-Form Audit And Style Unification

The executable chunk-audit workflow splits a year-long novel, article series, or large report at natural boundaries. Each body span is audited once, with a small read-only lead-in and the same user-confirmed style baseline plus outline or project ledger. It writes independent chunk prompts, deterministic cross-chunk style diagnostics, and a reconciliation prompt for model- or prompt-version drift in narration, character dialogue, terminology, and section function.

For fiction, --outline or --context makes supported goals, knowledge, relationships, limits, abilities, and speaker voice canonical. Without it, character inferences remain provisional. News, academic, official, and report workflows instead align terminology, facts, attribution, claim scope, and section purpose without loading fiction rules.

human-writing-skills chunk-audit --draft full-novel.md --style fiction --outline novel-outline.md --output-dir novel-audit

Discovery terms: long-form audit, chunked manuscript audit, writing style unification, style consistency review, character consistency audit, cross-chapter continuity, novel audit, and report review. See the long-form consistency guide.

Earned Scene And Document Endings

AI-assisted drafts often reach a real stopping point and then append a scenic dissolve, shared silence, life lesson, future-facing reflection, or summary of what the scene already showed. The earned-ending-audit finds this reflective bookend / false closure pattern in Chinese and English by locating the last meaningful change and applying a deletion test. It does not ban sunsets, silence, reflection, or lyrical prose.

• Fiction and webnovels stop on an earned consequence, decision, discovery, changed object, live pressure, or image whose meaning changed inside the scene.
• Hard news ends on the last useful verified fact, response, constraint, or next step; feature kickers must add meaning instead of manufacturing uplift.
• Academic, technical, and official writing ends with supported findings, limits, implications, decisions, owners, or deadlines rather than a ceremonial conclusion.

human-writing-skills audit --draft chapter.md --document-type fiction --profile ending
human-writing-skills lint --draft chapter.md --style fiction

The full module loads only through the explicit ending profile, while END001 provides a lightweight deterministic preflight for narrative endings. Discovery terms: AI story ending, reflective ending, scene ending audit, chapter ending audit, formulaic conclusion, false closure, AI reflective bookend, and can't-help-but-reflect ending.

Repetition, Exposition, And Scene Economy

Some drafts avoid obvious stock phrases yet still feel generated because they repeat a line, image, action sequence, or narrator explanation with no changed consequence. The narrative-only repetition-exposition-audit separates intentional refrains and needed recap from exact echoes, repeated choreography, inventory-like viewpoint scans, and explanation that merely tells the reader what dialogue or action already showed.

# Isolated, token-bounded narrative pass
human-writing-skills audit --draft chapter.md --document-type fiction --profile repetition

# Long drafts: add it only when matching narrative cues appear
human-writing-skills pipeline --draft chapter.md --lint-style fiction --auto --output-dir chapter-audit

REP001 flags a non-trivial verbatim sentence echo; NAT005 and NAT006 are low-severity density prompts for repeated interpretive narration and action frames. They are editing evidence, not authorship claims, and can be allowlisted. Quick humanization and serious-document workflows do not load this module.

Why This Exists

AI writing often fails in predictable ways:

Built-In Style Skills

Deep Human-Trace Modules

These modules target deeper AI-writing artifacts, not only surface phrases.

Quick Start

git clone https://github.com/whh110112/human-writing-skills.git
cd human-writing-skills
python -m pip install .

human-writing-skills list --kind style
human-writing-skills list --kind module
human-writing-skills build --style fiction --context examples/story-ledger.md --task "Write the next scene."
human-writing-skills humanize --draft chapter.md --style fiction --mode quick
human-writing-skills chunk-audit --draft full-novel.md --style fiction --outline novel-outline.md --output-dir novel-audit
human-writing-skills lint --draft chapter.md --style fiction
human-writing-skills verify --source original.md --candidate revised.md

You can also run directly from the source checkout with python -m humanwriting.cli .... The build and humanize commands print instruction packs that can be pasted into Codex, ChatGPT, Claude, local LLM tools, or another writing agent.

Quick Humanize

humanize is the low-friction rewrite route. It treats --draft as the original, keeps the same language and genre by default, and preserves meaning before changing surface style.

# Minimum stack: surface patterns + fidelity + voice/ambiguity preservation
human-writing-skills humanize --draft chapter.md --style fiction

# Add structural editor passes only when the draft needs them
human-writing-skills humanize --draft article.md --style self-media --mode deep

# Examples remain opt-in and are never treated as factual or stylistic source material
human-writing-skills humanize --draft chapter.md --style fiction --with-examples

quick does not load cliche, formulaic-structure, paragraph-progress, or editor-loop modules. deep adds those high-cost passes. humanize-examples loads only with --with-examples; voice-ambiguity-preservation loads only for supplied-text humanization or an explicit preservation audit.

Multilingual Scope

The skill instructions have no Chinese-only gate: they can guide fiction and serious prose in English, Japanese, French, Spanish, Portuguese, Arabic, Latin, and other languages supported by the selected model. Deterministic lexical rules are naturally language-specific, while structural continuity and review remain language-agnostic. The narrative heading scanner recognizes time cards across the languages above, and stats profiles Han, kana, Arabic, and several Latin-script language families. Use genre context and human review for mixed-language or low-resource text.

Example Output Shape

# Core Directive
# Continuity Protocol
# Selected Skill: fiction
# Project Context
# Task
# Output Contract

This format keeps the model focused on the current task while still carrying the previous facts, style decisions, and unresolved threads.

Explicit Reference Style

Reference matching is opt-in. It activates only with --reference, --reference-style, or explicit task wording such as "match this voice." A continuity ledger by itself never activates it.

human-writing-skills build `
  --style fiction `
  --context examples/story-ledger.md `
  --reference examples/reference-style-source.zh-CN.md `
  --task "Continue the scene while matching the reference's restrained rhythm."

human-writing-skills audit `
  --draft my-chapter.md `
  --reference examples/reference-style-source.zh-CN.md `
  --profile style-match

The compiler extracts point of view, rhythm, register, imagery, description, dialogue cadence, emotion handling, and transitions. Plot facts still come from --context; names, events, and distinctive phrases must not be copied from the reference. See docs/reference-style.md.

Original-Text Fidelity

Use --original only when revising an existing text and meaning must remain stable. It activates a dedicated fidelity module for rewrite and review; ordinary drafting does not pay this token cost.

human-writing-skills build `
  --style self-media `
  --original original.md `
  --task "Rewrite for clarity without adding facts or strengthening claims."

human-writing-skills audit `
  --draft revised.md `
  --original original.md `
  --profile fidelity

--original is semantic authority, --reference is style evidence, and --source is factual evidence for serious documents. They are deliberately isolated so a style sample cannot rewrite facts and an original cannot silently become a style target. See docs/editing-tools.md.

Serious-Document Sources

--source is separate from --reference. It activates source-grounding only for academic, news, legal, or technical work and builds a claim-to-source evidence map. Fiction, webnovels, self-media, and casual answers do not auto-load it.

human-writing-skills audit `
  --draft paper.md `
  --document-type academic-paper `
  --source study-a.md `
  --source study-b.md `
  --profile sources

The audit separates source existence from claim support. Without external registry access, it marks citation metadata as unverified instead of inventing a verdict.

Long-Form Continuity

For longer works, this project recommends a small ledger instead of relying only on a large context window. Use context in this order: canonical ledger, latest confirmed state, recent chapters, relevant retrieved older spans, then explicitly uncertain inference. Retrieved text is recall evidence and cannot overwrite a later canonical state.

The ledger tracks:

• fixed facts: names, dates, locations, relationships, rules, timeline
• active threads: unresolved conflicts, clues, promises, open arguments
• relationship state: who knows, wants, hides, owes, refuses, or holds leverage
• relationship stance: public/private posture, current audience, mention policy, forbidden leaks, and exception motives
• voice anchors: point of view, diction, directness, disclosure habits, domain limits, audience shifts, taboo phrases
• language identity: shared scene language, demonstrated dialect/second-language exposure, address forms, particles, and switch gates
• capability state: permanent power/skill/authority plus temporary injury, equipment, resources, cooldowns, counters, costs, and transition gates
• dialogue contract: who speaks to whom, why now, desired listener action, protected information, and intended state change
• interaction debt: which consequential line or action still awaits uptake, refusal, interruption, consequence, or delayed payoff
• current state: where the previous passage ended and what must connect next
• beat bridge: previous residue, entry pressure, micro-turn, and exit hook
• change log: what became newly true in the latest output

See examples/story-ledger.md for a fiction example.

speech-register-continuity auto-loads only for fiction/webnovel dialogue when the task or ledger contains explicit language, regional, dialect, honorific, or register evidence. It can also be selected with audit --profile register; region or nationality never licenses an invented accent.

capability-state-audit loads during generation only when the current task names a capability constraint. Automatic pipeline review additionally requires context, so ordinary dialogue scenes do not pay its Token cost. Select it explicitly with audit --profile capability --context ledger.md when needed.

Chatbox

Yes, this project works in Chatbox because it outputs plain text prompt packs. For long writing sessions, use the continuity ledger as the source of truth and paste the compiled prompt pack into Chatbox's system prompt or first message.

• English guide: docs/chatbox.md
• Chinese guide: docs/chatbox.zh-CN.md
• Ledger template: examples/chatbox-ledger-template.md

Physical Continuity

For scenes where space matters, such as cars, elevators, hospital rooms, dining tables, and bedrooms, use --strict-continuity. It adds occupancy, spatial blocking, and appearance/prop generation guards. Use audit --profile physical for one evidence-first forensic pass on an existing draft; it owns capacity, blocking, appearance, props, barriers, reach, and body-state contradictions in one ledger.

python -m humanwriting.cli build `
  --style fiction `
  --strict-continuity `
  --review `
  --context examples/vehicle-scene-ledger.md `
  --task "Continue the car argument. Every seat change must have an on-page transition. Keep clothing and props consistent."

• Guide: docs/physical-continuity.md
• Vehicle ledger example: examples/vehicle-scene-ledger.md
• Capacity ledger template: examples/capacity-ledger-template.md
• Capacity conflict example: examples/capacity-conflict-draft.zh-CN.md
• Draft audit example: examples/problem-car-scene-draft.md

Relationship Stance Continuity

For scenes with rival factions, secret relationships, hierarchy, family politics, office politics, or sect leaders, use --deep-review or add relationship-stance-audit. It extracts each dialogue line as speaker -> listener/audience -> referenced party and checks whether praise, criticism, comparison, naming, secrecy, and rank fit the established relationship graph.

• Guide: docs/relationship-stance-continuity.md
• Ledger template: examples/relationship-stance-ledger.zh-CN.md

Character- and Situation-Fit Dialogue

Bidirectional interaction review addresses missing reactions and unfinished actions. It covers speech, wordless exchanges, and the viewpoint character's own responses. Track initiator, affected recipient, separate speech/action obligations, evidence of reception, and completed or pending state. A spoken answer may leave a simultaneous action unfinished; one person's movement does not establish that another followed. Refusal, unawareness, stillness, or delayed uptake can be valid. Clearly implied completion needs no added gesture or emotional commentary.

Fiction and webnovel base Skills retain a brief check; detailed review uses the existing on-demand voice profile. Automatic pipelines and deep chunk reviews also route directed interpersonal actions. Use --profile voice when automatic cues miss a language or phrasing. Reconciliation checks responses across chunk boundaries. These are model-executed contextual checks; routing tests and deterministic lint do not establish that a model will catch every omitted reaction.

dialogue-voice-audit and dialogue-performance-audit separate stable speaker baseline, situation-driven modulation, and the action each turn is trying to perform. Occupation, class, region, and trait labels supply possible knowledge, incentives, duties, and register pressure; they do not substitute for personality. An explicit speech or interpersonal-action task activates the module on demand. Review an existing scene with an independent voice pass:

human-writing-skills audit `
  --draft my-dialogue-scene.md `
  --context my-novel-ledger.md `
  --profile voice

The audit separates contradiction from motivated contrast and checks scene purpose, knowledge boundaries, practical constraints, response linkage, audience, and power. A consequential line or action does not require a mechanical spoken reply, but it must receive verbal, physical, silently legible, interrupted, or deliberately deferred uptake before the prose shifts away. A physical beat is retained only when it changes access, attention, leverage, permission, distance, or the next available action; the module does not prescribe touch, gestures, weather, clothing, or scenery after every line.

If the draft already exists, use audit:

python -m humanwriting.cli audit `
  --draft examples/problem-car-scene-draft.md `
  --context examples/vehicle-scene-ledger.md

Project Layout

humanwriting/        Python package and CLI
skills/              reusable writing SKILLS in Markdown
examples/            sample continuity ledgers and article briefs
tests/               standard-library unit tests

CLI Usage

Optional Narrative Modules

The narrative controls use progressive disclosure. Generation adds the dialogue modules only when a fiction or webnovel task explicitly asks for a speech-centered or character-interaction scene such as dialogue, negotiation, reunion, testing, reconciliation, confrontation, a meeting, interrogation, or argument. Narration-only and serious-document tasks do not trigger them. The voice, serial, world, process, momentum, salience, recurrence, repetition, texture, and sources and preservation audit profiles remain outside broad full review:

human-writing-skills build --style fiction --task "Write a negotiation in which both speakers want different outcomes."
human-writing-skills build --style webnovel --context ledger.md --module serial-reentry --task "Continue chapter 18."
human-writing-skills audit --draft chapters.md --profile momentum
human-writing-skills audit --draft chapter.md --profile texture
human-writing-skills audit --draft chapter.md --profile process
human-writing-skills audit --draft chapters.md --profile recurrence

The dialogue modules model baseline speech, practical incentives, knowledge limits, scene goals, response linkage, and purposeful performance beats without treating a job as a personality. dialogue-voice-audit owns response obligation and deferred interaction debt; dialogue-performance-audit only tests whether a selected physical beat earns its place. Use speech-register-continuity for evidence-backed language identity, particles, honorifics, and code-switching; use capability-state-audit for power and resource state. Use serial-reentry only with prior chapters or a ledger, momentum for a multi-chapter draft, and texture for narrative distance, cinematic opening stacks, imagery load, paragraph fragmentation, emotional over-explanation, and detail inventory. Use world only with explicit setting constraints, process for consequential domain work, salience for long drafts, recurrence for at least three chapters, repetition for long enough narrative drafts with matching repetition/exposition cues, and sources only with serious documents and factual source files.

During generation, world, process, and attention-budget modules activate only from explicit setting, consequential-process, expansion, long-form, or dilution signals; ordinary --deep-review does not load them. The repetition/exposition module is likewise audit-first: use --profile repetition or narrative ai-trace, and let pipeline --auto add its separate pass only when the draft supplies matching cues.

Audit Profiles

audit can load only the checks needed for the current pass:

Profiles can be combined, for example --profile relationship --profile ai-trace.

Ordinary generation loads only a lightweight sentence-completeness guard. Full omission, missing-object, stranded-connector, and reference checks load only in the proofread profile or pipeline proofreading stage, preserving the generation token budget.

Chunked Long-Form Audit

Use chunk-audit when a manuscript exceeds one reliable context window or was written across model, prompt, or time changes. It complements pipeline: chunking handles manuscript size and cross-block drift, while the pipeline separates different review responsibilities for one draft.

human-writing-skills chunk-audit `
  --draft full-novel.md `
  --style fiction `
  --outline novel-outline.md `
  --reference approved-sample.md `
  --output-dir novel-consistency-audit

Without an explicit reference, --baseline-chunk selects a candidate manuscript block; approve or correct it during baseline extraction. Reference prose supplies style evidence only. Fiction uses the outline or ledger for character canon and permits earned development; serious reports protect facts, numbers, terminology, attribution, and conclusion scope. Default body, context, and baseline budgets keep the workflow usable on smaller-context models.

Verified Agent Review For Long Documents

Add --agent-mode deep when coverage matters more than token cost. It writes an explicit task graph in agent-plan.json, requires a Coverage Receipt from every reviewer, and reserves report paths under reports/. After the baseline is approved, tasks that depend only on baseline may run in parallel in fresh model conversations or API calls.

human-writing-skills chunk-audit `
  --draft full-novel.md `
  --style fiction `
  --outline novel-outline.md `
  --agent-mode deep `
  --output-dir novel-agent-audit

human-writing-skills verify-chunk-audit `
  --package-dir novel-agent-audit

Do not run 9999-reconcile-prompt.md until verification reports complete coverage. Deep mode adds a paragraph-level prose pass for every block, an interaction pass where dialogue or directed actions occur, and an evidence pass only for serious documents with explicit --source files. Standard mode remains one complete audit per unique block. For an explicitly translated or localized long document, add --translationese; it never activates merely because the text uses another language.

• Guide: docs/long-form-consistency.md

Multi-Stage Pipeline

For high-precision review, generate independent single-purpose passes instead of asking one model to check everything at once:

human-writing-skills pipeline `
  --draft my-chapter.md `
  --context my-novel-ledger.md `
  --auto `
  --output-dir chapter-audit

Run every stage in a fresh model conversation or independent API request. Automatic mode keeps logic, AI-trace, and proofreading stages, then adds focused stages only when their cues and gates match. serial and capability require context; fidelity requires an original; salience requires a long narrative of at least 4,000 characters; recurrence requires at least three chapters; repetition requires a sufficiently long narrative with repeated explanation or choreography cues; and sources requires both a serious document and explicit factual sources. The higher-cost preservation comparison is explicit-only: use --stage preservation --original original.md. Add --with-stats only when distributional diagnostics are useful. The manifest explains every selection and skip.

• Guide: docs/audit-pipeline.md

Deterministic Safeguards

Use lint for evidence-located pattern checks, stats for optional distributional diagnostics, fix for conservative mechanical cleanup, and verify to catch protected facts changed during rewriting. Scores and statistics are editing heuristics, not authorship proof.

Protected-content instructions auto-load only for academic papers, formal documents, news reports, and strongly identified legal or technical documents. Fiction, webnovels, casual Q&A, playful text, and self-media do not auto-load them; use --protect-content or --protect-term to override this gate.

With --style fiction or --style webnovel, lint also flags unrequested narrative mini-headings and multilingual standalone time cards. It preserves work/chapter titles and does not apply the rule to news or academic section headings. The repair restores a prose transition; it does not merely delete the label and join two disconnected blocks.

human-writing-skills lint --draft my-chapter.md --style fiction
human-writing-skills stats --draft my-chapter.md --style fiction
human-writing-skills fix --draft my-chapter.md --preview
human-writing-skills verify --source original.md --candidate revised.md --protect-term "Project Atlas"

• Pattern lint: docs/pattern-linter.md
• Fidelity, statistics, and conservative fixes: docs/editing-tools.md
• Protected content: docs/protected-content.md

Number Sense

Use this to catch false precision such as unnecessary exact centimeters, seconds, or micro-counts in emotional and bodily action, while preserving necessary numbers in medicine, forensics, engineering, architecture, news, and technical writing.

python -m humanwriting.cli audit `
  --draft examples/false-precision-draft.zh-CN.md `
  --profile numbers

• Guide: docs/number-sense.md
• Example: examples/false-precision-draft.zh-CN.md

Common Writing Problems

The project converts recurring long-form writing problems into executable checks: stock phrasing, plastic prose, triplet structures, over-smooth transitions, static paragraphs, hollow emotion, cultural vacuum, and long-form drift.

• Rule map: docs/forum-complaint-research.md

List styles:

python -m humanwriting.cli list

Build a prompt pack:

python -m humanwriting.cli build `
  --style webnovel `
  --module narrative-bridges `
  --module relationship-state `
  --module natural-measurement `
  --module embodied-emotion `
  --module vocal-rhythm `
  --strict-continuity `
  --review `
  --context examples/story-ledger.md `
  --task "Continue chapter 3. Keep the confrontation unresolved but reveal one new clue."

The compact --review flag adds only:

• editor-loop: draft, diagnose, locally rewrite, then finalize
• ai-trace-rubric: score cognitive smoothness, generic diction, emotional flatness, rhythm monotony, context drift, weak beat bridges, relationship resets, false precision, cultural vacuum, over-clean prose, and closure addiction

The --deep-review flag adds the compact review plus:

• relationship-stance-audit: check speaker, listener, referenced party, secrecy, stance, rank, and audience permissions
• cliche-phrase-audit: check stock phrases, generic body cues, empty emotion labels, and dead transitions
• formulaic-structure-audit: check triplets, bidirectional contrasts, chained comparisons, and paragraphs that close too neatly
• surface-pattern-audit: check recurring significance, attribution, range, lexical, formatting, and mini-heading patterns in genre context
• prose-progress-audit: check whether each paragraph advances facts, relationships, evidence, action, or pressure
• narrative-naturalness-audit: in deep or explicit AI-trace review, check recurring scene-entry/closure recipes across six or more beats; local phrase, structure, and uptake findings stay with their owning modules
• natural-measurement: check false precision in fiction, webnovels, and self-media

The --strict-continuity flag adds:

• spatial-blocking: position and movement checks
• occupancy-capacity: physical resource mode, capacity, occupancy, and transformation checks
• appearance-prop-continuity: clothing, shoes, props, and body-state checks

Use audit --profile physical for the final physical-state contradiction pass. The optional physical-continuity-audit is a light manual checklist and cannot be combined with this forensic profile.

Run tests:

python -m unittest discover -s tests -v

Writing Philosophy

Good AI-assisted prose should be:

• situated: it knows who is speaking, what changed, and why this passage exists
• specific: it uses details that belong to this topic, not any topic
• continuous: it respects previous facts, costs, injuries, claims, and promises
• shaped: it understands the genre before choosing structure and diction
• revised: it removes filler, canned transitions, and decorative certainty

Editorial Guardrails

This project avoids claiming that any tool can perfectly hide authorship or beat detectors. It focuses on craft: voice, context, genre, revision, and continuity.

When studying published work, use short analysis, public-domain sources, licensed material, or your own examples. Do not copy protected passages into skills.

Contributing

Contributions are welcome. Useful additions include:

• new Markdown skills
• Chinese and multilingual style packs
• model-specific adapters
• stronger continuity ledger examples
• tests for prompt compilation and context preservation

Please keep each skill practical. A good rule should tell the model what to do, what to avoid, and how to check the result.

License

MIT. See LICENSE.