writing-tools

Agent skill that removes signs of AI-generated writing from text

「說人話」：繁體中文的去 AI 味改寫 skill。抓 38 種 AI 寫作痕跡，順手校正中國用語與半形標點，給 Claude Code / Codex / Cursor 用。

Two-pass pipeline for removing AI writing tells from outward-facing text: a surface pass plus a structural pass grounded in the StoryScope study. Packaged as Claude Code Skills. Free community: skool.com/jens-ai-community-1306

A local detector for AI-writing patterns. Scores every prose file your agent saves. Python standard library only, no network, no model.

Skill для AI-агентов (Claude Code, Codex, OpenClaw, Hermes): убирает 37 признаков AI-генерации из русского текста и проверяет, писала ли его нейросеть - канцелярит, штампы ChatGPT, артефакты копипаста | Russian AI-text humanizer & detector skill for coding agents

Open-source agent skills for turning raw book ideas into full manuscripts with blind literary evaluation gates.

Make AI output sound human. Strips AI-isms (sycophancy, stock vocab, hedging stacks, em-dash pileups), preserves code/URLs/headings. Plugin for Claude Code, Cursor, Windsurf, Codex, Cline, Copilot, Gemini.

ScriptReader allows you to perform Optical Character Recognition (OCR) on your handwritten notes!

German AI Text Humanizer for Claude Code & Codex. Audits 72 German AI-writing patterns using deterministic linters and evidence-safe rewrites. No fact-bending, no bypassing tricks.

AI长篇小说工程化写作流水线 — SQLite记忆、21道Guard门禁、Agent陪审团、防幻觉检查、多小说独立数据库、人工味质量层

Turn your own spoken words into a finished article. AI does the research, structure and checking. You supply the sentences, by talking.

Suite per la lingua italiana e sistema avanzato anti AI, per Claude e non solo: scrittura, revisione, voce d'autore.

清理简体中文模型化口癖并保护事实、语体与人物声口的 Agent Skill

43 Claude Code skills for making content that doesn't read like a machine made it — prose editing with an offline linter, prompt engineering for 40+ image/video/music models with optional one-command execution, and orchestrators from research to a published carousel, reel or proposal. Russian-first, English throughout.

AI-detector auditing toolkit: measures how often a detector flags genuine human writing, how stable its verdict is across seeds, and whether that verdict survives meaning-preserving edits. Detector-in-the-loop measurement harness. Claude Code skill + Python CLI. MIT.

稿匣：面向长篇小说创作的本地优先桌面工作台

Open-source screenwriting knowledge infrastructure for writers and agents: route, generate, review, and orchestrate narrative, branded, and interactive scripts.

Strip AI writing patterns from any text. Claude Code skill with 507-entry banned word list, structural pattern detection, and 12-check validation.

PlotRail: canon-aware AI novel writing skill for long-form fiction

Agent skill that removes documented AI-writing patterns — two modes, register awareness, voice calibration, and a deterministic linter. Works in Claude Code, Cursor, Copilot, Codex, or any harness that reads SKILL.md