0xwilliamortiz
精选
openclaude-improved
OpenClaude is an open-source CLI coding agent that runs on any platform and supports a wide range of LLM providers, offering the same tools and workflows as Claude Code.
AI 仓库情报摘要
FR-AI / ANALYSIS为什么值得关注
它关注被忽视的结构性 AI 指纹，有同行评审研究支撑（基于话语特征检测 F1 达 93.2%），并提供确定性扫描器和免费社区支持。
适合谁使用
- Claude Code 用户，希望让 AI 生成文本更自然
- 内容创作者、营销人员，需要可读性强的文案
- 小说或非虚构长文的作者与编辑
- AI 检测与人性化技术的研究者
典型使用场景
- 对 AI 生成的博客、文章或营销文案依次运行第一阶段和第二阶段以人性化
- 用确定性扫描器快速标记草稿中词汇层或结构层的 AI 特征
- 将技能集成到 Claude Code 工作流中迭代改写
- 通过提供的参考文档（copy-tells、StoryScope 发现、体裁校准）学习结构性 AI 特征
项目优势
- 两阶段方法（词汇 + 结构）针对最持久的 AI 指纹，有 StoryScope 研究支持
- 确定性扫描器（copy_scan.py、structural_scan.py），可接入 hook 并输出机器可读格式
- MIT 开源，附有明确归属声明和免费社区用于讨论与支持
- 提供详细参考（词汇特征、StoryScope 发现、体裁校准），辅助知情决策
使用前须知
- 核心研究基于约 5000 词的虚构文本，应用于短非虚构作品尚属推论，未直接验证
- 扫描器只能捕获约一半的 AI 特征；韵律、模式化结构及空洞填充仍需人工判断
- 审计 3（'展示而非告知'已成为机器签名）与经典写作建议冲突，需谨慎使用
README 快速开始
humanizer-stack
A two-pass pipeline for removing the signs of AI writing from outward-facing text, packaged as Claude Code Skills.
Most humanizers only fix words. That is the easy half, and it is the half that is decaying fastest. This repo pairs a surface pass with a structural pass, because the research says structure is where the durable fingerprint lives.
Free community. I build tools like this in the open inside the Jens AI Community, a free Skool group for putting AI to work in your business. If this repo is useful to you, come join us: https://www.skool.com/jens-ai-community-1306
Why two passes
The StoryScope study (Russell et al., 2026) classified 61,608 stories from humans and five LLMs using only discourse-level features, with every style feature withheld. It detected AI text at 93.2% F1.
Then the authors ran AI text through LAMP, a professional span-level rewriting system that strips cliche, purple prose, and redundant exposition. Functionally, a very good surface humanizer.
Detection dropped 1.6 points.
Meanwhile the surface layer is eroding on its own. GPT 5.4 already cut its em-dash usage sharply, and fine-tuning drops stylistic detection from 97% to 3%. Word-level tells are a moving target. Structural tells require structural rewrites.
So: pass 1 fixes the words. Pass 2 fixes the shape. Run them in that order.
What is in here
skills/
humanizer/ Pass 1: words and phrasing
SKILL.md
references/copy-tells.md Copy-specific tells (em dash, hype vocab, antithesis)
structural-humanizer/ Pass 2: discourse structure
SKILL.md
references/
storyscope-findings.md The study distilled: 30 core features with rates
genre-calibration.md Which audits apply per genre
scripts/structural_scan.py Deterministic scanner for grep-able structural tells
scripts/
copy_scan.py Deterministic scanner for mechanical copy tells
docs/
PIPELINE.md How the passes chain, and what each one owns
Pass 1: humanizer
Vocabulary, punctuation, and phrasing. Inflated symbolism, promotional language, superficial "-ing" analyses, vague attributions, em dash overuse, rule of three, AI
项目描述
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
相关仓库与替代方案
根据分类、Topic 和编程语言匹配的相似项目。
0xwilliamortiz
精选
ponytail-improved
Ponytail is a plugin for AI coding agents that enforces a disciplined ladder of reuse before writing code, reducing code volume by roughly 54% while preserving safety.
S40911120
精选
recensa
Recensa is a self-hosted web viewer that indexes Claude Code session transcripts into a local SQLite database, enabling full-text search, replay, and audit of all past agent conversations without uploading data anywhere.