仓库/Skill 库

XCutors——面向 Windows 桌面的综合性 Roblox 执行器与脚本加载器合集XCutors – A comprehensive Roblox executor and script loader collection for Windows desktops.

🎓 降低中文学术写作 AIGC 检测率的 Claude Code Skill | Reduce AIGC detection rate for Chinese academic writing

免费 AI 人性化工具：在线将 AI 文本改写为人类风格Free AI Humanizer: Humanize AI Text Online

面向对外文本的 AI 写作痕迹两轮清除流水线：表层处理 + 基于 StoryScope 研究的结构性处理。打包为 Claude Code Skills。免费社区：skool.com/jens-ai-community-1306Two-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

Codex 去 AI 味 Skill：紧凑型中文 AI 写作人性化工具，用于清理 AI 味、模板化句式壳与虚假互动式结尾去AI味 skill for Codex: a compact Chinese AI writing humanizer for AI味清理, template sentence shells, and fake engagement endings.

Claude Skill，用于消除俄语文本中的 54 种神经网络痕迹：官腔、生硬直译、ChatGPT 与 Claude 指纹。针对 GPTZero、DivEye、RuBERT 的检测指标，抬高 perplexity 与 burstiness。包含 20 项硬性禁令、四轮审计、作者语气校准，以及带前后指标的 eval 评测框架Скилл для Claude. Убирает 54 признака нейросети в русском тексте: канцелярит, кальки, фингерпринты ChatGPT и Claude. Метит в то, что меряют GPTZero, DivEye, RuBERT: поднимает perplexity и burstiness. 20 жёстких банов, quad-pass аудит, калибровка под голос автора, eval-харнес с метриками до/после.

Humanizer: AI writing trace removal tool（AI 写作去痕工具）

还原你已拥有工作中被改写的原始标题。剥离 Anthropic 分配给你的 Outputs 中附加的供应商标识。Restore clean title in work you already own. Strip vendor marks from Outputs Anthropic assigned to you.

本综述目标有二：(i) 综述对抗机器学习（AML）在推荐系统（RS）安全上的最新进展，即攻击与防御推荐模型；(ii) 展示 AML 在生成对抗网络（GAN）生成应用中的成功应用，得益于其学习（高维）数据分布的能力。本文对发表于主流 RS 与 ML 期刊会议的 74 篇文献进行了详尽综述，可作为 RS 社区在推荐系统安全及利用 GAN 提升生成模型质量方面的参考The goal of this survey is two-fold: (i) to present recent advances on adversarial machine learning (AML) for the security of RS (i.e., attacking and defense recommendation models), (ii) to show another successful application of AML in generative adversarial networks (GANs) for generative applications, thanks to their ability for learning (high-dimensional) data distributions. In this survey, we provide an exhaustive literature review of 74 articles published in major RS and ML journals and conferences. This review serves as a reference for the RS community, working on the security of RS or on generative models using GANs to improve their quality.

适用于 Claude Code 的 Skill，去除学术医学论文中的 AI 生成痕迹，使文本更自然、更具专业写作风格A Claude Code skill that removes signs of AI-generated writing from academic medical papers, making them sound more natural and professionally written.

AI 写作模式检测与改写工具。覆盖 53 种模式、5 种语气风格，提供 0–100 AI 痕迹评分。纯 Markdown 实现，零依赖AI writing pattern detector and rewriter. 53 patterns, 5 voices, 0-100 AI-tell score. Pure Markdown, zero dependencies.

GoLiveBypass — Equicord/Vencord 插件，通过在非巴西代理（Tor 或经过测试的免费代理）后启动会话来恢复巴西 Discord 用户的 Go Live 与摄像头功能。隐私与反审查工具。GoLiveBypass — Equicord/Vencord plugin that restores Go Live & camera for Brazilian Discord users by booting the session behind a non-BR proxy (Tor or tested free proxy). Privacy and anti-censorship tool.

降AIGC率，降低知网、维普、格子达平台的AIGC检测率，降知网AI，降维普AI，降格子达AI。

免费 Warhounds Trainer，支持大量 cfg 文件。自动更新，无需密钥系统。2026 年可用。Free Warhounds Trainer with support for many cfg files. Auto-updates, no key system. Works in 2026.

XCutors – 一套完整的 Windows 桌面工具集合，配合我们的通用加载器运行自定义 Roblox 脚本。XCutors – A complete Windows desktop collection for running custom Roblox scripts with our universal loader.

Tonkeeper Fake Balance —— TON 钱包余额伪造工具，支持 Tonkeeper 移动端与桌面端的实时浮层覆盖、自定义 TON 与 Jetton 余额注入、交易记录伪造以及截图安全的持久化显示。Tonkeeper Fake Balance — TON wallet balance spoofing tool with real-time overlay for Tonkeeper mobile & desktop, custom TON & Jetton balance injection, transaction history forging, and screenshot-safe persistent display

那条 API 背后究竟是谁？在浏览器中对任何 OpenAI 兼容端点进行指纹识别：9 项基础设施探针、并列对比、社区可扩展。Who is really behind that API? Fingerprint any OpenAI-compatible endpoint in the browser: 9 infrastructure probes, side-by-side comparison, community-extensible.

Electrum Fake —— 针对 Electrum 桌面客户端的比特币钱包余额伪造工具，具备实时叠加层、自定义 BTC 余额注入、交易历史伪造以及截图安全的持久化显示渲染。Electrum Fake — Bitcoin wallet balance spoofing tool with real-time overlay for Electrum desktop client, custom BTC balance injection, transaction history forging, and screenshot-safe persistent display rendering

面向 coding agent 的本地护栏机制：策略、审批、86 个安全策略包、操作系统级沙箱、审计追踪，无需 Docker。Local guardrails for coding agents. Policy, approvals, 86 safety packs, OS sandbox, audit trail — no Docker.

ThumbGate 预动作检查通过排序后的教训和反复失败进行自我改进，硬性阻断检测到的密钥泄露，并在严格模式下阻断匹配项。ThumbGate Pre-Action Checks self-improve from ranked lessons and repeated failures, hard-block detected secret leaks, and block matches in strict mode.

面向行情录制、交易安全与可复现研究的工程工具包。多交易所 kill-switch、带钱包标签的 Hyperliquid 微结构录制器、资金费率 carry 研究栈。Engineering toolkit for market-data recording, execution safety and reproducible research. Multi-exchange kill-switch, wallet-tagged Hyperliquid microstructure recorder, funding-carry research stack.

Spring AI 的隐私护栏：跨模型/工具调用的请求作用域 PII 令牌化与最小特权披露，基于 Presidio 与 JVM 本地 OpenNLP。Privacy guardrails for Spring AI: request-scoped PII tokenization and least-privilege disclosure across model/tool calls, with Presidio and JVM-local OpenNLP.

Claude Code 学术研究防幻觉插件。严格 FSM + 10 源 PDF 级联 + 首页防同名歧义 + 19 条不变量 + 每条引用审计。与 Vault 解耦（Obsidian/扁平目录/Zotero）。MIT 许可。Anti-hallucination plugin for academic research in Claude Code. Strict FSM + 10-source PDF cascade + page 1 anti-homonymy + 19 invariants + per-citation audit. Vault-agnostic (Obsidian/flat/Zotero). MIT.

Local-first、确定性的验证层，用于 AI 声明、记忆写入和风险操作。Local-first, deterministic verification layer for AI claims, memory writes, and risky actions.

Spec Seatbelt 让 AI 编程 Agent 保持诚实：先写计划、逐步证明、以全新视角验证；一次加载一个阶段（token 用量减少约 70%）；持久化的 .specs/ 记忆、循环计划波次与任务图，支持安全的并行工作。支持 Cursor 与 ClaudeSpec Seatbelt keeps AI coding agents honest: write the plan first, prove each step, verify with fresh eyes. Load one phase at a time (~70% fewer tokens). Persistent .specs/ memory, loop-plan waves, and task graphs for safe parallel work. Cursor & Claude.

实验性 Python 库：基于 dataframe 导航至研究问题，并内置统计与因果安全闸门Experimental Python library for dataframe-to-research-question navigation with statistical and causal safety gates.

智利国家机构网络安全合规扫描器，对标 21.663 号法令及 ANCI 通用指令。结合主动网络扫描与声明式问卷，生成 PDF 差距报告以及面向 CSIRT Chile 的 JSON 报告。Escáner de cumplimiento de ciberseguridad para organismos del Estado chileno, alineado a Ley 21.663; y las Instrucciones Generales de la ANCI. Combina escaneo activo de red con un cuestionario declarativo para producir un informe de brechas en PDF y un reporte JSON listo para CSIRT Chile.

围绕 LLM 人类价值观与多元对齐的精选论文、基准、数据集与工具合集。A curated collection of papers, benchmarks, datasets, and tools on human values in LLMs and pluralistic alignment.

Spectre AI 2026：新一代 OSINT 引擎与自主图谱消歧工具包。Spectre AI 2026: Next-Gen OSINT Engine & Autonomous Graph Disambiguation Toolkit

大语言模型情境感知相关论文精选目录。Curated bibliography of papers on situational awareness in large language models

EoG 应用迁移与功能实现的代码仓库。Code for EoG App Migration and Functionality

硕士论文研究：使用 Terraform IaC、Atomic Red Team MITRE ATT&CK 模拟与 Python 统计分析，在 Microsoft Azure 中实证评估零信任架构（ZTA）与传统边界安全。Sheffield Hallam University 2026。MSc dissertation research: Empirical evaluation of Zero Trust Architecture (ZTA) vs conventional perimeter security in Microsoft Azure using Terraform IaC, Atomic Red Team MITRE ATT&CK simulations, and Python statistical analysis. Sheffield Hallam University 2026.

学习驱动运动预测与规划中风险校准及运行时保障系统综述的可复现材料。Reproducibility materials for a systematic review of risk calibration and runtime assurance in learning-enabled motion prediction and planning.

个人简介：可信 AI、可复现研究、开发者工具。Profile overview: trustworthy AI, reproducible research, and developer tools.

🔐 使用 KeyVault Pro 安全管理 API key，具备军事级加密、智能自动填充与面向开发者的无缝 AI 集成。🔐 Manage API keys securely with KeyVault Pro, featuring military-grade encryption, intelligent auto-fill, and seamless AI integration for developers.