待核验
接入
skills
Public repository for Agent Skills
人类知识与 Agent Skills
项目发现雷达
让目录逐日增长，但不让自动化越过证据边界。候选达到可核验标准后，才会晋级为独立工具页。
正式目录回答“该不该用”；发现雷达只回答“最近出现了什么、为什么被扫描规则命中”。候选描述不构成本站评测。
DISCOVERY RADAR
GitHub 每日发现，尚未替你下结论。
这些项目由分类规则自动发现。Stars、许可证、描述和活跃时间来自 GitHub；未完成本站核验，不等同于推荐。
待核验
接入
agent-skills
Production-grade engineering skills for AI coding agents.
人类知识与 Agent Skills
待核验
接入
agentic-awesome-skills
AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 1,987+ agentic skills. Includes CLI, local MCP, catalog, plugins, and Workbench.
人类知识与 Agent Skills
待核验
接入
obsidian-skills
Agent skills for Obsidian. Teach your agent to use Obsidian CLI and open formats including Markdown, Bases, JSON Canvas.
人类知识与 Agent Skills
待核验
接入
scientific-agent-skills
Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 170,000+ scientists worldwide. 158 ready-to-use skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.
人类知识与 Agent Skills
待核验
接入
cli
Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.
人类知识与 Agent Skills
待核验
接入
skills
The open agent skills tool - npx skills
人类知识与 Agent Skills
待核验
溯源 · 校验
remove-ai-watermarks
AI watermark remover. CLI and Python library to strip visible and invisible AI watermarks (Gemini / Nano Banana sparkle, SynthID) and provenance metadata (C2PA, EXIF, IPTC) from images.
C2PA 与内容来源
待核验
人化 · 校验
best-humanizer-handbook
Best AI Humanizer Handbook A practical guide to making AI-assisted writing clearer, more credible, and more human
AI 写作人化
待核验
人化 · 校验
humanize-text-skill
Free AI Humanizer: Humanize AI Text Online
AI 写作人化
待核验
溯源 · 校验
specifications
The public specifications for the C2PA
C2PA 与内容来源
待核验
识别 · 校验
Deepfake_detection_using_deep_learning
This projects aims in detection of video deepfakes using deep learning techniques like RestNext and LSTM. We have achived deepfake detection by using transfer learning where the pretrained RestNext CNN is used to obtain a feature vector, further the LSTM layer is trained using the features. For more details follow the documentaion.
视频深度伪造检测
待核验
识别 · 校验
Audio-Deepfake-Detection
Research progress on speech deepfake detection: Relevant datasets aggregated from the review literature and publicly available codes
声音深度伪造检测
待核验
溯源 · 校验
c2pa-python
Python binding for c2pa-rs library
C2PA 与内容来源
待核验
溯源 · 校验
C2PAremover
A command-line tool to detect and remove Content Authenticity Initiative (CAI) metadata, also known as C2PA (Coalition for Content Provenance and Authenticity) metadata, from image files.
C2PA 与内容来源内容真实性与元数据
待核验
识别 · 校验
SIDA
The offical repository of "SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model"
图片与深度伪造检测
待核验
保护 · 校验
Pyison
Pythonic AI crawler tarpit
训练退出与抓取控制
待核验
溯源 · 校验
atlas-cli
A command-line interface tool for creating, managing, and verifying Content Provenance and Authenticity (C2PA) manifests for machine learning models, datasets, and related artifacts.
C2PA 与内容来源内容真实性与元数据
待核验
识别
2026-AI-DETECTOR-BENCHMARK
Benchmarking AI text detectors (GPTHumanizer, GPTZero, ZeroGPT, Sapling) across multiple datasets to evaluate accuracy, human false positive rates, and risk trade-offs.
AI 文本检测
待核验
溯源 · 校验
c2pa-js-legacy
JavaScript SDK for displaying and validating C2PA data
C2PA 与内容来源
待核验
识别 · 校验
SafeEar
[ACM CCS'24] SafeEar: Content Privacy-Preserving Audio Deepfake Detection
声音深度伪造检测
待核验
人化 · 校验
slopornot
Agentic AI Humanizer Skill for Codex, Claude and OpenClaw: Bypass AI Detectors
AI 写作人化
待核验
溯源 · 校验
conformance-public
Public documentation for the C2PA Conformance Program
C2PA 与内容来源
待核验
识别 · 校验
Celeb-DF-PP
Celeb-DF++: A Large-scale Challenging Video DeepFake Benchmark for Generalizable Forensics
视频深度伪造检测
待核验
识别 · 校验
AUDDT
A toolkit for benchmarking on a wide variety of audio deepfake datasets.
声音深度伪造检测
待核验
保护 · 校验
WP-robots-generator
Smart client-side robots.txt generator for WordPress - security levels, plugin presets, AI crawler blocking, i18n. No backend, no dependencies.
训练退出与抓取控制
待核验
溯源 · 校验
c2pa-org.github.io
C2PA Website
C2PA 与内容来源
待核验
溯源 · 校验
c2pa-content-credentials-extension
C2PA Chrome Extension
C2PA 与内容来源
待核验
溯源 · 校验
socialforge
Open-source agency-grade social media production plugin — 16 skills, 25 commands, AI image (Nano Banana Pro) + AI video (Kling v3.0 Pro) + C2PA signing (EU AI Act Article 50). Installs on Claude Code, Cowork, Codex, Cursor, Copilot CLI, Antigravity. By Indranil Banerjee (indranil.in).
C2PA 与内容来源
待核验
溯源 · 校验
c2pa-swift
C2PA SDK for Swift (iOS/macOS)
C2PA 与内容来源
待核验
溯源 · 校验
softbinding-algorithm-list
A list of C2PA approved soft binding algorithms
C2PA 与内容来源
待核验
人化 · 校验
contentforge
Open-source enterprise content production plugin — 21 skills, 13 agents, 11 quality gates, 29-pattern AI humanizer, fact-checker, real .docx output with C2PA signing (EU AI Act Article 50 ready). Installs on Claude Code, Cowork, Codex, Cursor, Copilot CLI, Antigravity. By Indranil Banerjee (indranil.in).
AI 写作人化
待核验
保护 · 校验
aeo-god-mode
Free AEO + AI search readiness plugin for WordPress. Schema, llms.txt, AI crawler controls, brand sentiment + citation tracking.
训练退出与抓取控制
待核验
保护 · 校验
agentmarkup
Build-time llms.txt, JSON-LD, markdown mirrors, AI crawler controls, and validation for Vite, Astro, and Next.js websites.
训练退出与抓取控制
待核验
识别 · 校验
SLSforASVspoof-2021-DF
Code for paper "Audio Deepfake Detection with Self-supervised XLS-R and SLS classifier
声音深度伪造检测
待核验
人化 · 校验
AI-Text-Humanizer
ZAYUVALYA - AI Humanizer is a developing tool designed to rephrase AI-generated text to make it more natural and reduce detection by AI content detectors. Currently in its early stages, the project focuses on context-aware paraphrasing and aims to improve with further optimizations.
AI 写作人化
待核验
溯源 · 校验
guidance-for-media-provenance-with-c2pa-on-aws
This Guidance demonstrates how to run the Coalition for Content Provenance and Authenticity (C2PA) standard for tracking provenance with media workloads on AWS.
内容真实性与元数据
待核验
人化 · 校验
ai-humanizer-mcp-server
A powerful Model Context Protocol (MCP) server that helps refine AI-generated content to sound more natural and human-like. Built with advanced AI detection and text enhancement capabilities.
AI 写作人化
待核验
识别 · 校验
ADD-arxiv-daily
🕵️♂️🔊 Automatically update Audio Deepfake Detection (ADD) papers daily using GitHub Actions (updates every 12 hours)
声音深度伪造检测
待核验
识别
ai-text-detector
Desklib's AI Text Detector
AI 文本检测
待核验
识别 · 校验
audio-deepfake-detection
Audio deepfake detection sytem on CNN
声音深度伪造检测
待核验
识别 · 校验
OpenAVFF
An unofficial pytorch implementation of the closed-source newly published work AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection.
视频深度伪造检测
待核验
识别 · 校验
MINTIME-Multi-Identity-size-iNvariant-TIMEsformer-for-Video-Deepfake-Detection
Code for Video Deepfake Detector from "MINTIME: Multi-Identity Size-Invariant Video Deepfake Detection", paper available on IEEE Transactions on Information Forensics and Security.
视频深度伪造检测
待核验
人化 · 校验
ai_humanizer
AI Humanizer - Prompt Model Release
AI 写作人化
待核验
识别 · 校验
attack-agnostic-dataset
Implementation of Attack Agnostic Dataset: Towards Generalization and Stabilization of Audio DeepFake Detection paper
声音深度伪造检测
待核验
识别 · 校验
audio-deepfake-adversarial-attacks
Implementation of "Defense against Adversarial Attacks on Audio DeepFake Detection"
声音深度伪造检测
待核验
识别 · 校验
audio-deepfake-source-tracing
Baselines for IS25 Source Tracing Special Session
声音深度伪造检测
待核验
识别 · 校验
RAIS
RAIS (Rehearsal with Auxiliary-Informed Sampling) for Audio Deepfake Detection [INTERSPEECH'25]
声音深度伪造检测
待核验
保护 · 校验
rankready
AI SEO for WordPress — get cited by ChatGPT, Perplexity, Claude, Gemini & Google AI Overviews. llms.txt generator + Markdown endpoints + FAQ schema + 31 AI crawler controls + E-E-A-T + WebMCP. Works alongside Yoast, Rank Math, AIOSEO. Zero frontend bloat. By POSIMYTH.
训练退出与抓取控制
待核验
人化 · 校验
ai-humanizer
AI Humanizer
AI 写作人化
待核验
识别 · 校验
RawNetLite
Implementation of the paper "RawNetLite: Lightweight End-to-End Audio Deepfake Detection"
声音深度伪造检测
待核验
识别 · 校验
DFADD
Official Implementation and Dataset of paper - DFADD: The Diffusion and Flow-matching based Audio Deepfake Dataset
声音深度伪造检测
待核验
识别 · 校验
FakeOut
Leveraging Out-of-domain Self-supervision for Multi-modal Video Deepfake Detection
视频深度伪造检测
待核验
识别 · 校验
who_are_you
This repository contains the code associated with the paper: "Who Are You (I Really Wanna Know)? Detecting Audio DeepFakes Through Vocal Tract Reconstruction"
声音深度伪造检测
待核验
保护 · 校验
block-ai-crawlers
Adds an option to block AI crawlers via robots.txt
训练退出与抓取控制
待核验
保护 · 校验
AI-Crawler-Detector
Tool for Fast Detection of Website/Server AI Crawler Blocking Policies（Not robots.txt）
训练退出与抓取控制
待核验
识别 · 校验
M2S-ADD
[InterSpeech'2023] "Betray Oneself: A Novel Audio DeepFake Detection Model via Mono-to-Stereo Conversion"
声音深度伪造检测