30 open-source projects similar to blader/humanizer, ranked by shared indexed features. Tags may describe platforms or build tools rather than the same primary purpose. Check each project’s use case, license, and deployment requirements before treating it as a replacement.
Humanizer-zh is a tool designed to transform AI-generated content into natural-sounding writing by removing repetitive patterns and mechanical formatting. It functions as an AI content de-optimizer and text humanizer specifically focused on making Chinese text sound more human-authored. The project specializes in Chinese language refinement, replacing corporate jargon and artificial linguistic markers with native expressions and varied sentence rhythms. It employs a system to strip formulaic signatures and repetitive structures common in large language model outputs to increase perceived auth
Sepia is an agent skill that detects and removes machine-sounding patterns from text, editing prose so it reads as human-written rather than model-generated. It ships as a single canonical skill file that follows the Agent Skills standard, and it can be installed with one command or through ready-made plugin packages for several popular coding agents. Its editing is organized around a 30-feature diagnostic rubric that can review a passage and report AI-sounding patterns without changing anything, leaving the author to decide which problems are worth fixing. When the writing model is known, pe
Twitter scraper API skill for tweet search, advanced Twitter search, profile tweets, follower export, media download, monitors, webhooks, MCP, and posting automation: send tweets and replies.
Email marketing skill for Claude Code. 55K words, 908 sources, 19 industry playbooks. Install the skill and Claude becomes your email marketing expert.
Claude Code skill for publishing Markdown articles to X (Twitter) Articles
Open-source Claude skills for GEO, AI discoverability, and developer GTM workflows. Built for developer-focused companies that want their documentation to be found, parsed, and cited by AI systems.
This project provides a standardized framework for extending the functional range of artificial intelligence agents through a registry of modular, declarative instructions. It enables agentic workflow automation by allowing developers to define task-specific behaviors and operational constraints that guide how agents interact with external tools and execute multi-step processes. The system distinguishes itself through a directory-based discovery model and a plugin-registry architecture that facilitates the distribution of specialized workflows. By utilizing a schema-driven specification that
Open-source AI marketing plugin for agencies & in-house teams — 158 skills, 25 specialist agents, 12-Part Strategy Flow, Cowork team-persistent, EU AI Act Article 50 ready, 6-platform AEO/GEO incl. Google AI Mode. Installs on Claude Code, Cowork, Codex, Cursor, Copilot CLI, Antigravity. MIT-licensed.
Career-ops is an AI-driven job search automation system designed to manage the entire application lifecycle, from discovery to tracking. It functions as a career copilot that utilizes autonomous agents to identify vacancies, evaluate professional fit, and generate tailored application materials. The project distinguishes itself through a multi-archetype persona management system and writing style calibration, allowing users to maintain different professional identities and a consistent voice across documents. It employs a multi-dimensional weighted scoring system to evaluate job suitability a
Inkos is an automated fiction pipeline and interactive narrative engine designed for generating novels, scripts, and interactive games. It employs a multi-stage writing workflow that manages long-form narrative memory through a database-backed system to prevent context drift and maintain character and world consistency. The system distinguishes itself through a style-fingerprinting engine that extracts linguistic patterns from reference texts to mimic specific authorial voices and refine AI prose. It utilizes a role-based model routing system to assign different language models to specific ta
research-writing-skill is a prompt-driven toolkit of reusable large language model skills for academic paper writing. It guides researchers through planning a paper with a multi-round question-and-answer session, drafting one chapter at a time into separate files, polishing the text, and running a self-review pass before submission to a journal or committee. Writing tasks are routed to guidance for engineering, social science and humanities, medical, or legal papers so that tone and structure suit the field. Several capabilities set it apart from a general writing helper. A humanizing pass re
Everywhere is a desktop AI assistant that understands whatever is on your screen and can act across applications without requiring screenshots or manual context switching. It reads structured UI data through accessibility and automation APIs to perceive the active application and visible content, then provides context-aware help, summaries, translations, and answers to natural language questions about what you are viewing. The tool distinguishes itself by combining on-screen content analysis with a multi-LLM agent platform that routes requests to providers like OpenAI, Anthropic, and local mo
In a world where it's easy to feel overwhelmed, https://kuakua.app/ offers a sanctuary of uplifting words, ideas, and content designed to inspire and empower you. Built around the belief that Money Doesn't Change the World, IDEAS DO, this platform encourages you to focus your energy on what truly matters.
snips-nlu is a Python library and natural language understanding engine designed to convert unstructured text into structured data. It identifies user intents and extracts associated entities from natural language sentences to enable machine-readable command processing. The engine functions as a multilingual parser capable of processing text across multiple languages. It maps identified entities to canonical values or standardized ISO formats, such as timestamps, to ensure data consistency. The project covers intent classification and named entity recognition, utilizing sequence labeling and
Presenton is an AI-powered presentation engine and API designed to transform natural language prompts, uploaded documents, and structured data into professional slide decks. It functions as a generation service that leverages large language models to automate the creation of outlines, slide content, and visual assets. The system is distinguished by its support for both cloud-based and self-hosted infrastructure, allowing for the integration of local language models and image generators to ensure data privacy. It implements a Model Context Protocol server, enabling external AI agents to trigge
cuml is a GPU-accelerated machine learning library and framework that uses CUDA to accelerate tabular data preprocessing and model execution. It provides a suite of tools for training and deploying classification, regression, and clustering models on NVIDIA GPUs and GPU clusters. The library is designed for scalability, offering a distributed GPU machine learning environment that can spread computation and data across multiple hardware accelerators and nodes to handle datasets exceeding single-device memory. It mirrors standard estimator interfaces to allow the replacement of CPU-based models
This project provides a translated version of the scikit-learn machine learning library guides and API references for Chinese speakers. It serves as a localized knowledge base and technical reference for implementing predictive data analysis and statistical modeling using a Python-based toolkit. The resource covers the implementation of supervised learning, including classification and regression tasks, and unsupervised learning workflows for pattern discovery and anomaly detection. It also provides guidance on data science education, specifically focusing on the use of scikit-learn for machi
Human-writing is a portable Agent Skill that guides AI agents to draft and revise Chinese prose in a plain spoken voice, so the text reads like one specific person talking rather than generic, report-style machine output. It covers articles, posts, stories, reviews and scripts, and works by stripping out stock phrases, repeated explanations and formulaic wording. Beyond style guidance, the skill sets rules for what gets written. Before drafting, it checks whether enough real source material exists, searches for missing facts, asks at most three questions, and shortens the piece instead of pad
This project is a collection of supervised and unsupervised machine learning algorithms implemented from scratch using Python. It serves as an educational resource for studying model training, parameter optimization, and the implementation of core predictive models. The library provides a variety of supervised learning tools, including linear and logistic regression, decision trees, and support vector machines. It also features unsupervised learning capabilities for discovering patterns in unlabeled datasets through clustering algorithms. Broad capability areas include ensemble learning thro
The TensorFlow Cookbook is a collection of code examples and recipes for building, training, and deploying machine learning models using TensorFlow. It covers the full model lifecycle, from constructing neural networks and training them with configurable parameters to packaging trained models for production deployment with unit tests and multi-device support. The project also integrates TensorBoard for logging and visualizing computational graphs, scalar summaries, and histograms during training. The cookbook demonstrates a wide range of machine learning techniques, including convolutional ne
Featuretools is a Python data science library and automated feature engineering framework designed to create predictive features from multiple related datasets. It automates the data preparation and transformation steps required for machine learning models through deep feature synthesis. The library enables the automatic generation of comprehensive feature tables by applying recursive transformations to relational data. It supports the transformation of unstructured text into structured numeric features and allows users to define custom primitives to extend the synthesis process with specific
This project is an LLM research workflow framework and academic writing automation tool designed to coordinate the research, drafting, and peer-review processes of scholarly papers. It functions as a scientific manuscript auditor and an AI peer review system that uses multi-agent evaluation to verify citation integrity and score manuscripts against quality rubrics. The system distinguishes itself through a verification suite that employs vision models for figure fidelity auditing and anchor links for claim support verification. It includes a writing style calibration utility that analyzes pre
CKEditor 4 is a browser-based WYSIWYG rich text editor that enables users to create and format HTML content directly in the browser. It operates on a plugin-based architecture with a configurable toolbar system, DOM-based content editing, and an event-driven lifecycle, all delivered through a CDN-based distribution model. The editor supports skin-based theming and includes a legacy plugin compatibility layer for backward compatibility. The editor distinguishes itself as a cross-platform framework that integrates natively with Angular, React, Vue, Electron, Android, and iOS environments. It of
Odysseus is a self-hosted AI workspace and autonomous agent framework designed for deploying and managing large language models. It serves as a centralized platform for orchestrating agentic tasks, utilizing a model context protocol server to connect AI models to external system utilities, browser automation, and local hardware. The system distinguishes itself through a combination of retrieval-augmented generation and a RAG knowledge base, using vector stores and local embeddings to provide persistent semantic memory. It further integrates AI-driven communication management to triage email i
This project provides a framework for managing multi-agent systems, designed to automate complex software development, infrastructure, and business workflows. It functions as a multi-agent workflow orchestrator that routes tasks to domain-specific workers while maintaining state persistence and infrastructure automation. By leveraging large language models, the system decomposes high-level objectives into actionable plans, ensuring that complex operations are executed with consistency and reliability. The framework distinguishes itself through its hierarchical agent registry and policy-driven
PedalinoMini™ is a versatile, wireless, multi-purpose MIDI and HID controller that empowers performers, creators, and speakers to stay fully focused on their craft — hands-free.
AI agent skills for App Store Optimization (ASO) and app marketing. Built for indie developers, app marketers, and growth teams who want Cursor, Claude Code, or any Agent Skills-compatible AI assistant to help with keyword research, metadata optimization, competitor analysis, and app growth.