Humanizer is a skill (prompt) for AI agents that rewrites AI-generated text to sound human-written without altering factual content. It is built on Wikipedia's 'Signs of AI writing' guide and provides 26 numbered patterns grouped into six categories (staging, rhythm, inflation, formatting, leftovers, wrong reader). The skill is distributed as a single markdown file (SKILL.md) with YAML metadata, installable via plugin manifests for Claude Code, Cursor, and other agents through the Skills CLI. The repository also includes a validation script, issue templates, and CI workflows to maintain consistency across package files. While not a traditional software application, it functions as a tool that agents execute, with clear entry points (/humanizer command) and a well-defined workflow (mark tells, draft rewrite, check, finalize). The codebase is meticulously maintained with active issue triage, regular releases, and automated validation.
Patina is a deterministic, pattern-based AI text detection and humanization tool, primarily targeting Korean but supporting English, Chinese, and Japanese. It operates as a Node.js CLI (`patina-cli`), a web API (Vercel serverless), and an agent skill (Claude Code, Codex, Cursor). The core workflow: analyze source text for AI-typical patterns (stylometry, lexicon, discourse tells), build a structured prompt, invoke an LLM backend (OpenAI, Claude, Gemini, Kimi, etc.), verify meaning preservation (MPS/fidelity), and output a humanized rewrite with a deterministic audit trail. It enforces strict meaning guards (number safety, polarity, causation) and provides scoring, diff, and verification modes. The architecture is modular: a shared deterministic analysis core (`src/features/`) runs identically in Node and browser; a prompt builder assembles context from pattern packs, document types, and personas; multiple backend adapters abstract LLM invocation; and a verification pipeline ensures fidelity. The project includes extensive research infrastructure (benchmarking, human evaluation panels, corpus management) and a commercial Pro tier with Polar license validation. It is well-tested with over 200 unit/e2e tests, CI/CD, and security hardening (SSRF guards, input fencing, atomic writes).
NovelForge is an AI-assisted long-form novel writing desktop application built with Electron, Vue 3, and FastAPI. It provides a card-based content management system where each story element (characters, scenes, chapters, items, concepts) is stored as typed cards with JSON Schema validation. The core differentiator is a custom workflow engine that uses a code-style DSL with marker comments (`#@node`) to define automation flows, supporting triggers, async execution, pause/resume, and streaming SSE progress. AI integration is deep: configurable LLM providers (OpenAI, Google, Anthropic, Qwen), structured generation via instruction streams (LLM outputs JSON instructions that the frontend executes incrementally), memory extraction from text into cards and a knowledge graph (dual backend: SQLModel or Neo4j), and a context assembly system with a rich template language. The frontend features a dynamic form renderer from JSON Schema, an inspiration assistant with tool-calling agents, a workflow agent that can autonomously edit workflow code via patches, and a chapter editor with AI continuation, polish, and review. The system is designed for professional novelists and supports full project lifecycles from tags and outlines to chapter drafts and quality reviews. The architecture is a typical two-tier application: the backend exposes RESTful APIs and SSE streams; the frontend is a single-page Vue 3 app bundled as an Electron desktop application (with web compatibility via mock). Notable engineering strengths include the workflow node registration pattern, the expression evaluator with safe eval, the memory extractor registry, and the dynamic form system—all of which are cleanly abstracted and potentially reusable across projects. The codebase is actively maintained, with regular commits, well-organized modules, and comprehensive bootstrap initialization for built-in prompts and card types. However, some features are experimental (workflow agent auto-patching), the custom DSL is format-sensitive, and the heavy reliance on LangChain may introduce version lock-in.
Magic Resume is a production-oriented, bilingual resume-builder web application. Users manage resume documents in a dashboard, edit them in a multi-panel workbench with a live A4 preview, choose among nine templates, and export to PDF, PNG, JSON, or Markdown. The editor supports rich text, structured sections, custom themes, typography controls, and automatic one-page scaling. Resume data is local-first, persisted to localStorage and optionally synced to the local file system via the File System Access API. Under the hood, it is a React/TypeScript full-stack app with a somewhat unusual dual route-tree structure: an older Next.js App Router layout coexists with a newer TanStack Router source tree. State is managed with Zustand, UI uses Tailwind CSS and shadcn-style components, and rich text editing is built on Tiptap. AI features—streaming text polish, grammar checking, and vision-based PDF import—run through server routes that abstract OpenAI, Gemini, Anthropic, DeepSeek, Qwen, and Doubao behind a common transport with retries and SSE streaming. Export paths include a server-side PDF renderer, client-side html2canvas/jsPDF, browser print, JSON, and Markdown. The codebase is feature-rich and actively maintained, with some solid server-side AI abstractions and a meaningful test suite. However, it carries structural debt: near-identical section components are duplicated across nine templates, the old Next.js route tree remains alongside the newer TanStack routes, and AI model IDs/configurations are speculative and likely to age. It is deployable to Cloudflare Workers, Node, or Docker, but the architecture is hybrid and transitional rather than cleanly unified.
This repo is a structured AI-assisted long-form article writing system, primarily delivered as a Claude Code plugin and a Tauri desktop app. It orchestrates a 14+ stage workflow (topic clarification, research, drafting, humanization, fact-checking, export) using specialized subagents and a central workflow contract (`collab_v2.json`). The system is model-agnostic, supporting Anthropic-compatible APIs including Chinese providers. It includes extensive tooling for evidence management, style modeling, blind evaluation, and publication metrics. While the core functionality is robust and well-tested, the codebase suffers from triple directory mirroring (`.claude/`, `claude-runtime/`, `plugins/writing-agent/`) requiring manual sync, hardcoded Windows paths in the desktop app, and a partially unverified style library. The architecture cleanly separates agent prompts (Markdown), runtime scripts (Python/Node), and a Tauri frontend, making the workflow itself reusable as a pattern for multi-stage AI agent orchestration.
This repository is a curated collection of prompt templates and agent skill configurations for AI-assisted academic writing. It contains no executable code, only a single README.md file that documents prompts for translation, polishing, logic checking, and figure/table caption generation, as well as instructions for configuring agent skills in tools like Cursor. The prompts are designed for use with large language models to help researchers write and refine papers. While the content is well-organized and practical, the repository is purely documentation with no software implementation, making it a reference resource rather than a functional application.