v0.6.0 · MIT
Procedural writing-style skills for AI agents: official frameworks (plain language, business writing, GOV.UK, AP style, STE-100, developer docs) + character voices. Agent Plugins 1.0.0, works in opencode, Claude Code, Codex.
v1.3.0 · MIT
Claude Code plugin:去除文章中的 AI 寫作痕跡,使文字更自然、更有人味。以台灣正體中文為主。
— · MIT
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
v2.4.0 · AGPL-3.0
Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks.
v0.7.1 · MIT
Free, open-source AI writing humanizer and detector. 55 patterns, 5 voices, a 0-100 AI-tell score, and nothing leaves your machine.
v0.18.0 · MIT
Agent Skills for end-to-end story writing in markdown, packaged as Codex and Claude Code plugins.
v0.9.3 · Apache-2.0
A local detector for AI-writing patterns. Scores every prose file your agent saves. Python standard library only, no network, no model.
— · AGPL-3.0
AI humanizer skill for Claude Code, Codex and Cursor. Removes AI slop and the signs of AI writing, then measures the rewrite against human baselines.
v2.13.0 · Apache-2.0
An open-source, local-first writing workspace where you can write with Claude Code and Codex, drawing on your own sources and past work.
v0.7.0 · MIT
ISO 24495 Plain Language skills and plugin
v0.7.0 · MIT
Make AI output sound human. Strips AI-isms (sycophancy, stock vocab, hedging stacks, em-dash pileups), preserves code/URLs/headings. Plugin for Claude Code, Cursor, Windsurf, Codex, Cline, Copilot, Gemini.
v0.2.10 · Apache-2.0
dsh-Openwrite:OpenWrite 的 DeepSeek Harness 小说创作插件,含统一创作 Agent、90 个小说工具、原生工作台与标准审稿 DAG
v0.1.0 · MIT
Air traffic control discipline for agent output. Written for a reader with ADHD.
v0.6.25 · MIT
Achieve extraordinary results with claude code across a variety of tasks
v1.1.0 · MIT
Compare multiple skills on the same task and pick the winner.
— · MIT
Claude Code plugin for people who describe what they want and let Claude build it: brand identity, product planning, plain-language build/ship/debug workflows, and a creator toolkit.
v2.0.0 · Apache-2.0
AI 编译纯文本小说工作台 for the dsh web GUI: import a novel outline (docx/text), plan volumes & chapters with LLM, generate chapter by chapter (3000-4000 chars each), auto AI review & book audit, and export the full book as Markdown/TXT into your chosen output fold
v3.8.0 · no license
面向 AI Agent 的微信公众号创作与发布 CLI:Markdown 排版、AI 配图、预览与草稿创建;支持由浏览器 Agent 保存知乎、CSDN、头条未发布草稿。
— · MIT
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.
v0.1.12 · MIT
DeepSeek 写网文/小说的工作流插件:DeepSeek Harness 社区插件,内置小说、短剧、游戏、视频解说四个工作台 | Community DeepSeek Harness plugin with novel, short-drama, game and video-recap workbenches.
v0.1.0 · Apache-2.0
The open standard for omnipresent AI. Claude Code, OpenCode, Gemini CLI, Shell, Chrome, DeepSeek Harness. Model-agnostic
— · no license
372 AI skills, 76 expert agents, and 867 stdlib Python tools for every team: engineering, PM, marketing, C-level, compliance, business ops, and research. Installs on Claude Code, Cursor, Codex, Gemini, Copilot, and 6 other AI assistants.
v1.1.0 · MIT
Claude Code skill for editing Russian text using Ilyakhov's information style (инфостиль). First-ever AI skill based on 'Пиши, сокращай' methodology.
— · Apache-2.0
Agent Skills marketplace: framework-aware skills for code review, documentation, test-plan generation, AI-writing detection, architectural analysis, and git workflows — for Python, Go, Rust, Elixir, React, Remix, and iOS/Swift. Works with Claude Code, Codex, and any agent that supports Agent Skills.