Writing & Editing

Archive of my writing, style skills, agents, etc.

Agent skill for writing, validating, testing, and tuning ModSecurity v3, Coraza, and OWASP CRS WAF rules using AI coding assistants.

通过流程图来构建流水线提示词, 辅助Claude Code的Skill和Agent提示词编写; Flowcharts are used to construct pipeline prompts, assisting in the writing of Skill and Agent prompts for Claude Code.

Hermes Agent research skill — orchestrated article writing with multi-model routing

SharkonAI is a fully autonomous, self-recovering AI agent that lives in Telegram. It combines a powerful LLM brain (NVIDIA-hosted models) with 51+ executable tools to perform virtually anything — from running system commands and writing code, to controlling your desktop GUI with pixel-perfect precision, to creating its own new skills at runtime.

Humanizer is an AI writing skill that detects and rewrites common signs of AI-generated prose. It helps agents preserve meaning, match audience and tone, reduce hype and filler, and produce writing that sounds natural, specific, and human across drafts, posts, docs, and messages.

A systematic implementation of Harness Engineering, enabling agents to work in a stable, controllable, and verifiable environment. It shifts focus from "writing code" to "designing feedback loops".

An AI agent skill for value investing analysis, valuation, moat assessment, cycle positioning, and investment memo writing for listed technology companies.

README writing skill for Amplifier agents — dual-audience structure, problem-first opening, quality checklist

Agent Skill for writing RFCs

Agent plugins and skills for thinking and writing

Agent skill for writing prose based on https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing

InfiEpisteme 📜 — Talk to Claude Code, get a research paper. 19 Markdown skills orchestrate the full pipeline: literature survey → ideation → experiments → writing → cross-model review. No framework, no lock-in — pure .md skills runnable by any LLM agent.

🧬 Stop writing bad CLAUDE.md files. A Claude Code skill that generates production-grade CLAUDE.md configurations with verified commands, real architecture, and safety guardrails.

Agent-ready Japanese writing kit based on 『悪文』 for review and revision

Here are the skills for agent to write the abstract related to biomedical subject.

OpenClaw workspace initializer skill - generates all template files (AGENTS.md, SOUL.md, USER.md, IDENTITY.md, BOOTSTRAP.md, TOOLS.md, HEARTBEAT.md, MEMORY.md) for new agent workspaces.

Professional essay writing and editing skills for AI agents

An agent skill to de-AI your writing

🚀 工业级 AI 长篇网文生成框架 | An industrial-grade AI web novel generation framework based on a microkernel and plugin architecture, featuring context isolation, RAG memory, and MCP-inspired skills for writing million-word stories.

Source code for wchen.ai — a vibe-coded personal website and blog built with spec-kit, with posts/content generated from the author’s ideas using agent skills. Designed for easy customization on a solid foundation for publishing projects, notes, and long-form writing.

Agent Skill for writing high-quality Agent Skills

🎒 A curated starter pack of AI agent skills. One URL, one command — your agent is ready. 14 battle-tested skills for coding, design, writing, and marketing.

This is a repository of reusable “agent skills” — structured workflows for an AI assistant. Each folder is one skill that handles a specific task (planning, coding, tooling, or writing). Together, they let you install and run these workflows in projects via simple commands.