This skill should be used when the user asks to "create AGENTS.md", "update AGENTS.md", "maintain agent docs", "set up CLAUDE.md", or needs to keep agent instructions concise. Enforces research-backed best practices for minimal, high-signal agent documentation.
avoid-ai-writing
avoid-ai-writing is an open-source docs skill for Claude Code and compatible agents, published by wshobson. Its author describes it as: “Audit and rewrite prose so it stops reading as machine-generated. Use this skill when asked to remove AI-isms, clean up AI writing, edit a draft for AI tells, audit a README, changelog, release note, PR description, o…”. The project has 39k stars on GitHub and is available under the MIT license. Add it to your setup with `/plugin marketplace add wshobson/agents`.
What avoid-ai-writing does
Find the patterns that make text read as machine-generated, then fix them without sanding off the author's voice.
Installation
Add avoid-ai-writing to your agent with:
/plugin marketplace add wshobson/agentsAlways review a skill's source before installing it. This command comes from the skill's public repository; the linked repo is the source of truth for exact setup steps.
What's inside
The SKILL.md for avoid-ai-writing is organised into these sections:
- What a flag proves
- Modes
- The pass
- Rewriting without installing a new accent
- Escape hatch
- Output
When to use it
Reach for avoid-ai-writing when you want docs help from your agent without writing the same instructions every session. Load the skill and the agent picks it up automatically for relevant tasks.
Strengths
- Clear MIT license — safe to read and adapt
- Ships in wshobson/agents, an established project with 38,890 GitHub stars
- Actively maintained (recent commits)
Topics
Frequently asked questions
- What does avoid-ai-writing do?
- Audit and rewrite prose so it stops reading as machine-generated. Use this skill when asked to remove AI-isms, clean up AI writing, edit a draft for AI tells, audit a README, changelog, release note, PR description, or blog post for machine-sounding prose, or make text sound less like AI. Supports a detect-only mode, a rewrite mode, and an edit-in-place mode, with optional voice and context profiles.
- How do I install avoid-ai-writing?
- Run /plugin marketplace add wshobson/agents in your agent, then reload your skills. Review the source at https://github.com/wshobson/agents before installing.
- Is avoid-ai-writing free to use?
- Yes. avoid-ai-writing is free and open source under the MIT license, so you can read, run, and adapt it within that license's terms.
- Where does avoid-ai-writing come from?
- avoid-ai-writing ships inside wshobson/agents, a repository that contains 54 catalogued skills in total. The repository's 38,890 GitHub stars apply to that whole collection, not to this skill on its own.
Related skills
More Docs →
README is an open-source docs skill for Claude Code and compatible agents, published by alirezarezvani. It packages reusable instructions an agent loads on demand to help with docs tasks. The project has 25k stars on GitHub and is available under the MIT license. Add it to your setup with `/plugin marketplace add alirezarezvani/claude-skills`.
Diagnose LazyCodex and Codex CLI installation health against the latest sources. Use whenever the user asks for a doctor or health check, says LazyCodex, lazycodex-ai, omo-codex, or Codex behaves oddly after an install, update, or config change, suspects a stale, drifted, or broken setup, or wants the local install audited and compared with the latest LazyCodex and Codex code.
Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code and runtime actually do, so the next session or the next person starts from one current answer. Trigger when the user names "neat-freak", "洁癖", or "/neat" — and also on clear knowledge-closeout intent without the name: syncing or tidying project docs/rules/memory after development ("把文档和记忆整理一下", "收尾时把文档同步掉", "docs 和代码对不上了"), stale or conflicting CLAUDE.md/memory, a clean handoff to a teammate or a fresh session, or auditing whether workspace rules are actually followed. Do not trigger for pure coding/refactoring/debugging tasks, tidying data or prose (JSON, 周报, changelog announcements), or a bare "整理" with no project-knowledge context.
Rewrite text that sounds AI-generated while keeping the writer's facts, meaning, and voice. Use when editing or reviewing prose for inflated claims, sales language, vague sources, repetitive structure, stock AI words, passive voice, filler, or chatbot artifacts. Based on Wikipedia's "Signs of AI writing."