avoid-ai-writing: A Rule-Based Auditor for LLM Prose, Not a One-Shot Prompt
Skill that audits and rewrites content to remove AI writing patterns. Use it with your favorite agents including Claude Code, OpenClaw, Codex, and Hermes.
At a glance
- What is it?
- avoid-ai-writing is an MIT-licensed agent skill that flags and rewrites AI writing patterns using a 112-entry replacement table and a pattern catalog. It is rule-driven and inspectable, which is also where its limits sit.
- Who is it for?
- Adopt it if you already run Claude Code or another agentskills.io-compatible agent and you want an auditable, rule-based pass over prose you publish, with detect mode available for text you do not want altered. Do not adopt it for source code, configuration or generated data: the README states the Edit mode refuses those because prose rewrites can corrupt structured content.
- Can I use it commercially?
- Yes. MIT is a permissive licence: you can use, modify and sell software built on it, as long as you keep its copyright and licence notices.
- Is it still maintained?
- Yes. The repository received new commits within the last day.
- What is it written in?
- Mainly JavaScript, according to GitHub's language statistics.
Answers come from the project's GitHub data, last synced on November 15, 2026, and from our analysis. They are not legal advice.
Star history
- conorbronsdon/avoid-ai-writing5,663 ★ · +1,377
| Repository | 2026-09-10 | 2026-11-15 |
|---|---|---|
| conorbronsdon/avoid-ai-writing | 4.3k | 5.7k |
1,377 Stars in the last 66 days, measured from the daily GitHub snapshot. Compare with other projects
Editorial analysis
The Problem: One-Shot "Sound Human" Prompts Do Not Show Their Work
The README frames the project against a specific failure: a single prompt asking a model to make text sound human catches obvious tells and hides its reasoning. This skill instead completes its audit, correction and available verification before returning one final version, with a short change summary when useful and a detailed audit available on request. The target user is someone who publishes prose and needs to see what changed and why, not someone who wants a black-box polish. It ships as a portable skill for Claude Code, OpenClaw, Hermes and other agentskills.io-compatible agents, so the same rule set travels across tools rather than being rewritten per editor.
How the Detection Actually Works: Tiers, Density and a Second Pass
The mechanism is a word replacement table with 112 entries across three tiers, plus 10 Tier 3 phrases. Tier 1 matches flag unless a listed exception applies. Tier 2 words flag when they cluster. Tier 3 words flag only at high density. Tier 1 splits further into 1A frequency markers such as delve and tapestry, and 1B clarity edits such as "in order to" and "utilize". On top of the table sits a pattern reference covering content, language, structure, communication and meta patterns, plus structural detection, AI-tool fingerprints, conversational-register patterns, share-post framing, narrated candor and unnecessary hyphenation. After the first edit, review can catch patterns that survive it, with one shared limit covering corrective edits and preservation repairs. That second pass is the part a single prompt usually lacks.
Three Modes, and Why Detect Mode Is the One Worth Understanding
Rewrite is the default: flag patterns and rewrite the text, then run the second pass. Detect flags without rewriting and separates real problems from judgment calls. Edit modifies a prose file in place through the Edit tool with minimal targeted changes, preserving passages that are already human, and returns an edits-made plus verification report rather than the whole file. Detect mode is the mode that changes how you can use the tool. If a pattern is intentional, or you are auditing text you have no permission to alter, rewriting is the wrong operation. The README lists exactly those cases. There is also an optional voice profile with five settings (casual, professional, technical, warm, blunt) that controls how the prose should sound, independent of the audience context profile. Keeping voice separate from audience is a sensible split, and it is the kind of thing that is easy to conflate in a prompt-only approach.
Getting It Running: Clone, Single File, or Slash Command
The primary install is a directory clone into the agent's skills folder. The README has separate install sections for Claude Code, OpenClaw, Cursor, Hermes and OpenAI Codex, and Claude Cowork installs it as a plugin. The repository also bundles scripts/, detector/ and examples/ for optional mechanical verification.
The Install Footgun: SKILL.md Without references/patterns.md
The README tells you to install the complete skill directory. The repository root holds SKILL.md alongside a references/ directory and a self-contained SKILL.full.md, so copying a single file is not the documented install.
Where This Is the Wrong Tool: Structured Content and Judgement Calls
Edit mode refuses source code, configuration and generated data, on the stated grounds that prose rewrites can corrupt structured content. That refusal is correct and it is also a boundary: this skill is for prose, not for mixed repositories. The tiered design implies a second limitation. Tier 2 words flag when they cluster, and Tier 3 words flag only at high density. A short passage with one Tier 2 word will not trip the detector, so a genuinely AI-flavoured sentence can pass when it is short or when its tells are spread thinly across a document. The README acknowledges this class of problem by offering detect mode for separating real problems from judgment calls, which is an admission that some flags are not settled. The demo output is instructive here: the rewrite of the funding paragraph drops the promotional language and the vague attribution, and removes the unsupported market prediction.
The Real Alternative: General Linters and Style Checkers
The closest comparison is a general prose linter in the Vale or textlint family. Those tools parse text against configurable style rules and report violations, and they run in CI without an agent in the loop. The difference in approach is the rule vocabulary and the repair step. A style checker enforces rules you write for your house style, and it will not tell you that "serves as" is copula avoidance or that "watershed moment" is significance inflation. This project ships an opinionated pattern reference and a 112-entry word replacement table, so the rules are the product rather than something you author. The trade is control: you cannot easily redefine what counts as an AI-ism, because the tiers and the weighting are built in. The second difference is that this skill rewrites and then re-audits its own output, while a linter only reports. If your need is deterministic enforcement of a house style in a build pipeline, a linter fits better. If your need is a second reader that names AI tells and offers a plain-language replacement, this is the narrower and more specific tool.
Maintenance, Versioning and the MIT Licence
The project is MIT licensed, which permits commercial use and modification, though the usual caveat applies that this is not legal advice and you should read the LICENSE file yourself. Versioning is active and granular. The three most recent releases are v3.38.0 (2026-10-15), v3.37.0 (2026-10-04) and v3.36.0 (2026-09-23), so the rule set can shift under you between sessions. For a skill whose output you might paste into published work, pin the version you audited against rather than tracking main. The upgrade cost is otherwise low: there is no service, no runtime dependency to patch and no data leaving your machine beyond whatever your agent already sends. The real maintenance burden is reviewing the pattern catalog when you upgrade, because a changed tier weighting can move a document's classification without any change to the document. The repository was last pushed on 2026-11-02 and is not archived.
Editorial conclusion
Adopt it if you already run Claude Code or another agentskills.io-compatible agent and you want an auditable, rule-based pass over prose you publish, with detect mode available for text you do not want altered. Do not adopt it for source code, configuration or generated data: the README states the Edit mode refuses those because prose rewrites can corrupt structured content. Before relying on it, verify that you installed the complete skill directory, as the README installation section directs.
Frequently asked questions
What are AI words to avoid when writing?
The avoid-ai-writing detector ships a 112-entry word replacement table across 3 tiers plus 10 Tier 3 phrases, where every flagged word has a specific plainer alternative. Tier 1 words flag on sight unless a listed exception applies, Tier 2 words flag when they cluster, and Tier 3 words flag only at high density.
How do I avoid AI writing patterns with avoid-ai-writing?
Install the complete skill directory into your agent, then pick one of three modes. Rewrite flags patterns, applies up to two editing passes and returns one final version. Detect flags without changing anything. Edit rewrites a prose file in place and refuses source code, configuration and generated data.
Can avoid-ai-writing be used to detect AI writing from the command line?
Yes. The npm package avoid-ai-writing-detector declares two binaries, avoid-ai-writing and avoid-ai-writing-gate, and its entry point is detector/patterns.js. The README has sections for scoring a file or piped text and for gating prose in GitHub Actions or pre-commit. Node 18 or newer is required.
How can I remove AI tells from my writing style?
The skill runs in Rewrite mode by default, where it flags AI patterns, applies up to two editing passes, verifies the result when possible and returns one final version. An optional voice profile, one of casual, professional, technical, warm or blunt, sets how the prose should sound independently of the audience context profile. The README treats house style as a different job.
Official sources
Add this badge to your README
If you maintain this project, the badge below links readers to this analysis and shows its maintenance status from the daily GitHub snapshot. Paste the markdown into your README; add ?metric=license or ?metric=stars to the image URL for a different field.
[](https://hysenlabs.com/projects/conorbronsdon-avoid-ai-writing)Star history chart for your README
[](https://hysenlabs.com/projects/conorbronsdon-avoid-ai-writing)Was this useful?