# conorbronsdon/avoid-ai-writing

Skill that audits and rewrites content to remove AI writing patterns. Use it with your favorite agents including Claude Code, OpenClaw, Codex, and Hermes.

Repository: https://github.com/conorbronsdon/avoid-ai-writing
Canonical: https://ross.abutalabs.com/products/avoid-ai-writing
Homepage: https://chainofthought.show/go/avoid-ai-writing
Language: JavaScript
License: MIT
License Family: permissive
Topics: ai-writing, claude, claude-code, llm, prompt-engineering, skill, writing
Last push: 2026-08-24T17:41:39+00:00

## Health v2 (maintenance only)
Score: 82/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 99, longevity 12
- inputs: {"age_days": 180, "days_push": 9, "days_rel": 9, "gap_med": 0.0, "n_releases_24m": 19}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3329, forks 297 (observed 2026-08-28T04:07:52.907680+00:00)

## What it is
A portable agent skill that audits and rewrites text to remove AI writing patterns ('AI-isms'). It supports detect-only, rewrite, and edit-in-place modes with optional voice profiles, and works with Claude Code, OpenClaw, Codex, Hermes, and other agentskills.io-compatible agents.

## Use cases
- remove AI writing patterns from my blog posts
- detect if text sounds like it was written by ChatGPT
- rewrite AI-generated content to sound human
- audit marketing copy for AI cliches
- edit prose files in place without changing human-written passages
- make my documentation sound less like a chatbot

## When to choose
- you publish prose and want to strip AI tells like 'Certainly!', 'delve', and promotional filler
- you use Claude Code or another agentskills.io-compatible agent and want a drop-in writing skill
- you want a detect-only scan of content you don't want altered
- you need targeted in-place edits that preserve already-human passages

## When to avoid
- you need to rewrite source code, configuration, or structured data - it refuses those
- you want a standalone GUI or web app rather than an agent skill
- you need grammar or style checking beyond AI-pattern removal
- your agent doesn't support the agentskills.io skill format

## Facets
- artifact type: plugin
- maturity: active
- function: nlp, prompt-engineering, agent-framework
- domain: large-language-models, developer-tools
- platform: cli, cross-platform
- tags: ai-writing-detector, claude-code-skill, agentskills, text-rewriting, prose-editing, voice-profiles, natural-language-processing, ai-agents, nodejs

## Member repositories
- conorbronsdon/avoid-ai-writing (main) score 82

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:52.907680+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:41:44.319917+00:00, confidence not recorded.
  - readme: https://github.com/conorbronsdon/avoid-ai-writing (fetched 2026-08-28T04:07:52.907680+00:00, sha 1eae76807bde)
  - homepage: https://chainofthought.show/go/avoid-ai-writing (fetched 2026-08-29T09:34:50.463735+00:00, sha 3114f0a1a42f)
  - site_page: https://chainofthought.show/about (fetched 2026-08-29T09:34:50.472698+00:00, sha d55672e5bf26)
- Data as of 2026-08-30T08:39:29.467469+00:00.