agentleFS
Sign inStart free
d-o-hubd-o-hub/github-template-ai-agents/.agents/skills/avoid-ai-writing/SKILL.md

avoid-ai-writing

Skill2 starsChanged 11 days agoMITView on GitHub

Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Supports detect-only, rewrite (default), and edit-in-place modes, voice profiles, and iterative convergence.

14 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use marketing-psychology, pptx and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • SentrySkill

    marketing-psychology

    When the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,' 'behavioral science,' 'why people buy,' 'decision-making,' or 'consumer behavior.' This skill provides 70+ mental models organized for marketing application.

    Also in 3 projects that use this

  • AnthropicSkill

    pptx

    Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.

    Also in 3 projects that use this

  • OpenAISkill

    brainstorming

    You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When asked to "humanize" or "clean up" AI-generated text.

    line 15
  2. Distinctive:

    Before publishing agent-generated READMEs, changelogs, or documentation.

    line 16
  3. Distinctive:

    When auditing content for statistical AI tells.

    line 17
  4. Very specific:

    blog: Default; all rules full strength.

    line 36
  5. Very specific:

    Convergence: If --iterate 2 is passed, repeat until no patterns remain (max 2 passes).

    line 50

“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Avoid AI Writing — Audit & Rewrite

You are editing content to remove AI writing patterns ("AI-isms") that make text sound machine-generated.

When to Use

  • When asked to "humanize" or "clean up" AI-generated text.
  • Before publishing agent-generated READMEs, changelogs, or documentation.
  • When auditing content for statistical AI tells.

Core Modes

  • rewrite (default): Flag AI-isms and rewrite text to fix them. Returns Issues, Rewritten text, What changed, and a Second-pass audit.
  • detect: Flag AI-isms only. No rewriting. Useful for CI/CD gates or audits.
  • edit: Edit a file in-place with minimal, targeted changes using the Edit tool.

Voice Profiles (Optional)

Personas are canonical in voice-profiles — see that skill for definitions. Pass the chosen profile name (casual, professional, technical, warm, blunt) with the rewrite request instead of redefining personas here.

Context Profiles

Adjusts rule strictness for specific audiences.

  • linkedin: Social-first; relaxed on formatting, strict on P0 credibility killers.
  • blog: Default; all rules full strength.
  • technical-blog: Technical terms (robust, leverage, etc.) exempt; strict prose rules.
  • investor-email: Extra strict on promotional language and significance inflation.
  • docs: Clarity over voice; relaxed on hedging and copula avoidance.
  • casual: Slack/DM style; P0 credibility killers only.

Instructions

  1. Audit: Identify AI-isms using the references/patterns.md catalog.
  2. Apply Profile: Adjust strictness based on context and tone based on voice.
  3. Execute Mode:
    • rewrite: Return audit, full rewrite, change summary, and second-pass audit.
    • detect: Return severity-grouped issues (P0/P1/P2) and assessment.
    • edit: Apply minimal Edit tool changes to target file; return edit report.
  4. Convergence: If --iterate 2 is passed, repeat until no patterns remain (max 2 passes).

Severity Tiers

  • P0 — Credibility killers: Cutoff disclaimers, chatbot artifacts, vague attributions.
  • P1 — Obvious AI smell: Word-list violations, template phrases, "Let's" openers.
  • P2 — Stylistic polish: Generic conclusions, uniform length, transition overuse.

Rationalizations

RationalizationReality
"AI writing is grammatically perfect, so it's fine."Perfection is a tell; natural human writing has varied rhythm and personality.
"I can just ask the LLM to 'sound human'."One-shot "sound human" prompts are vibes-based; this skill uses a structured audit.
"This will flag non-native speakers."Patterns are signals, not proof. Use judgment and pair with context.

Red Flags

  • Sanding away all personality in pursuit of "clean" prose (creating new uniformity).
  • Rewriting quoted material or code blocks.
  • Ignoring the Second-pass audit (patterns often survive the first edit).

References

  • references/patterns.md — Exhaustive catalog of AI patterns and vocabulary.

See Also

  • ui-ux-optimize — For optimizing UI/UX specific copy and layouts.
  • readme-best-practices — For documentation structure and discovery.

Voice & Context

  • Default: professional + blog
  • Reference: voice-profiles skill for definitions and auto-detection.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free