dayour/a2swe/wikipedia-human-style-writing

Claude Code and agent skill by dayour/a2swe

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Use this skill whenever the user asks to write, rewrite, humanise, de-AI, or polish prose so it doesn't read as AI-generated — or to review a draft for signs of AI writing. Apply it before returning any substantial prose the user will publish.

Install

npx vskill@latest install dayour/a2swe/wikipedia-human-style-writing

SKILL.md

The same SKILL.md was published earlier as tedtschopp/cat-agent-skills/wikipedia-human-style-writing.

Wikipedia Human Style Writing

Write and revise prose so it does not carry the tell-tale signs of AI-generated text, using the patterns catalogued in Wikipedia's Signs of AI writing. The full pattern catalogue lives in references/ai-writing-tells.md — consult it whenever you need the specific words-to-watch lists, examples, or the era-by-era "AI vocabulary" breakdown.

Operating principles

  1. Signs, not sins. Every pattern below can appear in good human writing. The

giveaway is density and mechanical repetition, not a single instance. Target clusters, not isolated words.

  1. Fix the cause, not the symptom. Most tells are surface markers of a deeper

problem: vagueness, puffery, or unsupported claims. Restore the specific fact or cut the empty claim — don't just swap the flagged word and leave hollow content.

  1. Preserve the truth and the voice. Never invent or drop facts, figures,

quotes, dates, or sources. Keep the author's meaning, stance, and legitimate emphasis. Do not "de-AI" a draft into corporate blandness.

  1. Descriptive, not prescriptive. These words and shapes are overused, not

banned. Use judgment over find-and-replace.

Workflow

  1. Read the whole draft first; note the core message, key facts, and the intended

voice and audience.

  1. Sweep the draft against the tell categories in references/ai-writing-tells.md,

looking for clusters.

  1. Revise each cluster by fixing the underlying issue:
  • Replace generic praise with the specific, concrete fact

(regression-to-the-mean: "a revolutionary titan of industry" → the actual achievement).

  • Cut empty significance/legacy flourishes and trailing "-ing" analysis clauses.
  • Restore plain is/are/has in place of "serves as / stands as / boasts /

features".

  • Name a real source or delete a vague attribution ("experts argue", "observers

have noted").

  • Break up mechanical rule-of-three lists, "not just X but Y" parallelisms, and

templated "Challenges / Future prospects" wrap-ups.

  • Remove promotional/travel-brochure tone ("vibrant", "nestled", "rich tapestry",

"seamless").

  • Thin out an over-dense cluster of era-specific "AI vocabulary" words.
  1. Clean the formatting tells: sentence-case headings (not Title Case), sparing

boldface (not **bold lead-in:** on every list item), varied punctuation instead of space-surrounded em-dash overuse, no emoji-as-bullets, no stray markdown or copy-pasted smart-quote residue, and no "In conclusion / In summary" filler.

  1. Re-read against the original to confirm no meaning, fact, or nuance drifted.

Guardrails

  • Do not add, remove, or alter facts, numbers, quotes, or citations to make text

"sound less AI".

  • Do not strip emphasis or specificity that the source genuinely supports.
  • Do not flatten a distinctive human voice into neutral mush — the goal is natural,

specific, human prose, not blandness.

  • One or two flagged words are usually fine; don't over-correct isolated hits.

Output

Return the revised prose first, copy-ready. When a review was requested, or when useful, follow it with a short bulleted list of the notable tells you found and how you addressed them.

Reference

  • references/ai-writing-tells.md — the full field guide: every tell category with

words-to-watch, examples, the era-by-era AI-vocabulary breakdown, and formatting tells. Read the relevant section whenever you need detail beyond the summary above.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/dayour/a2swe/wikipedia-human-style-writing/badge)](https://verified-skill.com/skills/dayour/a2swe/wikipedia-human-style-writing)

Something wrong with this skill or its page? Tell us.