#writing
GitHub repositories that have self-applied the topic "writing" — a creator-tagged metadata that surfaces how AI projects describe themselves.
REPOS Repos for #writing (top 23 by stars)
仕事の日本語を、読みやすくわかりやすく書く・直すための Agent Skill です。
dbhq-uk/verve-skill#1316311605Agent skill that strips AI tells from prose and puts a human voice back, pitched at the reader it is for. British English by default. Works in Claude Code, Codex and any agent the Skills CLI reaches. Free, MIT, no network, no detector evasion.
Lucasli6833/slop-copDetect AI-generated language patterns in your codebase with this Claude Code skill to ensure human-quality prose.
oFrusch/ste-guardIn a battle against Claudlish, this just might be a pretty good defense.
2youg1/RefRain specailm5/arabic-writing-skillAgent skill for authentic Arabic writing: strips English calques and translated phraseology (العرنجية) from Arabic text. Works with Claude Code, Codex, Antigravity, VS Code. Based on Ahmad Al-Ghamdi's treatise — مهارة الكتابة العربية الفصيحة ونبذ العرنجية
derekcedarbaum2/content-machineAn AI-native content pipeline for Claude Code: Oracle idea-mining, interview-panel extraction, voice-locked drafting, a 9/10 writers-council gate, and a lessons loop. Rebuilt from Alex Lieberman's content machine (How I AI).
dharmawan-id/anti-ai-slopAn anti-AI-slop writing standard: catch and rewrite the patterns that make text read as AI-generated. Bilingual English + Indonesian, agent-executable (MCP server + skill + CLI).
Wike-CHI/ai-winter-and-spring《智能之冬与智能之春:专家系统、互联网、大模型与 Agent 的四十年战争》——一部用多智能体协作工程化方法写就的 AI 史。连载中。
ELhadratiOth/agent-antislopTwo agent skills that stop generated prose and generated UI from looking generated. Works with Claude Code, Codex CLI, and Cursor. npx agent-antislop
rightin2/shape-rotateA Claude skill that makes stuck arguments, drafts, plans and decisions click into place: visualize every piece, rotate the shape until it locks, then rebuild.
swayamdhawan/anti-ai-writing-skillAI skill that removes the machine-made tells from your writing: vague claims, 'not X but Y' reframes, hype words, fake metaphors. Works with Claude Code, Cowork, Codex, ChatGPT, Grok.
shaysega/maybe-dont-post-thatA Claude skill that pressure-tests and rewrites leadership communication before it ships - catches posts that read as contemptuous, keeps the edge, drops the own-goals.
JeanStory/deslopDeterministic, zero-dependency detector for AI-generated 'slop' tells in prose.
shaowen-ye/evidence-calibrated-writingPrevent defense-first caveats and evidence-free grandiosity in Claude and Codex writing.
ChristianNHill/chrisnizerIf you want to sound more human, or really, more like me: a writing linter tuned to my voice, as a Claude Code skill
Guilou001/skill-redaction-pedagogiqueDeux guides de rédaction pour expliquer les termes, montrer d'où viennent les chiffres et aider le lecteur à comprendre les tableaux, sans perdre la précision.
bryankwandou/rangkaKerangka dulu, baru menulis. Skill terbuka untuk Claude dan model AI lain.
sgbaird/cringe-filterStrip AI tells from prose: a linter, scorer and prompt builder measured on 1.9M words of human vs. Claude writing
micheledalsanto/italian-masterL'italiano di chi scrive per mestiere, genere per genere e con i soli fatti ricevuti. Agent skill for Claude and Codex: natural Italian writing, measured on real Italian texts.
tns-research/slopcheck-frRepère les tics d'écriture IA dans vos textes en français et propose une correction. Déterministe, hors ligne, skill pour Claude Code, Codex, Cursor, Gemini, Grok.
dbhq-uk/verve-skillAgent skill that strips AI tells from prose and puts a human voice back, pitched at the reader it is for. British English by default. Works in Claude Code, Codex and any agent the Skills CLI reaches. Free, MIT, no network, no detector evasion.
adsorgcn/WorkBuddyiLang 专家与技能的 GitHub 安装源,海外版 WorkBuddy 可直接装:公众号爆文结构专家 v2.0(素材进稿子出,12 项自查,内置去 AI 味)· iLang experts & skills for WorkBuddy, installable from GitHub
RELATED Other topics · full topics ranking →
#claude-code
2,838#ai-agents
2,208#llm
1,699#claude
1,484#mcp
1,376#python
1,357#developer-tools
1,237#ai
1,038#codex
1,005Aggregated by case-insensitive match against topics_json of each repo's latest content snapshot. methodology