content-humanizer
Skill8.6k starsChanged 5 months agoGPL-2.0View on GitHub
分析一段内容或一个文件的"人味"(即像不像人类自然写出来的,AI 生成痕迹有多重),给出 0-100 量化打分,并在低于目标线(默认 80 分,用户可指定其他数值如90分)时在不改变原意的前提下改写到目标分数以上。触发条件:用户提到"人味"、"AI味"、"AI感"、"降AI率"、"去AI化"、"人性化改写"、"像人写的"、"过人工检测"、"过AI检测"、"让文章更自然"、"这段话是不是AI写的"、"帮我把这篇文章改得不像AI写的",或者给出一段文字/文件并希望知道"读起来自然不自然"、"会不会被认出是AI写的"。即使用户只说"这段话感觉很机器,帮我改一下"或"帮我看看这篇稿子像不像真人写的",也应使用本 skill。输出为 Markdown 报告,保存到当前项目 markdown/ 目录。
6 other projects use a version of this.
Trending
Quiet since September.about the whole repository
Most recently taken up by
- darkweb19/skillstheir own version, first seen Nov 8, 2026
- scayver/marketing-skillstheir own version, first seen Oct 13, 2026
- jtprogru/bear-skillstheir own version, first seen Aug 8, 2026
- Hassaan146/claude-skillstheir own version, first seen Jul 25, 2026
- Hussain-Elfalah/Agentic-Skillstheir own version, first seen Jun 4, 2026
- Getampz/Skillstheir own version, first seen Apr 21, 2026
Who's talking about digoal/blog
- tensorchord/pg_bestmatch.rs“feat: The support for Chinese doesn't seem very good yet. Here is a test document.”GitHub · Jun 25, 2024 · 1 reactions
- BigPengSays/awesome-creator-skills“candidate: daily-finance”GitHub · Sep 14, 2026
- liyupi/github-claw“📰 AI 科技日报 — 2026-05-16”GitHub · May 16, 2026
- liyupi/github-claw“📰 AI 科技日报 — 2026-04-21”GitHub · Apr 21, 2026
- BharatDBPG/BharatDBMS-PG“bug #16505: ssl_crl_file bug?”GitHub · Sep 17, 2025
The biggest 5 of 20 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 20
Talked about on GitHub (20 times).
On GitHub · 20
- Jun 25, 2024feat: The support for Chinese doesn't seem very good yet. Here is a test document. — tensorchord/pg_bestmatch.rs1 reaction · 1 comment
- Sep 14, 2026candidate: daily-finance — BigPengSays/awesome-creator-skills0 reactions
- May 16, 2026📰 AI 科技日报 — 2026-05-16 — liyupi/github-claw0 reactions
- Apr 21, 2026📰 AI 科技日报 — 2026-04-21 — liyupi/github-claw0 reactions
- Sep 17, 2025bug #16505: ssl_crl_file bug? — BharatDBPG/BharatDBMS-PG0 reactions
15 more on GitHub
- Mar 7, 2025PG参数autovacuum_naptime解析 — swrd/swrd.github.io0 reactions
- Feb 20, 2025PG参数maintenance_work_mem解析 — swrd/swrd.github.io0 reactions
- Jan 30, 2024PG database connection problem, causing server memory and load to be too high — blockscout/blockscout0 reactions · 2 comments
- Jan 26, 2024ERROR on PolarDB 11.9 — alitrack/duckdb_fdw0 reactions · 3 comments
- Oct 27, 2022explain cann't runout, when inner and outer join 48 tables. — duckdb/duckdb0 reactions · 7 comments
- May 14, 2020Fix Blog: digoal — ty4z2008/Qix0 reactions · 1 comment
- May 14, 2020Add Postgres Blog — dhamaniasad/awesome-postgres0 reactions · 3 comments
- Nov 11, 2019Add human annotations to dubious samples (round 1) — smola/language-dataset0 reactions · 7 comments
- Sep 25, 2019MySQL 为什么要这样优化 - WZQTSX — guevara/read-it-later0 reactions
- Sep 25, 2019MySQL 为什么要这样优化 - WZQTSX — guevara/read-it-later0 reactions
- Sep 25, 2019MySQL 为什么要这样优化 - WZQTSX — guevara/read-it-later0 reactions
- Jul 30, 2019install PostgreSQL11.4 on redhat linux 6.4 — fbirdzp/PostgreSQL0 reactions
- Apr 20, 2019Create ADDING AN INDEX CAN DECREASE SELECT PERFORMANCE.docx — postgres-cn/pg_articles0 reactions
- Nov 5, 2017数据透视之维度建模 — linhong88/-0 reactions
- Feb 28, 2017HI, i have an chinese version doc for vops, can add link? thank you. — postgrespro/vops0 reactions
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- Hassaan146/claude-skills★ 18same name
- scayver/marketing-skills★ 8same name
- Hussain-Elfalah/Agentic-Skills★ 2same name
- jtprogru/bear-skills★ 1same name
- darkweb19/skills★ 0same name
- Getampz/Skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository108 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- andres-freund-perspectiveSkill
- article-fact-checkerSkill
- article-to-podcast-scriptSkill
- a-stock-predictionSkill
- axiom-explainerSkill
- blog-cover-posterSkill
- buffettSkill
- daily-financeSkill
- database-foundation-course-writerSkill
- db-ai-github-paper-weekly-newsSkill
- digoal-perspectiveSkill
- digoal-read-think-writerSkill
- digoalSkill
- douban-book-notesSkill
- enterprise-future-planning-advisorSkill
- finance-beginner-explainerSkill
- finance-core-analysisSkill
- finance-explosive-articleSkill
- finance-weekly-outlookSkill
- financial-report-analysisSkill
- find-postgres-bugSkill
- future-planning-advisorSkill
- github-weekly-trendingSkill
- good-askSkill
- higher-order-article-writerSkill
- industry-chain-investment-analysisSkill
- industry-deep-explainerSkill
- industry-news-insightSkill
- investor-news-impactSkill
- job-advisorSkill
- karl-marx-perspectiveSkill
- logic-thinker-coachSkill
- luo-hongxian-perspectiveSkill
- mao-zedong-perspectiveSkill
- 微信公众号运营Skill
- market-opening-analystSkill
- multi-expert-analyzerSkill
- ni-haixia-perspectiveSkill
- opensourcefaqSkill
- open-source-project-articleSkill
- paper-interpretationSkill
- pgfaqSkill
- postgres-commit-history-articleSkill
- product-feature-tech-designSkill
- product-feature-tech-implementSkill
- product-multi-role-analysisSkill
- product-review-reportSkill
- product-tech-influence-articleSkill
- rational-red-blue-debateSkill
- retail-trading-manual-writerSkill
- multi-expert-analyzerSkill
- multi-expert-analyzerSkill
- multi-expert-analyzerSkill
- multi-expert-analyzerSkill
- article-fact-checkerSkill
- article-rewriterSkill
- a-stock-predictorSkill
- axiom-explainerSkill
- book-note-writerSkill
- The first 60 shown.
The file
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
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.

