[{"data":1,"prerenderedAt":4},["ShallowReactive",2],{"readme:humanizer":3},"\u003Ch1>Humanizer\u003C\u002Fh1>\n\u003Cp>\u003Ca href=\"https:\u002F\u002Fskills.sh\u002Fblader\u002Fhumanizer\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fskills.sh\u002Fb\u002Fblader\u002Fhumanizer\" alt=\"skills.sh installs\" \u002F>\u003C\u002Fa>\u003C\u002Fp>\n\u003Cp>A portable agent skill that removes signs of AI-generated writing from text, making it sound more natural and human. It is plain Markdown, so it can run in any harness that supports skill-style instructions.\u003C\u002Fp>\n\u003Ch2>Installation\u003C\u002Fh2>\n\u003Ch3>Skills CLI\u003C\u002Fh3>\n\u003Cp>Install globally with the cross-agent skills CLI so Humanizer is available in every project:\u003C\u002Fp>\n\u003Cpre>\u003Ccode class=\"language-bash\">npx skills add blader\u002Fhumanizer --global\n\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Cp>Update an existing install:\u003C\u002Fp>\n\u003Cpre>\u003Ccode class=\"language-bash\">npx skills update humanizer --global\n\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Cp>To install globally into every supported agent harness:\u003C\u002Fp>\n\u003Cpre>\u003Ccode class=\"language-bash\">npx skills add blader\u002Fhumanizer --global --agent '*'\n\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Cp>To target one configured harness, pass its agent name:\u003C\u002Fp>\n\u003Cpre>\u003Ccode class=\"language-bash\">npx skills add blader\u002Fhumanizer --global --agent <agent-name>\n\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Cp>Omit \u003Ccode>--global\u003C\u002Fcode> for a project-local install that can be committed and shared with collaborators. Start a new agent session or reload skills after installation.\u003C\u002Fp>\n\u003Ch3>Claude Code plugin\u003C\u002Fh3>\n\u003Cp>Claude Code users can also install Humanizer as a plugin:\u003C\u002Fp>\n\u003Cpre>\u003Ccode>\u002Fplugin marketplace add blader\u002Fhumanizer\n\u002Fplugin install humanizer@humanizer\n\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Cp>The skill is then invoked as \u003Ccode>\u002Fhumanizer:humanizer\u003C\u002Fcode>.\u003C\u002Fp>\n\u003Ch3>Manual\u003C\u002Fh3>\n\u003Cp>Any agent harness can use the skill directly because the runtime artifact is \u003Ccode>SKILL.md\u003C\u002Fcode>. Install it wherever your harness expects skill directories, or copy \u003Ccode>SKILL.md\u003C\u002Fcode> into an existing skill folder.\u003C\u002Fp>\n\u003Cp>For example:\u003C\u002Fp>\n\u003Cpre>\u003Ccode class=\"language-bash\">git clone https:\u002F\u002Fgithub.com\u002Fblader\u002Fhumanizer.git \u002Fpath\u002Fto\u002Fyour\u002Fskills\u002Fhumanizer\n\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Cp>Or, if you already have this repo cloned:\u003C\u002Fp>\n\u003Cpre>\u003Ccode class=\"language-bash\">mkdir -p \u002Fpath\u002Fto\u002Fyour\u002Fskills\u002Fhumanizer\ncp SKILL.md \u002Fpath\u002Fto\u002Fyour\u002Fskills\u002Fhumanizer\u002F\n\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Ch2>Usage\u003C\u002Fh2>\n\u003Cp>Invoke the skill however your agent harness exposes installed skills. Common forms include a slash command or a direct request:\u003C\u002Fp>\n\u003Cpre>\u003Ccode>\u002Fhumanizer\n\n[paste your text here]\n\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Cpre>\u003Ccode>Please humanize this text: [your text]\n\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Cp>Point it at a file and the skill rewrites it in place:\u003C\u002Fp>\n\u003Cpre>\u003Ccode>Humanize the prose in docs\u002Flaunch-post.md\n\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Ch3>Voice Calibration\u003C\u002Fh3>\n\u003Cp>To match your personal writing style, provide a sample of your own writing:\u003C\u002Fp>\n\u003Cpre>\u003Ccode>\u002Fhumanizer\n\nHere's a sample of my writing for voice matching:\n[paste 2-3 paragraphs of your own writing]\n\nNow humanize this text:\n[paste AI text to humanize]\n\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Cp>The skill will analyze your sentence rhythm, word choices, and quirks, then apply them to the rewrite instead of producing generic \"clean\" output.\u003C\u002Fp>\n\u003Ch2>Overview\u003C\u002Fh2>\n\u003Cp>Based on \u003Ca href=\"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FWikipedia:Signs_of_AI_writing\" rel=\"nofollow ugc noopener\">Wikipedia's \"Signs of AI writing\"\u003C\u002Fa> guide, maintained by WikiProject AI Cleanup. This comprehensive guide comes from observations of thousands of instances of AI-generated text.\u003C\u002Fp>\n\u003Cp>The skill also includes a final \"obviously AI generated\" audit pass and a second rewrite, to catch lingering AI-isms in the first draft.\u003C\u002Fp>\n\u003Cp>Rewrites follow a no-fabrication rule: they never add facts, names, dates, or citations that aren't in the source text. Specificity has to come from the source or the author, not from the rewrite.\u003C\u002Fp>\n\u003Ch3>Key Insight from Wikipedia\u003C\u002Fh3>\n\u003Cblockquote>\n\u003Cp>\"LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases.\"\u003C\u002Fp>\n\u003C\u002Fblockquote>\n\u003Ch2>33 Patterns Detected (with Before\u002FAfter Examples)\u003C\u002Fh2>\n\u003Ch3>Content Patterns\u003C\u002Fh3>\n\u003Ctable>\n\u003Cthead>\n\u003Ctr>\n\u003Cth>#\u003C\u002Fth>\n\u003Cth>Pattern\u003C\u002Fth>\n\u003Cth>Before\u003C\u002Fth>\n\u003Cth>After\u003C\u002Fth>\n\u003C\u002Ftr>\n\u003C\u002Fthead>\n\u003Ctbody>\u003Ctr>\n\u003Ctd>1\u003C\u002Ftd>\n\u003Ctd>\u003Cstrong>Significance inflation\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>\"marking a pivotal moment in the evolution of...\"\u003C\u002Ftd>\n\u003Ctd>\"was established in 1989 as part of a wider decentralization\"\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>2\u003C\u002Ftd>\n\u003Ctd>\u003Cstrong>Notability name-dropping\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>\"cited in NYT, BBC, FT, and The Hindu\"\u003C\u002Ftd>\n\u003Ctd>Trim the list; keep only sourced context\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>3\u003C\u002Ftd>\n\u003Ctd>\u003Cstrong>Superficial -ing analyses\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>\"symbolizing... reflecting... showcasing...\"\u003C\u002Ftd>\n\u003Ctd>Remove, or keep only what the source supports\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>4\u003C\u002Ftd>\n\u003Ctd>\u003Cstrong>Promotional language\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>\"nestled within the breathtaking region\"\u003C\u002Ftd>\n\u003Ctd>\"is a town in the Gonder region\"\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>5\u003C\u002Ftd>\n\u003Ctd>\u003Cstrong>Vague attributions\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>\"Experts believe it plays a crucial role\"\u003C\u002Ftd>\n\u003Ctd>Name a real source or cut the\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftbody>\u003C\u002Ftable>\n",1786232076462]