{"data":{"slug":"blader-humanizer","name":"humanizer","tagline":"A tool to remove signs of AI-generated text","github_url":"https://github.com/blader/humanizer","owner":"blader","repo":"humanizer","owner_avatar_url":"https://avatars.githubusercontent.com/u/1672?v=4","primary_language":"Python","stars":33808,"forks":3049,"topics":["agent-skills","ai-writing","claude-code","codex","cursor","prompt-engineering","writing-tools"],"archived":false,"github_pushed_at":"2026-07-22T06:26:25+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/blader-humanizer","markdown_url":"https://www.graphcanon.com/tools/blader-humanizer.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/blader-humanizer","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=blader-humanizer","description":"Agent skill that removes signs of AI-generated writing from text","homepage_url":"https://skills.sh/blader/humanizer","license":"MIT","open_issues":24,"watchers":200,"ai_summary":"humanizer removes telltale signs that writing was generated by an AI and can personalize the output to match specific writing styles","readme_excerpt":"# Humanizer\n\n\n\nA 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.\n\n## Installation\n\n### Skills CLI\n\nInstall globally with the cross-agent skills CLI so Humanizer is available in every project:\n\n```bash\nnpx skills add blader/humanizer --global\n```\n\nUpdate an existing install:\n\n```bash\nnpx skills update humanizer --global\n```\n\nTo install globally into every supported agent harness:\n\n```bash\nnpx skills add blader/humanizer --global --agent '*'\n```\n\nTo target one configured harness, pass its agent name:\n\n```bash\nnpx skills add blader/humanizer --global --agent <agent-name>\n```\n\nOmit `--global` for a project-local install that can be committed and shared with collaborators. Start a new agent session or reload skills after installation.\n\n### Claude Code plugin\n\nClaude Code users can also install Humanizer as a plugin:\n\n```\n/plugin marketplace add blader/humanizer\n/plugin install humanizer@humanizer\n```\n\nThe skill is then invoked as `/humanizer:humanizer`.\n\n### Manual\n\nAny agent harness can use the skill directly because the runtime artifact is `SKILL.md`. Install it wherever your harness expects skill directories, or copy `SKILL.md` into an existing skill folder.\n\nFor example:\n\n```bash\ngit clone https://github.com/blader/humanizer.git /path/to/your/skills/humanizer\n```\n\nOr, if you already have this repo cloned:\n\n```bash\nmkdir -p /path/to/your/skills/humanizer\ncp SKILL.md /path/to/your/skills/humanizer/\n```\n\n## Usage\n\nInvoke the skill however your agent harness exposes installed skills. Common forms include a slash command or a direct request:\n\n```\n/humanizer\n\n[paste your text here]\n```\n\n```\nPlease humanize this text: [your text]\n```\n\nPoint it at a file and the skill rewrites it in place:\n\n```\nHumanize the prose in docs/launch-post.md\n```\n\n### Voice Calibration\n\nTo match your personal writing style, provide a sample of your own writing:\n\n```\n/humanizer\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```\n\nThe skill will analyze your sentence rhythm, word choices, and quirks, then apply them to the rewrite instead of producing generic \"clean\" output.\n\n## Overview\n\nBased on [Wikipedia's \"Signs of AI writing\"](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing) guide, maintained by WikiProject AI Cleanup. This comprehensive guide comes from observations of thousands of instances of AI-generated text.\n\nThe skill also includes a final \"obviously AI generated\" audit pass and a second rewrite, to catch lingering AI-isms in the first draft.\n\nRewrites 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.\n\n### Key Insight from Wikipedia\n\n> \"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.\"\n\n## 33 Patterns Detected (with Before/After Examples)\n\n### Content Patterns\n\n| # | Pattern | Before | After |\n|---|---------|--------|-------|\n| 1 | **Significance inflation** | \"marking a pivotal moment in the evolution of...\" | \"was established in 1989 as part of a wider decentralization\" |\n| 2 | **Notability name-dropping** | \"cited in NYT, BBC, FT, and The Hindu\" | Trim the list; keep only sourced context |\n| 3 | **Superficial -ing analyses** | \"symbolizing... reflecting... showcasing...\" | Remove, or keep only what the source supports |\n| 4 | **Promotional language** | \"nestled within the breathtaking region\" | \"is a town in the Gonder region\" |\n| 5 | **Vague attributions** | \"Experts believe it plays a crucial role\" | Name a real source or cut the claim |\n| 6 | **Formulaic challenges** | \"Despite challenges... continues to thrive\" | Keep the s","github_created_at":"2026-01-18T05:30:15+00:00","created_at":"2026-07-11T23:49:25.319702+00:00","updated_at":"2026-08-06T06:01:54.144248+00:00","categories":[{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"}],"tags":[{"slug":"ai-text-correction","name":"ai text correction"},{"slug":"text-polishing","name":"text polishing"},{"slug":"voice-matching-for-text","name":"voice matching for text"}],"trust":{"provenance":{"is_fork":false,"github_id":1136666433,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-06T06:01:52.844Z","maintenance":{"label":"Active","score":82,"methodology":"github_public_v1","releases_90d":2,"days_since_push":14,"last_release_at":"2026-07-22T06:26:26Z"},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T23:49:27.712Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-06T06:01:53.464Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-08-06T06:01:53.464Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-08-06T06:01:53.464Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need to make AI-generated content more human-like without losing its original meaning or intent.","If specific AI-isms identified in your document are known and need to be targeted directly, as humanizer uses a comprehensive list derived from Wikipedia's guide on signs of AI writing."],"when_not_to_use":["When the exact structure, tone, or style of the AI text is intentionally maintained for particular purposes such as showcasing technological output.","If the content requires legal review to ensure it adheres strictly to its original form without alterations that could change meaning or implications inadvertently."],"source":"enrich:decision_facts","observed_at":"2026-07-17T13:07:22.714Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"humanizer is a tool designed to remove signs that identify text was generated by an AI system. It can be personalized using samples of the user's own writing."}]}}