{"id":51696948,"url":"https://github.com/AIScientists-Dev/academic-humanizer","last_synced_at":"2026-07-16T17:01:14.988Z","repository":{"id":366373200,"uuid":"1275268652","full_name":"AIScientists-Dev/academic-humanizer","owner":"AIScientists-Dev","description":"Remove AI-writing patterns from academic manuscripts while preserving scholarly voice and matching claims to evidence. Forks blader/humanizer; adds an academic layer.","archived":false,"fork":false,"pushed_at":"2026-06-21T13:38:20.000Z","size":28,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-21T15:23:13.510Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AIScientists-Dev.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-06-20T13:23:52.000Z","updated_at":"2026-06-21T13:38:24.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/AIScientists-Dev/academic-humanizer","commit_stats":null,"previous_names":["aiscientists-dev/academic-humanizer"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/AIScientists-Dev/academic-humanizer","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AIScientists-Dev%2Facademic-humanizer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AIScientists-Dev%2Facademic-humanizer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AIScientists-Dev%2Facademic-humanizer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AIScientists-Dev%2Facademic-humanizer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AIScientists-Dev","download_url":"https://codeload.github.com/AIScientists-Dev/academic-humanizer/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AIScientists-Dev%2Facademic-humanizer/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35551282,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-07-16T02:00:06.687Z","response_time":83,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2026-07-16T06:00:31.865Z","updated_at":"2026-07-16T17:01:14.977Z","avatar_url":"https://github.com/AIScientists-Dev.png","language":null,"funding_links":[],"categories":["🧠 Agent Skills","Documentation and Writing Skills"],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\n\u003cimg src=\"assets/banner.svg\" alt=\"Academic Humanizer: personalized editing for AI-assisted academic drafts, keeping your voice and every claim, number, and citation intact\" width=\"860\"\u003e\n\n[![license](https://img.shields.io/badge/license-MIT-2f8f57?style=flat-square)](LICENSE)\n\u0026nbsp;![version](https://img.shields.io/badge/version-0.3.2-2f8f57?style=flat-square)\n\u0026nbsp;![skill](https://img.shields.io/badge/skill-papers_and_grant_proposals-1c1a15?style=flat-square)\n\u0026nbsp;![built by](https://img.shields.io/badge/built_by-NSF,_CAREER,_NIH_R01-555?style=flat-square)\n\n\u003c/div\u003e\n\n## Why we built this\n\nSome of us write a lot of papers and grant proposals, and our team started using AI to help with\ndrafts. The problem is that AI-assisted drafts come out generic and verbose, with \"In recent years...\"\nopeners, inflated phrasing, and over-long sentences. They also drift from the author's own voice and\nlose the precision scholarship depends on.\n\nThere are tools called \"humanizers,\" but they are built for blogs and marketing. Run one on a paper or\nan NSF proposal and it flattens the precision along with everything else. The careful wording academic\nwriting depends on is the first thing to go.\n\nSo we put together our own. To calibrate it, we had the AI compare its own drafts with our team's\naccepted papers and funded proposals, and we went through the differences by hand. It is nothing fancy,\nand it is not about gaming review, defeating detectors, or adding fake novelty. We wanted AI-assisted\ndrafts to read clearly and in the author's own voice, with the numbers, citations, and claims left\nexactly as written.\n\n## Ethics and disclosure\n\nThis is an editing aid for clarity and voice, calibrated to an author's own prior accepted work. It does\nnot generate findings, invent data, or change citations, and it is not designed to evade AI-use\ndetection. Using it does not remove your obligation to disclose AI assistance: always follow the\ndisclosure policy of the venue you submit to.\n\n## See it work\n\n\u003e [!CAUTION]\n\u003e **Before** (a generic AI draft):\n\u003e\n\u003e In recent years, continual learning has attracted increasing attention and achieved remarkable\n\u003e success. However, existing methods still face crucial challenges. In this proposal, we propose a novel\n\u003e framework that leverages cutting-edge techniques to delve into these intricate problems, paving the way\n\u003e for a transformative paradigm that will revolutionize the field.\n\n\u003e [!TIP]\n\u003e **After** (clear, in the author's voice, with claims tied to evidence):\n\u003e\n\u003e Continual learning matters, but today's methods stay empirical and their principles are unclear. That\n\u003e limits reliability and progress. This proposal builds a principled framework on three fronts:\n\u003e adaptation, soft supervision, and cross-domain knowledge. We demonstrate it on autonomous driving and\n\u003e network management.\n\n**More before/after passes** are in [`examples/before-after.md`](examples/before-after.md): a general\nexample, an NIH Specific Aims page, and a funded NSF CAREER summary.\n\n---\n\n## What it does\n\n- **Sharpens clarity and voice:** trims generic AI phrasing (\"paves the way\", \"extensive experiments\", \"to the best of our knowledge\", \"In recent years...\", delve/underscore/tapestry, rule-of-three, very long sentences, em-dashes) and brings the draft closer to the author's own style.\n- **Keeps claims tied to evidence:** no verb stronger than the data (`prove` → `show empirically`), and\n  vague magnitudes become attributed ranges.\n- **Leaves real scholarship alone:** evidence-tied hedging, passive voice where it fits, `we`,\n  definitions, symbols, and every citation. It doesn't change a number or a reference.\n- **Has a separate mode for grant proposals (NSF, NIH):** it keeps the vision a paper would trim, and\n  spends most of the effort on the first pages, since that's what reviewers score.\n\n## Install\n\n```bash\ngit clone https://github.com/AIScientists-Dev/academic-humanizer ~/.claude/skills/academic-humanizer\n```\n\nIt is a plain `SKILL.md` plus examples, so it also runs as a skill or system prompt for **Codex** and\n**MorphMind**. Point your agent at `SKILL.md`.\n\n## Use\n\n```\n/academic-humanizer\n[paste a section, or point at main.tex]\n# optionally: \"match my voice from prior_paper.pdf; target venue: ICLR\"\n```\n\n## Make it yours\n\nThe rules here reflect one group's voice. Fork the repo and adapt them to your own: point it at a few of\nyour past papers, keep the checks that fit your field, and adjust the rest. It is meant to be\npersonalized, not a one-size-fits-all filter.\n\n## How it works\n\nSix layers: general AI-tell catalog → academic-specific tells → preserve scholarly conventions →\nclaim↔evidence matching → voice/venue calibration → funding-proposal mode (NSF/NIH structure,\nfirst-page primacy, claim↔feasibility). The audit→rewrite loop is defined in [`SKILL.md`](SKILL.md).\n\n## References\n\nLayer 6 distills the *stable* structure of NSF and NIH proposals. For current, binding requirements\n(page limits, formatting, deadlines), consult the source:\n\n- NSF: [Proposal \u0026 Award Policies \u0026 Procedures Guide (PAPPG)](https://www.nsf.gov/policies/pappg)\n- NSF: [CAREER program](https://new.nsf.gov/funding/opportunities/career-faculty-early-career-development-program)\n- NIH: [Write Your Application](https://grants.nih.gov/grants/how-to-apply-application-guide/format-and-write/write-your-application.htm) (Specific Aims, Significance, Innovation, Approach)\n\n## Acknowledgments\n\n- **[blader/humanizer](https://github.com/blader/humanizer)** (MIT). *Focus:* removing general\n  AI-writing patterns for blog, casual, and encyclopedic text. This skill reuses its general AI-tell\n  catalog (Layer 1) and extends it for academic prose.\n- **[koaeraser/ARMS](https://github.com/koaeraser/ARMS)**. *Focus:* an autonomous pipeline for\n  statistics/methodology research papers (idea → validated, revised manuscript). A complementary,\n  broader-scope project that informed the claim-evidence and numerical-precision emphasis here.\n\nThis skill is the narrower piece: a single-purpose **editing pass** that sharpens clarity and matches\nclaims to evidence while preserving the author's scholarly voice.\n\n## License\n\nMIT.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FAIScientists-Dev%2Facademic-humanizer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FAIScientists-Dev%2Facademic-humanizer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FAIScientists-Dev%2Facademic-humanizer/lists"}