Menu

#351 by GitHub stars

AIScientists-Dev/academic-humanizer

Improve the clarity and voice of AI-assisted academic writing (papers, theses, rebuttals) and funding proposals (NSF Project Summary/Description, NIH Specific Aims): preserve scholarly conventions, match claims to evidence (and, for proposals, claims to feasibility), and match the author's own voice

ResearchWriting

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

SKILL.md

Week of Oct 26, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

94b88b23703b → 94b88b23703b

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 94b88b23703bed7df507acae7d6d5876209a0cdf

3.6kGitHub stars
537stars in 7 days
1skill in this repository
0commits in 30 days

Heat

7.4
  • Star growth, last 7 daysAhead of 99% of tracked repositories
  • Star growth, last 24 hoursAhead of 100% of tracked repositories
  • Rank movement, last 7 daysAhead of 97% of tracked repositories
  • Commits, last 30 daysAhead of 0% of tracked repositories
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekAhead of 0% of tracked repositories

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Aug 2, 2026Nov 6, 20263,607

Individual skills in this repository

How it works

academic-humanizer

When your agent uses it

Improve the clarity and voice of AI-assisted academic writing (papers, theses, rebuttals) and funding proposals (NSF Project Summary/Description, NIH Specific Aims): preserve scholarly conventions, match claims to evidence (and, for proposals, claims to feasibility), and match the author's own voice. It never changes a number, result, or citation, and it is not for evading AI-use disclosure. Use when editing AI-assisted academic prose or grant proposals.

What it loads into context

Frontmatter

156 tokens

Always available to the agent

SKILL.md

3,961 tokens

When the skill is activated

Reference documents

2,917 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. When to use
  2. Core principle
  3. Process
  4. Layer 1: General AI-tell catalog
  5. Layer 2: Academic AI tells (remove or fix)
  6. Layer 3: Preserve these (do NOT over-correct)
  7. Layer 4: Claim-evidence discipline
  8. Layer 5: Voice and venue matching
  9. Layer 6: Funding-proposal mode (NSF, NIH)
  10. Output

Files

  • .gitignoreasset10 bytes
  • LICENSEasset890 bytes
  • README.mddoc6,205 bytes
  • SKILL.mdcore16,779 bytes
  • assets/banner.svgasset1,374 bytes
  • assets/rednote-zh.pngasset106,124 bytes
  • assets/rednote-zh.svgasset1,649 bytes
  • assets/x-en.pngasset169,099 bytes
  • assets/x-en.svgasset1,587 bytes
  • examples/before-after.mddoc6,949 bytes

No excerpt is shown for this license. Read the source on GitHub.

View the complete source on GitHub

Skills included

  • academic-humanizer

Repository facts

License
No license detected
Created
Jun 20, 2026
Last pushed
Jul 3, 2026
Forks
268
Open issues
4
Project activity
Slowing

Rank over the last 12 weeks

Now #351 · best #351 · up 122 in 30 days

  1. #382 on Nov 1
  2. #373 on Nov 2
  3. #367 on Nov 3
  4. #366 on Nov 4
  5. #352 on Nov 5
  6. #351 since Nov 6
83 earlier periods
  1. #657 on Aug 2
  2. #609 on Aug 7
  3. #602 on Aug 8
  4. #604 on Aug 9
  5. #623 on Aug 10
  6. #621 on Aug 11
  7. #605 on Aug 12
  8. #606 on Aug 13
  9. #592 on Aug 14
  10. #573 on Aug 15
  11. #575 on Aug 16
  12. #567 on Aug 17
  13. #578 on Aug 18
  14. #560 on Aug 19
  15. #556 on Aug 20
  16. #557 on Aug 21
  17. #537 on Aug 22
  18. #553 on Aug 23
  19. #549 on Aug 24
  20. #557 on Aug 25
  21. #544 on Aug 26
  22. #552 on Aug 27
  23. #548 on Aug 28
  24. #519 on Aug 29
  25. #502 on Aug 30
  26. #516 on Aug 31
  27. #515 on Sep 1
  28. #505 on Sep 2
  29. #507 on Sep 3
  30. #492 on Sep 4
  31. #489 on Sep 5
  32. #497 on Sep 6
  33. #498 on Sep 7
  34. #510 on Sep 8
  35. #500 on Sep 9
  36. #501 on Sep 10
  37. #495 on Sep 11
  38. #492 on Sep 12
  39. #489 on Sep 13
  40. #499 on Sep 14
  41. #491 on Sep 15
  42. #499 on Sep 16
  43. #493 on Sep 17
  44. #496 on Sep 18
  45. #475 on Sep 19
  46. #483 on Sep 20
  47. #484 on Sep 21
  48. #492 on Sep 22
  49. #484 on Sep 23
  50. #474 from Sep 24 to Sep 25
  51. #468 on Sep 26
  52. #482 on Sep 27
  53. #488 on Sep 28
  54. #494 on Sep 29
  55. #489 on Sep 30
  56. #481 on Oct 1
  57. #478 on Oct 2
  58. #467 on Oct 3
  59. #460 on Oct 4
  60. #468 on Oct 5
  61. #479 on Oct 6
  62. #473 from Oct 7 to Oct 8
  63. #471 on Oct 9
  64. #460 on Oct 10
  65. #454 on Oct 11
  66. #463 on Oct 12
  67. #454 on Oct 13
  68. #453 on Oct 14
  69. #451 on Oct 15
  70. #456 on Oct 16
  71. #445 on Oct 17
  72. #448 on Oct 18
  73. #447 on Oct 19
  74. #448 on Oct 20
  75. #446 on Oct 21
  76. #438 on Oct 22
  77. #429 on Oct 23
  78. #414 on Oct 24
  79. #431 on Oct 25
  80. #397 on Oct 28
  81. #393 on Oct 29
  82. #391 on Oct 30
  83. #386 on Oct 31

Before you install

Instructions only

Automated signals, not a guarantee

Checked Nov 2, 2026

Risk level changed on Oct 27, 2026

  • No broad tool permissions
  • No dangerous shell commands
  • 17 network referencesin 5 files: README.md:5 LICENSE:5 assets/banner.svg:1 and 2 more
  • No hidden or obfuscated text
  • No instruction overrides
  • No executable scripts
  • No access to secrets
  • No requests to vote in Hot
Show all 17 signals by file

LICENSE

  • Network accessline 5
    This work builds on "humanizer" by blader (https://github.com/blader/humanizer, MIT) and adopts
  • Network accessline 6
    standards from "ARMS" (https://github.com/koaeraser/ARMS); see the Acknowledgments in README.md.

README.md

  • Network accessline 5
    [![license](https://img.shields.io/badge/license-MIT-2f8f57?style=flat-square)](LICENSE)
  • Network accessline 6
     ![version](https://img.shields.io/badge/version-0.3.2-2f8f57?style=flat-square)
  • Network accessline 7
     ![skill](https://img.shields.io/badge/skill-papers_and_grant_proposals-1c1a15?style=flat-square)
  • Network accessline 8
     ![built by](https://img.shields.io/badge/built_by-NSF,_CAREER,_NIH_R01-555?style=flat-square)
  • Network accessline 72
    git clone https://github.com/AIScientists-Dev/academic-humanizer ~/.claude/skills/academic-humanizer
  • Network accessline 103
    - NSF: [Proposal & Award Policies & Procedures Guide (PAPPG)](https://www.nsf.gov/policies/pappg)
  • Network accessline 104
    - NSF: [CAREER program](https://new.nsf.gov/funding/opportunities/career-faculty-early-career-development-program)
  • Network accessline 105
    - 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)
  • Network accessline 109
    - **[blader/humanizer](https://github.com/blader/humanizer)** (MIT). *Focus:* removing general
  • Network accessline 110
    AI-writing patterns for blog, casual, and encyclopedic text. This skill reuses its general AI-tell   catalog (Layer 1) and extends it for academic prose. - **[koaeraser/ARMS](https://github.com/koaeraser/ARMS)**. *Focus:* an autonomous pipe
  • Network accessline 111
    catalog (Layer 1) and extends it for academic prose. - **[koaeraser/ARMS](https://github.com/koaeraser/ARMS)**. *Focus:* an autonomous pipeline for   statistics/methodology research papers (idea → validated, revised manuscript). A complemen
  • Network accessline 112
    - **[koaeraser/ARMS](https://github.com/koaeraser/ARMS)**. *Focus:* an autonomous pipeline for

assets/banner.svg

  • Network accessline 1
    <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 1200 360" font-family="Georgia, 'Times New Roman', serif">

assets/rednote-zh.svg

  • Network accessline 1
    <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 1080 1440" font-family="'PingFang SC','Hiragino Sans GB','Heiti SC','Microsoft YaHei',sans-serif">

assets/x-en.svg

  • Network accessline 1
    <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 1200 675" font-family="Georgia, 'Times New Roman', serif">

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 12 facts
  • Network access in prose of documentationREADME.md:5Low confidence
  • Network access in prose of documentationREADME.md:6Low confidence
  • Network access in prose of documentationREADME.md:7Low confidence
  • Network access in prose of documentationREADME.md:8Low confidence
  • Network access in code of documentationREADME.md:72Low confidence
  • Network access in prose of documentationREADME.md:103Low confidence
  • Network access in prose of documentationREADME.md:104Low confidence
  • Network access in prose of documentationREADME.md:105Low confidence
  • Network access in prose of documentationREADME.md:109Low confidence
  • Network access in prose of documentationREADME.md:110Low confidence
  • Network access in prose of documentationREADME.md:111Low confidence
  • Network access in prose of documentationREADME.md:112Low confidence

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md SKILL.md.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

You might also use

cLin-c/paper-skill

🎓 Claude Code skill — AI prompt library for academic paper writing, polishing, reviewing, translating and submitting to SCI/IEEE/Nature/TRO journals

140GitHub stars

huguryildiz/ieee-acm-paper-writing

Evidence-bounded skill for drafting, rewriting, humanizing, and auditing IEEE/ACM engineering manuscripts.

13GitHub stars

alfonso0512/research-writing-skill

🎓 AI 科研论文写作助手 - 30 个 Prompt 模板覆盖论文写作全流程。支持中英文翻译、润色、文献综述、投稿回复、基金申请等。

542GitHub stars

Michael-Jiahao-Zhang/game-the-llm-reviewer

Defend sound research against LLM reviewer bias through meaning-preserving rewrites.

219GitHub stars

heise3/academic-deai

Model-agnostic Chinese and English academic editing for the latest models across Agent platforms. Reduce formulaic prose while preserving evidence and author voice.

77GitHub stars

gxCaesar/open-research-skills

从选题到可复现发布：十个可独立安装的科研 agent skill —— 顶会/期刊论文、科研绘图、基金 proposal 撰写、方法迭代到 SOTA、冷审与代码数据发布。Ten installable agent skills for research…

63GitHub stars

Add this badge to your README

It updates every night and links to this page.

AIScientists-Dev/academic-humanizer: #351 on hotskills, 3.6k stars

[![AIScientists-Dev/academic-humanizer on hotskills](https://hotskills.dev/badge/aiscientists-dev-academic-humanizer.svg)](https://hotskills.dev/skill/aiscientists-dev-academic-humanizer/)