Skip to content
Back to search

academic-writing-skills

AI-powered post-writing toolkit for academic papers — format validation, grammar/style polishing, de-AI editing, reference checking, and reviewer-style paper audits. 5 skills for LaTeX, Typst & PDF. Focused on enhancing existing text quality, not generating from scratch.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/bahayonghang/academic-writing-skills with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/bahayonghang/academic-writing-skills'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/bahayonghang-academic-writing-skills/badge.svg)](/listings/bahayonghang-academic-writing-skills)

HTML

<a href="/listings/bahayonghang-academic-writing-skills"><img src="/api/listings/bahayonghang-academic-writing-skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Install the repository with skills:

npx skills add bahayonghang/academic-writing-skills

Then open an applicable tool in your manuscript project and ask for the task in natural language. The root README is only a routing guide; the authoritative usage details live in each `SKILL.md` file and in the docs site.

The LaTeX loaders reject includes outside the project root. For installation alerts and `E-INCLUDE-BOUNDARY`, see the [installation guide](docs/installation.md#security-assessments).

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 182 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # Academic Writing Skills for Claude Code
  2. [中文版](README_CN.md)
  3. This collection of skills grew out of my day-to-day paper-writing workflow and
  4. has been iteratively refined over time. It may still have shortcomings or rough
  5. edges; if needed, please fork it and adapt it yourself.
  6. > I have recently been writing my dissertation and revising English papers,
  7. > so I will keep improving `latex-thesis-zh` and `latex-paper-en` based on
  8. > actual usage.
  9. > Note: `paper-audit` review reports are for reference only; please verify and
  10. > evaluate them yourself.
  11. >
  12. > Post-writing polish and validation for academic papers: format checks,
  13. > bibliography search and verification, grammar analysis, de-AI editing, and
  14. > experiment narrative review. Focused on improving existing drafts, not writing
  15. > papers from scratch.
  16. >
  17. > Recommended models (★ is most recommended): **★ Gemini 4 Carbon / Gemini 4 Argon · Claude Opus 5.5**
  18. >
  19. > Google's models have a good writing style, but they may have some
  20. > hallucinations when writing science and engineering papers. Review carefully.
  21. >
  22. > GPT models do not write like a person, and the defensive hedging is serious.
  23. > If you use one, watch both. After GPT has revised the text, scan it again
  24. > with another model, and read it yourself.
  25. >
  26. > Recommended platforms: **Claude Code · Pi · OMP (Oh My Pi)**
  27. ## Install
  28. Install the repository with skills:
  29. ```bash
  30. npx skills add bahayonghang/academic-writing-skills
  31. ```
  32. Then open an applicable tool in your manuscript project and ask for the task in
  33. natural language. The root README is only a routing guide; the authoritative
  34. usage details live in each `SKILL.md` file and in the docs site.
  35. The LaTeX loaders reject includes outside the project root. For installation
  36. alerts and `E-INCLUDE-BOUNDARY`, see the [installation guide](docs/installation.md#security-assessments).
  37. ## Choose A Skill
  38. | Skill | Use When | Main Inputs | Source Of Truth |
  39. | ----------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------- | ------------------------------ |
  40. | [`cover-letter`](academic-writing-skills/cover-letter/SKILL.md) | Generate, optimize, align-check, preflight, or journal-fit-check a submission cover letter against an existing LaTeX manuscript. | `.tex`, optional `.md` or `.tex` letter draft | `cover-letter/SKILL.md` |
  41. | [`paper-audit`](academic-writing-skills/paper-audit/SKILL.md) | Run reviewer-style critique, submission gates, blocker triage, revision roadmaps, journal-style reports, or re-audits. | `.tex`, `.typ`, `.pdf` | `paper-audit/SKILL.md` |
  42. | [`latex-paper-en`](academic-writing-skills/latex-paper-en/SKILL.md) | Work on existing English LaTeX conference or journal papers: compile, formatting, grammar, logic, sections, references, figures, tables, pseudocode, title, translation, or de-AI polish. | `.tex` | `latex-paper-en/SKILL.md` |
  43. | [`latex-thesis-zh`](academic-writing-skills/latex-thesis-zh/SKILL.md) | Work on existing Chinese LaTeX theses: compile diagnostics, GB/T 7714 references, chapter structure, bilingual captions and rendered figure/table layout, evidence-faithful abstracts, summaries, literature synthesis, engineering-application chapters, results analysis, Chinese inter-sentence expression, de-AI polish, and paragraph/subsection polish with revision checks. Point-by-point thesis review responses, revision forms, and coverage/evidence checks. | `.tex`; PDF/TXT/MD review reports | `latex-thesis-zh/SKILL.md` |
  44. | [`typst-paper`](academic-writing-skills/typst-paper/SKILL.md) | Work on existing English or Chinese Typst manuscripts: compile/export diagnostics, venue formatting, references, grammar, logic, tables, pseudocode, title, translation, or de-AI polish. | `.typ` | `typst-paper/SKILL.md` |
  45. | [`bib-search-citation`](academic-writing-skills/bib-search-citation/SKILL.md) | Search, filter, preview, export, or create LaTeX/Typst citation snippets from a local BibTeX or BibLaTeX library. | `.bib` | `bib-search-citation/SKILL.md` |
  46. | [`paper-writing-studio`](academic-writing-skills/paper-writing-studio/SKILL.md) | Polish or translate academic prose with an explicit Nature, IEEE, Elsevier, or neutral profile; report venue conflicts and missing evidence instead of guessing. | prose text, optional venue, journal, or domain | `paper-writing-studio/SKILL.md` |
  47. | [`academic-defense-beamer`](academic-writing-skills/academic-defense-beamer/SKILL.md) | Build a Chinese PhD/master thesis defense or pre-defense deck in Beamer or Typst Touying (simply-ysu-touying theme) with speaker notes, plus a presenter PDF for FerroStage or pympress, from an existing XeLaTeX thesis repository; extraction is read-only, and a fidelity quality gate checks figures, numbers, equations, tables, and publications against the thesis. | thesis LaTeX repository | `academic-defense-beamer/SKILL.md` |
  48. Opt-in checks only report local candidates: `check_consistency.py --governance` requires `--custom-terms`, `--abbreviation-style` is independent, and `check_style_zh.py --degree-wording` is off by default; without these flags the previous output stays unchanged.
  49. College number, equation, table-body, and Chinese-caption checks use `--school yanshan-ee-2025` on `check_style_zh.py`, `check_format.py`, `check_tables.py`, and `check_references.py`. The default and `--school generic` add no candidates, and there is no bare `yanshan` alias.
  50. Citation placement, repeated-citation pages, college bibliography prompts, and review progression density run only behind explicit flags: `check_references.py --author-cite` and `--repeat-cite` are independent and may combine with `--school`; `verify_bib.py --college-details` is legal only with `--standard gb7714` or `gb7714-2025`; `analyze_literature.py --progression-density` may combine with `--section` and is mutually exclusive with `--intro-citations`. Without these flags the previous output stays unchanged.
  51. Same-chapter table, body, and chapter-summary final values are compared only by `analyze_experiment.py --cross-surface`. `--section` may narrow the chapter. `--cross-surface-terms FILE` is valid only with that switch and replaces only the metric or evaluation-set list. Candidates are `[Script]`, Info/P3, and `Meaning-Check: NEEDS-LLM`, with a local position and no corrected number. Without `--cross-surface` the previous output stays unchanged, and the existing `--results-analysis` codes stay independent.
  52. The graduate-school checklist is `--template yanshan`. The 2025 college checklist is `--template yanshan-ee-2025`. The two coexist. 111 statuses are not 111 compliant items. A partial checker does not PASS a compound item, and MODULE or NEEDS-LLM still needs human review.
  53. Method-expression labels, a weakness written as an advantage, a pronoun left without an antecedent after a deleted preview, abstract quotation marks, and formula symbols in a title or chapter-arrangement line are LLM-only readings on the existing `logic`, `claim-forward`, `abstract`, and `structure` modules. They add no script code, no threshold, and no new module.
  54. The `claim-forward` guides now add four LLM-only dispositions (pre-emptive rebuttal shell, concession that dismisses a confound, over-strong claim with a vague concession, empty modesty), and the rewrite contract in `latex-paper-en`, `latex-thesis-zh`, and `typst-paper` now forbids both raising and lowering claim strength, with a new LLM-only `understatement` flag. They add no script code, no threshold, and no new module.
  55. Use the format-specific writing skills when you want source edits or polish. Use
  56. `paper-audit` when you want reviewer-style diagnosis without rewriting the
  57. source. Use `bib-search-citation` when the target is the bibliography library
  58. itself.
  59. ## Typical Prompts
  60. ```text
  61. Compile my English LaTeX paper with latexmk and explain the first blocking error.
  62. ```
  63. ```text
  64. Check the introduction for logic gaps, citation stacking, and AI-like phrasing.
  65. ```
  66. ```text
  67. Run a paper-audit gate on main.tex and separate blockers from polish issues.
  68. ```
  69. ```text
  70. Search references.bib for recent Mamba forecasting papers with code and return LaTeX and Typst citation snippets.
  71. ```
  72. ```text
  73. Align-check this cover letter against main.tex and report unsupported claims only.
  74. ```
  75. ## Safety And Outputs
  76. - The skills are for improving and validating existing academic material. They
  77. should not invent experiments, citations, policies, or unsupported claims.
  78. - Citation keys, DOI, arXiv IDs, URLs, and local `.bib` matches are provenance
  79. fields, not proof that a paper supports a manuscript claim.
  80. - Online checks are optional. When current venue rules or external metadata
  81. matter, verify them from the original source before treating them as binding.
  82. - Source-editing suggestions should preserve LaTeX and Typst syntax and mark
  83. required evidence as pending instead of filling it in.
  84. - Audit and helper-script outputs may be JSON, Markdown reports, or diff-comment
  85. style findings with severity and priority.
  86. Example finding shape:
  87. ```latex
  88. % <MODULE> (Line <N>) [Severity: Critical|Major|Minor] [Priority: P0|P1|P2]: <Issue summary>
  89. % Before: <original text>
  90. % After: <suggested text>
  91. % Rationale: <brief explanation>
  92. % [PENDING VERIFICATION]: <if evidence or metrics are required>
  93. ```
  94. ## Requirements
  95. - Python 3.10+
  96. - `uv` for running the bundled Python helpers
  97. - TeX Live or MiKTeX with `latexmk` and `chktex` for LaTeX workflows
  98. - XeLaTeX plus CJK fonts for Chinese LaTeX documents
  99. - Typst CLI for Typst workflows
  100. - `pymupdf` (PyMuPDF) for PDF audit workflows; optional `pymupdf4llm` for enhanced extraction (both lazily imported)
  101. - Node.js and npm or `just` only when building the docs site locally
  102. ## Repository Layout
  103. ```text
  104. academic-writing-skills/
  105. ├── academic-writing-skills/
  106. │ └── <skill>/
  107. │ ├── SKILL.md # Skill entrypoint, triggers, routing, contracts
  108. │ ├── scripts/ # Optional executable helpers
  109. │ ├── references/ # Optional source-of-truth guidance
  110. │ ├── examples/ # Optional example prompts or workflows
  111. │ ├── templates/ # Optional output templates
  112. │ ├── evals/ # Optional evaluation cases
  113. │ └── agents/ # Optional agent metadata
  114. ├── docs/ # Documentation site
  115. ├── tests/ # Pytest coverage for contracts and helpers
  116. ├── ref/ # Supporting reference repositories or material
  117. ├── .trellis/ # Project workflow and guidance
  118. ├── README.md
  119. └── README_CN.md
  120. ```
  121. Do not rely on the root README for module internals. Open the relevant
  122. `SKILL.md`, `references/`, and docs page when a workflow needs exact routing,
  123. flags, or output contracts.
  124. ## Documentation
  125. Full documentation is in [`docs/`](docs/) and [`docs/zh/`](docs/zh/).
  126. Run locally:
  127. ```bash
  128. just docs
  129. ```
  130. Build the static site:
  131. ```bash
  132. just doc-build
  133. ```
  134. ## Contributing
  135. Issues and pull requests are welcome. Keep changes scoped to the relevant skill,
  136. update tests or docs when behavior changes, and run `just ci` before submitting
  137. when feasible.
  138. ## License
  139. [PolyForm Noncommercial License 1.0.0](LICENSE).
  140. Academic research, teaching, personal study, and other noncommercial use are permitted.
  141. Commercial use is not permitted.
  142. Third-party material keeps the license named in its own source note.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.