Skip to content
Back to search

journal-adapt-writing-skill

Learn any journal's writing conventions from its published papers, then revise your manuscript to match — section by section.

Safety scan

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

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/wantongc--journal-adapt-writing-skill/badge.svg)](/listings/wantongc--journal-adapt-writing-skill)

HTML

<a href="/listings/wantongc--journal-adapt-writing-skill"><img src="/api/listings/wantongc--journal-adapt-writing-skill/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.

1. Install the skill

For Claude Code:

mkdir -p ~/.claude/skills/journal-adapt
cp -R skill/* ~/.claude/skills/journal-adapt/

For Codex, copy or symlink the `skill/` folder into your Codex skills directory if your local setup supports custom skills. You can also keep the repository open and ask Codex to use `skill/SKILL.md` directly.

More detail: [Installation and PDF Conversion](docs/INSTALLATION.md).

2. Prepare inputs

Minimum Markdown workflow, no MinerU required:

my_project/
├── corpus/
│   ├── target_journal_001.md
│   ├── target_journal_002.md
│   └── field_top_paper_001.md
└── manuscript.md

PDF workflow:

my_project/
├── corpus_pdfs/
│   ├── paper_001.pdf
│   └── paper_002.pdf
└── manuscript.pdf

PDF input requires a PDF-to-Markdown converter. MinerU is supported, but Markdown input is the recommended path if MinerU is hard to install.

3. Invoke

/journal-adapt

Or ask:

Help me build a dynamic writing skill for my manuscript using these target-journal papers and this base writing skill.

The skill will ask for:

1. Target journal or writing destination 2. Primary corpus folder 3. Optional secondary corpus folder 4. Optional user/lab exemplar files 5. Optional base writing skill 6. Manuscript file 7. Sections to revise

---

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 · 236 lines

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

  1. # journal-adapt-writing-skill
  2. > **A static + dynamic academic writing skill framework. Start with reusable writing rules, then generate a corpus-grounded dynamic skill for one manuscript and one writing destination.**
  3. ![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)
  4. ![Claude Code](https://img.shields.io/badge/Claude_Code-compatible-blueviolet)
  5. ![Codex](https://img.shields.io/badge/Codex-compatible-green)
  6. ![Version](https://img.shields.io/badge/version-1.1-brightgreen)
  7. There are already many useful **static academic writing skills**: discipline templates, anti-AI phrasing rules, citation/equation safety rules, and general academic style guides. They are valuable, but they usually apply the same rules to every manuscript.
  8. The missing piece is **journal adaptation**. Even for the same manuscript, writing for Journal A and writing for Journal B may require different introduction logic, contribution framing, method exposition, result emphasis, and discussion scope. A strong revision workflow should learn from the actual papers that define the target writing destination.
  9. **journal-adapt adds that dynamic layer on top of optional static skills.**
  10. - **Static skills** are reusable base rules: discipline conventions, general academic writing constraints, anti-AI phrasing cleanup, citation/equation safety, or your own lab/advisor guide.
  11. - **Dynamic skills** are generated for one manuscript and one writing destination from a user-provided corpus: target-journal papers, optional field-top or topic-similar papers, and optional user/lab exemplars.
  12. The result is a visible, editable `dynamic_writing_skill.md`. It does not auto-write a paper; it gives the agent an auditable revision framework for section-by-section academic rewriting.
  13. ---
  14. ## Static + Dynamic
  15. ```mermaid
  16. flowchart TD
  17. A[Optional Static Skills\nreusable base rules] --> E[Dynamic Writing Skill]
  18. B[Target Journal Papers\nprimary corpus] --> D[Corpus Style Profile]
  19. C[Field-top or Topic-similar Papers\noptional] --> D
  20. U[User / Lab Exemplars\noptional] --> D
  21. D --> E
  22. E --> F[Human Review]
  23. F --> G[Section Revision]
  24. G --> H[Revision Log]
  25. style E fill:#e8f5e9,stroke:#4caf50
  26. style F fill:#f5f0e8,stroke:#999
  27. ```
  28. ## Optional Static Skills
  29. The static layer is optional. You can choose an existing open-source skill, bring your own, or skip this layer.
  30. | Static option | Field / purpose | Source |
  31. |---------------|-----------------|--------|
  32. | Economics writing | Economics writing and referee-style guidance | [hanlulong/econ-writing-skill](https://github.com/hanlulong/econ-writing-skill) |
  33. | ML / CV / NLP writing | Research paper writing for ML-style papers | [Master-cai/Research-Paper-Writing-Skills](https://github.com/Master-cai/Research-Paper-Writing-Skills) |
  34. | CS / research paper writing | Research paper pipeline for CS systems, networking, and ML-adjacent papers | [SNL-UCSB/paper-writing-skill](https://github.com/SNL-UCSB/paper-writing-skill) |
  35. | Philosophy / interdisciplinary writing | Academic paper planning and composition | [lishix520/academic-paper-skills](https://github.com/lishix520/academic-paper-skills) |
  36. | General AI-writing cleanup | Generic AI-writing cleanup / humanizing constraints | [blader/humanizer](https://github.com/blader/humanizer) |
  37. More details: [Static Skill Recommendations](docs/STATIC_SKILL_RECOMMENDATIONS.md).
  38. You can also use a custom static skill:
  39. | Custom input | Use when |
  40. |--------------|----------|
  41. | Your own `SKILL.md` | You already have reusable agent instructions. |
  42. | Lab/advisor writing guide | Your group has stable style preferences. |
  43. | Journal or field checklist | You want a lightweight rule sheet instead of a full skill. |
  44. | No static skill | You want the dynamic corpus to drive the workflow on its own. |
  45. ## Dynamic Corpus
  46. The dynamic corpus is the main feature. It is broader than "papers from the target journal."
  47. | Corpus role | Required? | What it contributes |
  48. |-------------|-----------|---------------------|
  49. | **Primary corpus: target-journal papers** | Yes | The journal's local writing culture: structure, contribution framing, method/result exposition, discussion scope. |
  50. | **Secondary corpus: field-top or topic-similar papers** | Optional | High-quality field writing when the target-journal corpus is small or when the topic needs extra reference points. |
  51. | **User/lab exemplars** | Optional | Author, advisor, or lab preferences that should be preserved when they do not conflict with the target journal. |
  52. The target journal usually has the highest priority. Optional secondary papers and user/lab exemplars enrich the dynamic skill, but they do not override reviewed target-journal patterns unless the user explicitly chooses that behavior.
  53. ## Priority System
  54. | Priority | Source | Rule |
  55. |----------|--------|------|
  56. | P1 | Hard constraints | Preserve facts, citations, equations, notation, numerical results, labels, and author-defined terminology. |
  57. | P2 | Target journal corpus | Follow reviewed target-journal patterns. |
  58. | P3 | Secondary corpus and exemplars | Use high-quality field patterns or user/lab preferences when target-journal evidence is absent or weak. |
  59. | P4 | Static base skill | Apply discipline or general writing rules when corpus signals do not decide. |
  60. | P5 | Cleanup rules | Remove AI-taste phrases, hollow transitions, generic contributions, and unsupported overclaims. |
  61. P1 always wins. P2 usually beats P3 and P4. Any conflict that changes revision behavior should be recorded in the revision log.
  62. ---
  63. ## Corpus Preparation
  64. Recommended starting point:
  65. | Corpus role | Recommended size |
  66. |-------------|------------------|
  67. | Primary corpus: target-journal papers | 5-8 papers |
  68. | Secondary corpus: field-top or topic-similar papers | 2-5 papers |
  69. | User/lab exemplars | 1-3 documents |
  70. All corpus files should be fully readable Markdown/text before Phase 1. If a PDF conversion is incomplete, retry conversion, use another converter, provide clean Markdown/text, or replace the paper.
  71. ---
  72. ## Quick Start
  73. ### 1. Install the skill
  74. For Claude Code:
  75. ```bash
  76. mkdir -p ~/.claude/skills/journal-adapt
  77. cp -R skill/* ~/.claude/skills/journal-adapt/
  78. ```
  79. For Codex, copy or symlink the `skill/` folder into your Codex skills directory if your local setup supports custom skills. You can also keep the repository open and ask Codex to use `skill/SKILL.md` directly.
  80. More detail: [Installation and PDF Conversion](docs/INSTALLATION.md).
  81. ### 2. Prepare inputs
  82. Minimum Markdown workflow, no MinerU required:
  83. ```text
  84. my_project/
  85. ├── corpus/
  86. │ ├── target_journal_001.md
  87. │ ├── target_journal_002.md
  88. │ └── field_top_paper_001.md
  89. └── manuscript.md
  90. ```
  91. PDF workflow:
  92. ```text
  93. my_project/
  94. ├── corpus_pdfs/
  95. │ ├── paper_001.pdf
  96. │ └── paper_002.pdf
  97. └── manuscript.pdf
  98. ```
  99. PDF input requires a PDF-to-Markdown converter. MinerU is supported, but Markdown input is the recommended path if MinerU is hard to install.
  100. ### 3. Invoke
  101. ```text
  102. /journal-adapt
  103. ```
  104. Or ask:
  105. ```text
  106. Help me build a dynamic writing skill for my manuscript using these target-journal papers and this base writing skill.
  107. ```
  108. The skill will ask for:
  109. 1. Target journal or writing destination
  110. 2. Primary corpus folder
  111. 3. Optional secondary corpus folder
  112. 4. Optional user/lab exemplar files
  113. 5. Optional base writing skill
  114. 6. Manuscript file
  115. 7. Sections to revise
  116. ---
  117. ## Output
  118. Saved next to the manuscript:
  119. ```text
  120. [manuscript_name]_revised/
  121. ├── dynamic_writing_skill.md
  122. ├── style_profile.md
  123. ├── abstract_revised.md
  124. ├── introduction_revised.md
  125. ├── ...
  126. ├── [section]_revision_log.md
  127. └── revision_summary.md
  128. ```
  129. The revised files are Markdown. Move them into LaTeX, Word, or another writing environment after review.
  130. ---
  131. ## Example
  132. `examples/jeem/` shows an anonymized MVP run for the Journal of Environmental Economics and Management:
  133. - corpus-role metadata
  134. - conversion gate report
  135. - aggregated style profile
  136. - generated dynamic writing skill
  137. - sanitized section diagnosis, revision sample, and revision log
  138. Raw PDFs, converted full text, and the private manuscript are not included.
  139. ---
  140. ## Documentation
  141. - [Installation and PDF Conversion](docs/INSTALLATION.md)
  142. - [Static Skill Recommendations](docs/STATIC_SKILL_RECOMMENDATIONS.md)
  143. - [System Architecture](docs/ARCHITECTURE.md)
  144. - [Module Specifications](docs/MODULES.md)
  145. - [Templates](docs/templates/)
  146. ---
  147. ## Known Limitations
  148. - English-language academic writing only.
  149. - PDF conversion quality depends on the converter. MinerU can fail on some local setups.
  150. - The project extracts writing structure and rhetorical patterns only. It must not quote or paraphrase copyrighted corpus papers.
  151. - The generated dynamic skill needs human review before revision begins.
  152. - The tool does not add facts, citations, results, or claims that are not already in the manuscript.
  153. ---
  154. ## Contributing
  155. Useful contributions include:
  156. - new static base writing skills for disciplines not covered here
  157. - better installation paths for Claude Code, Codex, and other agent environments
  158. - safer PDF-to-Markdown conversion recipes
  159. - more anonymized example corpora
  160. - improvements to style-card and revision-log templates
  161. One base skill per file is preferred. Keep example corpora free of copyrighted full text and unpublished manuscript details.
  162. ---
  163. ## License
  164. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

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