[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-75962":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":9,"languages":9,"totalLinesOfCode":9,"stars":10,"forks":11,"watchers":12,"openIssues":13,"contributorsCount":13,"subscribersCount":13,"size":13,"stars1d":14,"stars7d":15,"stars30d":16,"stars90d":13,"forks30d":13,"starsTrendScore":17,"compositeScore":18,"rankGlobal":9,"rankLanguage":9,"license":19,"archived":20,"fork":20,"defaultBranch":21,"hasWiki":22,"hasPages":20,"topics":23,"createdAt":9,"pushedAt":9,"updatedAt":34,"readmeContent":35,"aiSummary":36,"trendingCount":13,"starSnapshotCount":13,"syncStatus":12,"lastSyncTime":37,"discoverSource":38},75962,"journal-adapt-writing-skill","WantongC\u002Fjournal-adapt-writing-skill","WantongC","Learn any journal's writing conventions from its published papers, then revise your manuscript to match — section by section.",null,675,43,2,0,4,42,339,27,8.93,"MIT License",false,"main",true,[24,25,26,27,28,29,30,31,32,33],"academic-writing","claude","economics","journal","latex","llm","manuscript-revision","prompt-engineering","research","writing","2026-06-12 02:03:38","# journal-adapt-writing-skill\n\n> **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.**\n\n![License: MIT](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-blue.svg)\n![Claude Code](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FClaude_Code-compatible-blueviolet)\n![Codex](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FCodex-compatible-green)\n![Version](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fversion-1.1-brightgreen)\n\nThere are already many useful **static academic writing skills**: discipline templates, anti-AI phrasing rules, citation\u002Fequation safety rules, and general academic style guides. They are valuable, but they usually apply the same rules to every manuscript.\n\nThe 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.\n\n**journal-adapt adds that dynamic layer on top of optional static skills.**\n\n- **Static skills** are reusable base rules: discipline conventions, general academic writing constraints, anti-AI phrasing cleanup, citation\u002Fequation safety, or your own lab\u002Fadvisor guide.\n- **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\u002Flab exemplars.\n\nThe 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.\n\n---\n\n## Static + Dynamic\n\n```mermaid\nflowchart TD\n    A[Optional Static Skills\\nreusable base rules] --> E[Dynamic Writing Skill]\n    B[Target Journal Papers\\nprimary corpus] --> D[Corpus Style Profile]\n    C[Field-top or Topic-similar Papers\\noptional] --> D\n    U[User \u002F Lab Exemplars\\noptional] --> D\n    D --> E\n    E --> F[Human Review]\n    F --> G[Section Revision]\n    G --> H[Revision Log]\n\n    style E fill:#e8f5e9,stroke:#4caf50\n    style F fill:#f5f0e8,stroke:#999\n```\n\n## Optional Static Skills\n\nThe static layer is optional. You can choose an existing open-source skill, bring your own, or skip this layer.\n\n| Static option | Field \u002F purpose | Source |\n|---------------|-----------------|--------|\n| Economics writing | Economics writing and referee-style guidance | [hanlulong\u002Fecon-writing-skill](https:\u002F\u002Fgithub.com\u002Fhanlulong\u002Fecon-writing-skill) |\n| ML \u002F CV \u002F NLP writing | Research paper writing for ML-style papers | [Master-cai\u002FResearch-Paper-Writing-Skills](https:\u002F\u002Fgithub.com\u002FMaster-cai\u002FResearch-Paper-Writing-Skills) |\n| CS \u002F research paper writing | Research paper pipeline for CS systems, networking, and ML-adjacent papers | [SNL-UCSB\u002Fpaper-writing-skill](https:\u002F\u002Fgithub.com\u002FSNL-UCSB\u002Fpaper-writing-skill) |\n| Philosophy \u002F interdisciplinary writing | Academic paper planning and composition | [lishix520\u002Facademic-paper-skills](https:\u002F\u002Fgithub.com\u002Flishix520\u002Facademic-paper-skills) |\n| General AI-writing cleanup | Generic AI-writing cleanup \u002F humanizing constraints | [blader\u002Fhumanizer](https:\u002F\u002Fgithub.com\u002Fblader\u002Fhumanizer) |\n\nMore details: [Static Skill Recommendations](docs\u002FSTATIC_SKILL_RECOMMENDATIONS.md).\n\nYou can also use a custom static skill:\n\n| Custom input | Use when |\n|--------------|----------|\n| Your own `SKILL.md` | You already have reusable agent instructions. |\n| Lab\u002Fadvisor writing guide | Your group has stable style preferences. |\n| Journal or field checklist | You want a lightweight rule sheet instead of a full skill. |\n| No static skill | You want the dynamic corpus to drive the workflow on its own. |\n\n## Dynamic Corpus\n\nThe dynamic corpus is the main feature. It is broader than \"papers from the target journal.\"\n\n| Corpus role | Required? | What it contributes |\n|-------------|-----------|---------------------|\n| **Primary corpus: target-journal papers** | Yes | The journal's local writing culture: structure, contribution framing, method\u002Fresult exposition, discussion scope. |\n| **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. |\n| **User\u002Flab exemplars** | Optional | Author, advisor, or lab preferences that should be preserved when they do not conflict with the target journal. |\n\nThe target journal usually has the highest priority. Optional secondary papers and user\u002Flab exemplars enrich the dynamic skill, but they do not override reviewed target-journal patterns unless the user explicitly chooses that behavior.\n\n## Priority System\n\n| Priority | Source | Rule |\n|----------|--------|------|\n| P1 | Hard constraints | Preserve facts, citations, equations, notation, numerical results, labels, and author-defined terminology. |\n| P2 | Target journal corpus | Follow reviewed target-journal patterns. |\n| P3 | Secondary corpus and exemplars | Use high-quality field patterns or user\u002Flab preferences when target-journal evidence is absent or weak. |\n| P4 | Static base skill | Apply discipline or general writing rules when corpus signals do not decide. |\n| P5 | Cleanup rules | Remove AI-taste phrases, hollow transitions, generic contributions, and unsupported overclaims. |\n\nP1 always wins. P2 usually beats P3 and P4. Any conflict that changes revision behavior should be recorded in the revision log.\n\n---\n\n## Corpus Preparation\n\nRecommended starting point:\n\n| Corpus role | Recommended size |\n|-------------|------------------|\n| Primary corpus: target-journal papers | 5-8 papers |\n| Secondary corpus: field-top or topic-similar papers | 2-5 papers |\n| User\u002Flab exemplars | 1-3 documents |\n\nAll corpus files should be fully readable Markdown\u002Ftext before Phase 1. If a PDF conversion is incomplete, retry conversion, use another converter, provide clean Markdown\u002Ftext, or replace the paper.\n\n---\n\n## Quick Start\n\n### 1. Install the skill\n\nFor Claude Code:\n\n```bash\nmkdir -p ~\u002F.claude\u002Fskills\u002Fjournal-adapt\ncp -R skill\u002F* ~\u002F.claude\u002Fskills\u002Fjournal-adapt\u002F\n```\n\nFor Codex, copy or symlink the `skill\u002F` 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\u002FSKILL.md` directly.\n\nMore detail: [Installation and PDF Conversion](docs\u002FINSTALLATION.md).\n\n### 2. Prepare inputs\n\nMinimum Markdown workflow, no MinerU required:\n\n```text\nmy_project\u002F\n├── corpus\u002F\n│   ├── target_journal_001.md\n│   ├── target_journal_002.md\n│   └── field_top_paper_001.md\n└── manuscript.md\n```\n\nPDF workflow:\n\n```text\nmy_project\u002F\n├── corpus_pdfs\u002F\n│   ├── paper_001.pdf\n│   └── paper_002.pdf\n└── manuscript.pdf\n```\n\nPDF input requires a PDF-to-Markdown converter. MinerU is supported, but Markdown input is the recommended path if MinerU is hard to install.\n\n### 3. Invoke\n\n```text\n\u002Fjournal-adapt\n```\n\nOr ask:\n\n```text\nHelp me build a dynamic writing skill for my manuscript using these target-journal papers and this base writing skill.\n```\n\nThe skill will ask for:\n\n1. Target journal or writing destination\n2. Primary corpus folder\n3. Optional secondary corpus folder\n4. Optional user\u002Flab exemplar files\n5. Optional base writing skill\n6. Manuscript file\n7. Sections to revise\n\n---\n\n## Output\n\nSaved next to the manuscript:\n\n```text\n[manuscript_name]_revised\u002F\n├── dynamic_writing_skill.md\n├── style_profile.md\n├── abstract_revised.md\n├── introduction_revised.md\n├── ...\n├── [section]_revision_log.md\n└── revision_summary.md\n```\n\nThe revised files are Markdown. Move them into LaTeX, Word, or another writing environment after review.\n\n---\n\n## Example\n\n`examples\u002Fjeem\u002F` shows an anonymized MVP run for the Journal of Environmental Economics and Management:\n\n- corpus-role metadata\n- conversion gate report\n- aggregated style profile\n- generated dynamic writing skill\n- sanitized section diagnosis, revision sample, and revision log\n\nRaw PDFs, converted full text, and the private manuscript are not included.\n\n---\n\n## Documentation\n\n- [Installation and PDF Conversion](docs\u002FINSTALLATION.md)\n- [Static Skill Recommendations](docs\u002FSTATIC_SKILL_RECOMMENDATIONS.md)\n- [System Architecture](docs\u002FARCHITECTURE.md)\n- [Module Specifications](docs\u002FMODULES.md)\n- [Templates](docs\u002Ftemplates\u002F)\n\n---\n\n## Known Limitations\n\n- English-language academic writing only.\n- PDF conversion quality depends on the converter. MinerU can fail on some local setups.\n- The project extracts writing structure and rhetorical patterns only. It must not quote or paraphrase copyrighted corpus papers.\n- The generated dynamic skill needs human review before revision begins.\n- The tool does not add facts, citations, results, or claims that are not already in the manuscript.\n\n---\n\n## Contributing\n\nUseful contributions include:\n\n- new static base writing skills for disciplines not covered here\n- better installation paths for Claude Code, Codex, and other agent environments\n- safer PDF-to-Markdown conversion recipes\n- more anonymized example corpora\n- improvements to style-card and revision-log templates\n\nOne base skill per file is preferred. Keep example corpora free of copyrighted full text and unpublished manuscript details.\n\n---\n\n## License\n\nMIT\n","journal-adapt-writing-skill 是一个用于学习特定期刊写作规范并根据这些规范逐节修订手稿的工具。该项目结合了静态和动态写作技能，其中静态技能提供可重用的基础规则，如学科惯例、学术写作约束等；而动态技能则基于用户提供的目标期刊论文及其他相关文献生成，以适应不同期刊的具体要求。适合需要向特定学术期刊投稿的研究人员使用，帮助他们更好地遵循目标期刊的写作风格和格式要求，从而提高稿件接受率。","2026-06-11 03:54:03","CREATED_QUERY"]