journal-adapt skill
Skill that adapts a research manuscript to a journal: it builds writing rules from published papers and revises a manuscript by section with a log
- 763 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The agent reads the folders with papers and the manuscript and saves style cards, revised sections and logs next to them
- The manuscript, possibly unpublished, goes whole to the agent's model and its provider
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/journal-adaptDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The agent reads the folders with papers and the manuscript and saves style cards, revised sections and logs next to them
- The manuscript, possibly unpublished, goes whole to the agent's model and its provider
This is third-party code. Review the repository files before installing.
What it does
journal-adapt helps rewrite a research paper for a specific journal. The work runs in two phases. In the first, the agent asks which journal you are writing for, where that journal's papers (the primary corpus) are, whether you have extra topic papers and lab exemplars, and which base rule set to attach: general academic, economics, machine learning or engineering. For each paper it writes a style card: how the abstract, introduction, contribution, literature review, method, results and discussion are built. It merges the cards into a journal profile and produces a dynamic_writing_skill.md file that you read and edit before any revision starts. In the second phase the agent revises the manuscript one section at a time and saves a separate file and a revision log for each section. A [name]_revised folder appears next to the manuscript with the style profile, the rewritten sections and an overall summary. The Markdown output is moved into LaTeX or Word after your review. The hard rules stay on: the agent adds no facts, citations or results, leaves equations, citation keys and notation untouched, and does not reproduce corpus papers: only their structure and rhetoric are described.
Who it is for. For researchers, doctoral students and academic editors who prepare an English-language paper for a specific journal and want to see how such papers are usually built before revising.
Good fit when
- A paper was rejected or sent back and the introduction and contribution framing must be rebuilt after nearby publications of the journal
- The manuscript goes to a different journal whose structure and tone requirements differ
- You have 5–8 papers from the target journal and want writing rules derived from them
- You want a revision log that shows what decision was made in each section and why
- You want your lab's shared rule layer kept separate from the settings of one journal
Not a fit when
- You must write a paper from scratch: the skill revises a finished manuscript and invents no results, references or data
- You do not have the target journal's papers in readable form: without a primary corpus there is no journal profile
- You need a check of facts, calculations or citations: the skill keeps them unchanged and does not verify them
- The text cannot be given to a model, for example unpublished results under an agreement: the agent itself reads the manuscript and the corpus
Example request
Help me build a dynamic writing skill for my manuscript from the Journal of Environmental Economics and Management papers in the corpus folder and rewrite the introductionLimitations
Only academic writing in English is supported.
The generated dynamic_writing_skill.md must be read and approved before revision starts, otherwise the journal rules remain the agent's unverified guesses.
PDF-to-Markdown conversion is handled by a separate program, MinerU, which fails on some local setups. In that case you need ready Markdown files or another converter, and every paper in the corpus must be fully readable. The author recommends 5–8 journal papers, 2–5 extra ones and 1–3 lab exemplars.
The skill describes the structure and rhetoric of the corpus papers and must not quote or paraphrase their copyrighted text. External base skills such as econ-writing-skill are only recommended, and it does not download them unless you ask. MIT license, version 1.1.
How to disable. Delete ~/.claude/skills/journal-adapt and Claude Code stops seeing the /journal-adapt command. For Codex remove the skill folder or its link from the skills directory. The _revised files and the style cards in _style_cards sit next to your manuscript and corpus; delete them separately if you do not need them.
FAQ
How is a dynamic skill different from a static one?
A static skill gives the same rules for any manuscript: discipline norms, cleanup of stock phrases, equation safety. A dynamic one is built for one manuscript and one journal from the corpus papers, and the target journal's papers keep the top priority.
Do I need MinerU to use it?
Only if the papers or the manuscript are PDFs. With Markdown or plain text the agent works without it. If MinerU will not install, you can supply ready Markdown or another converter; the condition is that every paper is fully readable.
How many papers does the corpus need?
The author advises starting with 5–8 papers from the target journal. You can add 2–5 topic papers from leading journals of the field and 1–3 documents with exemplars from the author or the lab.
Which base rule sets ship with the skill?
Four files in base_rules: general academic style, economics, machine learning with computer vision and language processing, and engineering and computer science. You can attach your own file or rely only on rules from the corpus.
What is in the JEEM example?
An anonymized trial run for the Journal of Environmental Economics and Management: corpus role metadata, a conversion report, an aggregated style profile, a generated dynamic skill, a sanitized section diagnosis and a revision sample with a log. PDFs, full texts and the private manuscript are not included.
Does the skill change equations and references in the text?
No, equations, LaTeX commands, citation keys, variable names, notation and numbers are preserved verbatim. This is the first of four hard rules, alongside the ban on adding facts and on paraphrasing corpus papers.
Discussion
No questions or reviews yet.
Related
SkillsSkills tailored to specific academic journals that help choose a venue, prepare a paper and pass review
The paper-spine skill takes a topic, materials and data through a scientific paper: literature, text, figures, review and Word, LaTeX and PDF files
Eight skills for finished papers and theses in LaTeX and Typst: compile, references, language polish, cover letters and a reviewer-style audit
A skill that stress-tests a research paper before submission: mocks a review, gives a verdict, helps revise and re-verify
A skill for writing and revising ML, CV and NLP papers: section structure, paragraph flow and reviewer-style self-review
A skill set for research work in the style of Nature journals: finding and reading papers, writing, statistics, figures, reviewer responses
Comparison with similar tools
Entries that share the main search query, and how they differ.
| Entry | Official | Repository stars | Main difference |
|---|---|---|---|
| journal-adapt (this entry) | no | 763 | |
| Academic Paper Skills | no | 1,416 | two skills for planning and drafting a paper, without profiling a specific journal's style |
| Academic Research Skills | no | 53,358 | set for research, drafting, peer review and citation checks step by step |
README in short
The description explains the static-plus-dynamic idea with a flow from the corpus to style cards, the journal profile, the dynamic skill and section revision. Tables follow for static skills with sources, corpus roles and a priority system from hard constraints down to stock-phrase cleanup, then a quickstart for Claude Code and Codex, the input folder layout and the list of output files. The repository has installation, architecture and module documents, templates and an example for one journal.
README badge
Original SKILL.md
--- name: journal-adapt description: "Dynamic academic writing skill generator. Combines optional static writing skills with target-journal, field-top, or user-provided reference corpora, then revises a manuscript with a reviewable temporary skill. Use when the user wants to adapt an academic paper to a target journal, build a corpus-grounded writing skill, or revise section by section using journal and field writing signals." argument-hint: "e.g. 'build a dynamic writing skill for my manuscript using these journal papers' or 'help me revise my paper for JEEM'" user-invocable: true --- You are a dynamic academic writing skill assistant. You help researchers build a temporary, reviewable writing skill for one manuscript by combining: 1. an optional static base writing skill, 2. a primary target-journal corpus, 3. optional field-top or topic-similar reference papers, 4. optional user/lab exemplars. The target journal usually receives the highest weight, but the corpus does not have to be limited to the target journal. This skill runs in two phases. Read all instructions before starting. --- # HARD RULES — apply at all times These override everything else. Never violate them. 1. **Never add facts.** Do not introduce new empirical claims, results, citations, or data not already in the original manuscript. 2. **Never change technical content.** All equations, LaTeX commands, citation keys, variable names, model notation, numerical results, proposition statements, and footnotes must be preserved verbatim. 3. **Never paraphrase corpus papers.** When reading reference papers in Phase 1, output only structural and rhetorical descriptions — never quotes, never paraphrases, never reproductions of findings. 4. **One section at a time.** In Phase 2, revise and output one section fully before moving to the next. --- # INPUT AND DEPENDENCY CHECK First determine whether the corpus and manuscript inputs are already Markdown/text or still PDFs. - If all inputs are Markdown, plain text, or already converted agent-readable files, **do not require MinerU**. Proceed directly to Phase 1. - If any input is PDF, ask the user whether they want to use MinerU or provide converted Markdown instead. For PDF input with MinerU, verify installation: ```bash mineru --version ``` If this command fails, do not stop the whole workflow. Tell the user: