Academic Journal Word Formatter Agent Skill

Formats and typesets academic DOCX papers to match journal, university thesis, and conference submission templates using direct OpenXML…

Context cost
90.3k tokensestimated from the bundle, loaded when it triggers
Bundle
14 files · 1017.0 kB6 scripts among them — read before you run
Licence
not declarednone named by its author
Last change
—v1.1.0
Servers it uses
Noneruns standalone

What it does

用于对学术论文类 Word/DOCX 文档进行期刊、学校、会议或课程要求的格式排版与修复。当用户需要把论文原稿套用.docx 模板或明确格式规则、或提到论文排版、期刊投稿格式、学位论文格式、会议论文模板、时使用;如果同一请求同时包含论文 Word 排版和任何非排版任务,必须先停止并询问用户选择“只做格式排版”还是“作为复合任务拆分处理”,在用户明确选择前不得执行排版。不用于论文写作、润色、降重、翻译、代写、文献检索、补引用、验证引用、伪造数据/引用,或普通非论文 Word 文档套模板;

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

productivity

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md52.3 kB · preview
--- name: doubao-journal-format Version: 1.1.0 ---
7# DOCX Journal Format
8
9Apply an academic journal DOCX template to a target DOCX without reconstructing the document through python-docx. The tool edits the OpenXML package directly and keeps body text, formulas, images, OLE objects, tables, and relationships in place.
10
11## Trigger And Boundaries
12
13Use this skill only when the user explicitly asks for paper formatting, journal formatting, Word formatting, document typesetting, applying a template format to a Word file, or reformatting a .docx according to another .docx or explicit formatting rules.
14
15Before running any formatting tool, enforce these input boundaries in this exact order:
16
17- Composite-request hard stop: this is the highest-priority boundary check and it runs before target-file, template, source-format, extraction, QA, or any other check. If the same user request contains academic Word/DOCX formatting plus any non-formatting demand, the whole request is temporarily blocked. Non-formatting demands include writing, rewriting, polishing, translation, plagiarism reduction, literature search, reference addition/completion, DOI lookup, citation/reference verification, content expansion, summary/abstract/conclusion rewriting, data/statistical changes, figure/table content recreation, or any request to create, improve, verify, or validate scholarly content. In this case, do not read files, inspect attachments, browse, search, extract text, run scripts, edit files, generate output documents, or continue the formatting route. Respond only with a concise clarification that names the non-formatting demand(s) and asks the user to choose:
18 - A. 只做 DOCX 格式排版:按用户已经提供的目标文档、内容和参考文献原样排版。
19 - B. 这是复合任务:先拆分/处理非排版部分,之后再进入排版。
20 End the turn after asking. Continue only after the user explicitly chooses A or clearly says to ignore all non-formatting demands and do formatting only. If the user chooses B, do not use this skill to perform the non-formatting parts.
21- Required target: the user must provide a target .docx file to be formatted. If no target .docx is provided, ask the user to upload the Word file that needs formatting.
22- Required format source: accept explicit user formatting instructions, a valid Word .docx template/source-format file, or extractable formatting evidence from another source.
23- Non-.docx source boundary: uploaded or linked format-source files that are not real .docx packages, including but not limited to .pdf, image files, website links, and legacy .doc/.dot, should not block the run by themselves. Extract explicit text formatting requirements first. If text rules are found, use them; if a property is missing, complete that property from the selected bundled fallback. If no text rule is found, use the selected standard fallback directly. Visual/geometry evidence from any non-.docx source may only choose zh_single, zh_double, en_single, or en_double; it must not define paragraph roles, alignment,字号/point size, fonts, bold/italic, color, underline, indentation, spacing, tabs, headers/footers, support files, or run-level style. Record that the source is weaker than a native .docx template and include the standard-fallback risk in the final notes.
24- Text-rule priority boundary: do not confuse weak source type with weak text rules. A PDF/website/image/OCR/DOC/DOT source is weaker than native .docx because it lacks Word XML style parts, but any explicit text rule extracted from it is authoritative for the exact properties it states. user_rules and extracted text rules must outrank bundled fallback. Fallback may fill only unstated, missing, or unsafe-default properties. In user-facing notes, never say or imply that an explicit website/PDF text rule was lower priority than fallback.
25- Website/author-guide boundary: website pages such as Nature author formatting guides are text-rule evidence, not full Word/OpenXML templates, unless they provide an actual editable .docx/.dotx template. Use explicit prose rules from the page, for example Contributions should be double-spaced, but do not promise replication of the publisher's print/PDF house style. If the website does not provide exact Word font/size/spacing/page XML, final notes must say the result follows extracted submission rules plus the standard fallback and should be checked in Word.
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md6,681 words
Files14
Licencenot declared
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈80
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
90,170
on trigger
The instruction body and 13 supporting files, read only when the skill fires.
45.1%
of a 200k window
Ten skills this size would not fit in the window together.
050k100k150k200k context window

90.3k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

14 files, 1017.0 kB on disk. Mostly text — the instructions the model reads — with 6 scripts in it that your client would run only if the instructions tell it to.

  • SKILL.md52.3 kB
  • render_docx.py21.3 kB
  • assets/fallback_ooxml_spec.json143.7 kB
  • references/equations-tables-sections.md30.0 kB
  • references/explicit-postprocess.md8.4 kB
  • references/preservation-rules.md34.9 kB
  • references/references-numbering-superscript.md13.0 kB
  • references/style-routing.md49.7 kB
  • references/template-distill-render-qa.md29.0 kB
  • scripts/explicit_postprocess.py26.7 kB
  • scripts/extract_pdf_format.py69.0 kB
  • scripts/format_docx.py495.0 kB
  • scripts/qa_audit.py39.2 kB
  • scripts/render_and_diff.py4.8 kB
What is not in it

A skill installs nothing and depends on nothing: it is a folder your client reads. This one carries 6 scripts beside the text, so the bundle is 14 files you can review in full before installing.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Academic Journal Word Formatter · 90.3k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/academic-journal-word-formatter/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/academic-journal-word-formatter" ] && { [ ! -e .claude/skills/academic-journal-word-formatter ] || { mv .claude/skills/academic-journal-word-formatter "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/academic-journal-word-formatter" .claude/skills/ && echo "Installed .claude/skills/academic-journal-word-formatter"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add ahang1598/academic-journal-word-formatter

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/academic-journal-word-formatter/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/academic-journal-word-formatter/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/academic-journal-word-formatter" ] && { [ ! -e ~/.claude/skills/academic-journal-word-formatter ] || { mv ~/.claude/skills/academic-journal-word-formatter "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/academic-journal-word-formatter" ~/.claude/skills/ && echo "Installed ~/.claude/skills/academic-journal-word-formatter" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/academic-journal-word-formatter/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where. It appears as doubao-journal-format in Gemini CLI, Codex, Copilot and Grok (its own name); Claude Code lists it by the folder name, academic-journal-word-formatter.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Version1.1.0
Publishedno release date on file
PriceFree
Referenceahang1598/academic-journal-word-formatter

Versions

v1.1.0 is what is on the shelf; no release here carries a date. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

v1.1.0
  • No earlier releases have been published to the marketplace.
Pinning

The install command always fetches the release that is current the day you run it — v1.1.0 today — and cannot ask for an earlier one. The copy on your disk does not change until you run it again.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Publisher
Servers0
Claim this skill