Agent skill

Latex To Word Workflow

by hajimi-kun in hajimi-kun/latex-to-word-workflow

Load when the user asks to convert an academic LaTeX manuscript, thesis, or report into an editable Word DOCX, adapt it to a Word template, preserve citations or cross-references, or diagnose a…

MITAuto-check passedDocuments & Office

Install Latex To Word Workflow

skills CLI

$ npx skills add hajimi-kun/latex-to-word-workflow --skill latex-to-word-workflow -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install hajimi-kun/latex-to-word-workflow latex-to-word-workflow --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/hajimi-kun/latex-to-word-workflow.git skills-src && mkdir -p .claude/skills && cp -r skills-src/latex-to-word-workflow .claude/skills/latex-to-word-workflow && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "latex-to-word-workflow" agent skill from https://github.com/hajimi-kun/latex-to-word-workflow/tree/main/latex-to-word-workflow into .claude/skills/latex-to-word-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "latex-to-word-workflow", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/hajimi-kun/latex-to-word-workflow/tree/main/latex-to-word-workflow

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add hajimi-kun/latex-to-word-workflow --skill latex-to-word-workflow -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install hajimi-kun/latex-to-word-workflow latex-to-word-workflow --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/hajimi-kun/latex-to-word-workflow.git skills-src && mkdir -p .agents/skills && cp -r skills-src/latex-to-word-workflow .agents/skills/latex-to-word-workflow && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "latex-to-word-workflow" agent skill from https://github.com/hajimi-kun/latex-to-word-workflow/tree/main/latex-to-word-workflow into .agents/skills/latex-to-word-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "latex-to-word-workflow", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add hajimi-kun/latex-to-word-workflow --skill latex-to-word-workflow -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install hajimi-kun/latex-to-word-workflow latex-to-word-workflow --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/hajimi-kun/latex-to-word-workflow.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/latex-to-word-workflow .cursor/skills/latex-to-word-workflow && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "latex-to-word-workflow" agent skill from https://github.com/hajimi-kun/latex-to-word-workflow/tree/main/latex-to-word-workflow into .cursor/skills/latex-to-word-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "latex-to-word-workflow", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/hajimi-kun/latex-to-word-workflow.git --path latex-to-word-workflow

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add hajimi-kun/latex-to-word-workflow --skill latex-to-word-workflow -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install hajimi-kun/latex-to-word-workflow latex-to-word-workflow --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/hajimi-kun/latex-to-word-workflow.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/latex-to-word-workflow .gemini/skills/latex-to-word-workflow && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "latex-to-word-workflow" agent skill from https://github.com/hajimi-kun/latex-to-word-workflow/tree/main/latex-to-word-workflow into .gemini/skills/latex-to-word-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "latex-to-word-workflow", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install hajimi-kun/latex-to-word-workflow latex-to-word-workflow

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add hajimi-kun/latex-to-word-workflow --skill latex-to-word-workflow -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/hajimi-kun/latex-to-word-workflow.git skills-src && mkdir -p .github/skills && cp -r skills-src/latex-to-word-workflow .github/skills/latex-to-word-workflow && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "latex-to-word-workflow" agent skill from https://github.com/hajimi-kun/latex-to-word-workflow/tree/main/latex-to-word-workflow into .github/skills/latex-to-word-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "latex-to-word-workflow", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add hajimi-kun/latex-to-word-workflow --skill latex-to-word-workflow -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install hajimi-kun/latex-to-word-workflow latex-to-word-workflow --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/hajimi-kun/latex-to-word-workflow.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/latex-to-word-workflow .opencode/skills/latex-to-word-workflow && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "latex-to-word-workflow" agent skill from https://github.com/hajimi-kun/latex-to-word-workflow/tree/main/latex-to-word-workflow into .opencode/skills/latex-to-word-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "latex-to-word-workflow", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: latex-to-word-workflow
GitHub stars: 128
Token cost: ~2.3k tokens
SKILL.md length: 993 words
Files: 12 (incl. scripts, references)
Skills in repo: 1
Repo updated: Jul 23, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Load when the user asks to convert an academic LaTeX manuscript, thesis, or report into an editable Word DOCX, adapt it to a Word template, preserve citations or cross-references, or diagnose a…

Works in 11 steps: Read the user request and nearest… → Compile the complete LaTeX project when… → If citations exist, complete the… → …
Asks to convert an academic LaTeX manuscript
SKILL.md covers Non-negotiable defaults, Capability boundary, Read routing and Required workflow, plus 3 more sections
Runs Python and Lua scripts from its folder; calls python

What it does

Latex To Word Workflow is an agent skill from hajimi-kun/latex-to-word-workflow. Load when the user asks to convert an academic LaTeX manuscript, thesis, or report into an editable Word DOCX, adapt it to a Word template, preserve citations or cross-references, or diagnose a LaTeX-to-Word conversion problem. Do not use for PDF-only LaTeX compilation, general Word editing, or DOCX-to-LaTeX conversion.

Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 16 other files, including scripts and reference files (for example `agents/openai.yaml`, `examples/bridge-starter/bridge_config.json` and `examples/bridge-starter/project_adapter.py`).

It sits in Documents & Office, covering LaTeX, Word documents and Citation management. It works with LaTeX, Microsoft Word and Zotero. The repository describes itself as: Agent Skill for polished LaTeX-to-Word conversion with live Zotero citations. The licence is MIT.

When your agent uses it

Asks to convert an academic LaTeX manuscript
Report into an editable Word DOCX
Adapt it to a Word template
Preserve citations

Example prompts

“/latex-to-word-workflow”

Requirements

Python 3

Workflow steps

11 steps, taken from the first numbered list in SKILL.md.

Read the user request and nearest project instructions. Identify the complete
Compile the complete LaTeX project when the host exposes the toolchain;
If citations exist, complete the mandatory Zotero setup and probe before
Classify and distill every new or changed Word target into an explicit role
For a new project, run python scripts/init_bridge.py and fill
Build the bridge `LaTeX role -> Pandoc output -> target Word representation
Convert a representative probe covering every high-risk role and transition.
Correct each mismatch at its responsible layer. Start the complete conversion
Build the complete candidate and validate source, target-contract, and DOCX
Follow references/conversion-playbook.md#validate-and-hand-off. Give the user
Deliver the candidate, agent-side evidence, user-refresh status, adaptations,

What it can do on your machine

Read from SKILL.md and the folder at commit 68b80c4. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 5 files in scripts/ (Python and Lua), which the agent can run.
Shell commands in SKILL.md call:
- python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Latex To Word Workflow loads about 2.3k tokens when it runs, and up to ~9k if it reads all its reference files. Until then it costs about 86 tokens; SKILL.md has 993 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~86
When it runs · the whole SKILL.md, loaded when a task matches: ~2.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from hajimi-kun/latex-to-word-workflow at commit 68b80c4, republished under its MIT licence (© hajimi-kun). 993 words, ~2,287 tokens.

Download SKILL.mdSave it as .claude/skills/latex-to-word-workflow/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.

name: latex-to-word-workflow
description: Load when the user asks to convert an academic LaTeX manuscript, thesis, or report into an editable Word DOCX, adapt it to a Word template, preserve citations or cross-references, or diagnose a LaTeX-to-Word conversion problem. Do not use for PDF-only LaTeX compilation, general Word editing, or DOCX-to-LaTeX conversion.
version: 3.0.0

LaTeX to Word

Produce a submission-grade Word candidate from a complete LaTeX project. The candidate must preserve scientific meaning, use the confirmed target semantics, remain editable where practical, and include an explicit status for the user-run Word/Zotero acceptance steps.

Non-negotiable defaults

Preserve the original LaTeX, bibliography, figures, and authoritative Word target. Work only on generated files or explicit copies.
Use Pandoc as the initial editable-structure converter. Add source annotations, Lua, OpenXML, or supported-adapter Word automation only for an observed bridge mismatch.
For a new project, initialize examples/bridge-starter/ into the generated build directory. Reuse docx_bridge.py for fields, bookmarks, styles, and DOCX packaging; adapt configuration or project_adapter.py instead of reimplementing those primitives.
For every new or changed target, distill the required roles (not unrelated template styles) and pass a representative probe before full conversion.
Treat object packaging and layout as target-owned contract values. Paragraphs, tab stops, borderless tables, caption segment sequences, label literals, and object order are possible representations, not generic skill defaults.
When citations exist, Zotero-live fields are mandatory. Run the fixed Zotero-live setup and probe in references/conversion-playbook.md#zotero-live-citations; repair agent-side configuration where possible and give the user exact manual steps for the remaining Word/Zotero setup.
Convert every LaTeX cross-reference occurrence to a verified native Word field by default. Static references require an informed, recorded user opt-out.
Treat desktop Microsoft Word as the authoritative environment for fields, numbering, layout behavior, and final validation. Word and Zotero actions are user-run acceptance steps unless the host explicitly provides a supported desktop adapter; never assume GUI, COM, or process access.
Prioritize: scientific fidelity, content completeness, citation/numbering semantics, editability, template structure, visual fidelity, then automation cost.

Capability boundary

Required for execution: access to the project files and a viable DOCX conversion path. If either is absent, provide diagnosis or a handoff plan and report the conversion as blocked.
Optional capabilities include shell or Python execution, LaTeX compilation, local application/process detection, Word rendering, GUI automation, and visual inspection. Attempt one only when the host explicitly exposes it.
An unavailable optional capability becomes a user-run gate, not a failed conversion. An unobservable capability remains unknown; never convert unknown into an installation or compatibility claim.

Read routing

Situation	Required read
New, changed, example-only, or ambiguous Word target	`references/template-distillation.md`, then `references/conversion-playbook.md#build-the-semantic-bridge`
First build for a project	`examples/bridge-starter/`, then `references/conversion-playbook.md#build-the-semantic-bridge`
Zotero, cross-references, equations, captions, complex objects, or diagnosis	Relevant section of `references/conversion-playbook.md`
Candidate validation or handoff	`references/conversion-playbook.md#validate-and-hand-off`
Other conversion work	Scan this file, then load only the relevant playbook section

Required workflow

Read the user request and nearest project instructions. Identify the complete LaTeX entry point, authoritative Word target, output path, and capabilities exposed by the host.
Compile the complete LaTeX project when the host exposes the toolchain; otherwise request the user's compiled reference or record compilation as a pending evidence gate. Inventory included sources, semantic roles, figures, tables, equations, citations, labels, reference occurrences, appendices, custom macros, and numbering behavior.
If citations exist, complete the mandatory Zotero setup and probe before expensive manuscript post-processing. Never use the absence of a zotero CLI alone as evidence that Zotero is unavailable. If live fields cannot be generated, stop the citation-bearing build and hand off the exact setup gate.
Classify and distill every new or changed Word target into an explicit role contract. Do not treat --reference-doc as an executable specification.
For a new project, run python scripts/init_bridge.py <build-dir> and fill bridge_config.json from the role contract. Keep stable field, bookmark, and package operations in the copied docx_bridge.py; put only project-specific behavior in project_adapter.py or the semantic Lua filter.
Build the bridge LaTeX role -> Pandoc output -> target Word representation -> method. Resolve every required role before full conversion.
Convert a representative probe covering every high-risk role and transition. Inspect actual styles, formatting, fields, bookmarks, lists, and objects.
Correct each mismatch at its responsible layer. Start the complete conversion only after the probe passes the applicable contract rows.
Build the complete candidate and validate source, target-contract, and DOCX evidence. Counts are diagnostic; semantic correspondence is the gate.
Follow references/conversion-playbook.md#validate-and-hand-off. Give the user a disposable candidate and exact Word/Zotero acceptance steps. If the user returns the refreshed file, re-run the audit and compare pre/post evidence.
Deliver the candidate, agent-side evidence, user-refresh status, adaptations, unresolved items, and approved exceptions.

Show full SKILL.md (282 more words)Show less

Bundled tools

Use the bundled standard-library scripts when Python 3 is available. init_bridge.py creates generated bridge files only; the manifest and audit scripts are read-only over source and DOCX inputs.

text

python scripts/latex_manifest.py <main.tex> --output <source-manifest.json>
python scripts/init_bridge.py <build-dir>
python scripts/docx_audit.py <candidate.docx> \
  --latex-manifest <source-manifest.json> \
  --require-native-crossrefs --require-zotero-fields \
  --output <candidate-audit.json>
python scripts/docx_audit.py <refreshed.docx> \
  --latex-manifest <source-manifest.json> \
  --baseline <candidate-audit.json> \
  --require-native-crossrefs --require-zotero-fields

--require-zotero-fields checks generated field presence, not that Refresh has occurred. Scripts provide package and semantic evidence; they cannot replace user-run Word rendering, field refresh, Zotero refresh, or user confirmation.

Stop conditions

Do not label the candidate fully verified when a required role is unmapped, a native field lacks a valid target, a REF target contains an entire drawing or table, the user reports a Word repair warning, live field generation is unverified, the user refresh/save/reopen gate is pending, or an unresolved scientific-content mismatch remains. A pending user gate may be delivered as a clearly labelled candidate; never silently downgrade it.

Known gotchas

Imported styles are not evidence that generated content uses them correctly. See references/template-distillation.md#build-the-role-contract.
ensuremath can turn prose formulae and units into unwanted OMML. See references/conversion-playbook.md#preserve-text-and-math-semantics.
A Pandoc bookmark can span a whole object, causing REF to reproduce it. See references/conversion-playbook.md#native-word-cross-references.
Raw OpenXML and field construction are starter-engine responsibilities, not project-adapter code. See examples/bridge-starter/.
Word/Zotero refresh can change fields and document structure. See references/conversion-playbook.md#validate-and-hand-off.
Zotero Refresh updates existing Zotero fields; it cannot create fields from non-Zotero citation text. See references/conversion-playbook.md#zotero-live-citations.
Field update can discard caption-run formatting or expose faulty equation packaging or alignment. See references/conversion-playbook.md#word-specific-objects.
Equation container (e.g. 1×3 borderless table) is not the same as column widths. Short template demos often use equal thirds; long OMML with fractions or \qquad secondaries needs a wide math cell or Word reflows mid-expression. Probe with a complex display equation. See references/conversion-playbook.md#numbered-equations.
PDF, EPS, TikZ, and PGFPlots artwork needs explicit Word-supported output. See references/conversion-playbook.md#high-risk-objects.

Files

SKILL.md and 11 other files (scripts, references) in latex-to-word-workflow of hajimi-kun/latex-to-word-workflow.

SKILL.md
agents/openai.yaml
examples/bridge-starter/bridge_config.json
examples/bridge-starter/project_adapter.py
examples/bridge-starter/semantic_filter.lua
references/conversion-playbook.md
references/template-distillation.md
scripts/docx_audit.py
scripts/docx_bridge.py
scripts/init_bridge.py
scripts/latex_manifest.py
scripts/test_better_bibtex.py

Open the folder on GitHubat commit 68b80c4

Compare with similar skills

Latex To Word Workflow next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Latex To Word Workflow compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Latex To Word Workflow this skillhajimi-kun/latex-to-word-workflow	128	—	~2.3k	Automated safety check: Pass	MIT	2 mo ago
Academic Paperbrycewang-stanford/Auto-Empirical-Research-Skills	4.6k	—	~7.3k	Automated safety check: Pass	Custom licence	6 days ago
Paper CovertGRIND-Lab-Core/night_owl_research_agent	106	—	~2.1k	Automated safety check: Notes	None	5 mo ago
ExportZimoLiao/scholaraio	577	—	~1.6k	Automated safety check: Pass	MIT	16 days ago
Thu ThesisLeoYeAI/openclaw-master-skills	2.2k	—	~4k	Automated safety check: Pass	MIT	2 mo ago
Scipilot Cite Skillfranklee16/academic-research-skills	223	—	~1.9k	Automated safety check: Pass	MIT	23 days ago

Similar skills

Academic Paper
brycewang-stanford/Auto-Empirical-Research-Skills
Academic paper writing skill with 12-agent pipeline. An agent skill from brycewang-stanford/Auto-Empirical-Research-Skills.
4.6k GitHub stars~7.3k tokensUpdated 6 days ago
Documents & OfficeAuto-check passed
Paper Covert
GRIND-Lab-Core/night_owl_research_agent
Converts the final Markdown manuscript from paper-draft / paper-review-loop into a submission package for the target venue — modular LaTeX (one file per section), compiled PDF, and Word .docx.
106 GitHub stars~2.1k tokensUpdated 5 mo ago
Documents & OfficeAuto-check: notes
Export
ZimoLiao/scholaraio
A skill your agent uses when the user needs BibTeX, RIS, Markdown reference lists, filtered citation exports, custom citation styles, or a Markdown-to-DOCX export for sharing.
577 GitHub stars~1.6k tokensUpdated 16 days ago
Research & ScienceAuto-check passed
Thu Thesis
LeoYeAI/openclaw-master-skills
清华大学毕业论文 Word → PDF 一键格式规范化工具。输入任意 Word (.docx) 格式的清华毕业论文，自动转换为符合清华 thuthesis 官方 LaTeX 模板规范的高质量 PDF。适用于所有清华学位论文（MBA/学硕/专硕），一条命令搞定。功能：自动提取章节结构、中英文摘要、参考文献（自动生成 BibTeX）、图片（含…
2.2k GitHub stars~4k tokensUpdated 2 mo ago
Documents & OfficeAuto-check passed
Scipilot Cite Skill
franklee16/academic-research-skills
SciPilot Skills 家族的文献检索与引用插入技能。支持两种输入模式—— 模式 A：读取用户的 Word(.docx) 或 LaTeX(.tex) 论文，在正文对应章节插入引用；模式 B：接收用户给出的一段话/一个观点/一个论断，输出能支撑它的参考文献列表（不修改文档）。两种模式都通过 Semantic Scholar、OpenAlex、Crossref 三源…
223 GitHub stars~1.9k tokensUpdated 23 days ago
Research & ScienceAuto-check passed
PDF
zai-org/ZCode
Professional PDF toolkit covering four production workflows: reports, creative visuals, academic LaTeX, and existing PDF processing.
7.7k GitHub stars~18k tokensUpdated yesterday
Documents & OfficeAuto-check: notes

Works with

Questions about Latex To Word Workflow

What does Latex To Word Workflow do?

Load when the user asks to convert an academic LaTeX manuscript, thesis, or report into an editable Word DOCX, adapt it to a Word template, preserve citations or cross-references, or diagnose a…. Latex To Word Workflow is an agent skill from hajimi-kun/latex-to-word-workflow. Load when the user asks to convert an academic LaTeX manuscript, thesis, or report into an editable Word DOCX, adapt it to a Word template, preserve citations or cross-references, or diagnose a LaTeX-to-Word conversion problem.

When should I use Latex To Word Workflow?

Latex To Word Workflow fits situations like: asks to convert an academic LaTeX manuscript; report into an editable Word DOCX; adapt it to a Word template; preserve citations.

How do I install Latex To Word Workflow in Claude Code?

Run `npx skills add hajimi-kun/latex-to-word-workflow --skill latex-to-word-workflow -a claude-code`. Or copy the skill folder (latex-to-word-workflow in hajimi-kun/latex-to-word-workflow) into .claude/skills/latex-to-word-workflow in your project. Claude Code loads it when a task matches its description.

How do I install Latex To Word Workflow in Codex?

Run `npx skills add hajimi-kun/latex-to-word-workflow --skill latex-to-word-workflow -a codex`. Or copy the skill folder (latex-to-word-workflow in hajimi-kun/latex-to-word-workflow) into .agents/skills/latex-to-word-workflow in your project. Codex loads it when a task matches its description.

Can I use Latex To Word Workflow in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add hajimi-kun/latex-to-word-workflow --skill latex-to-word-workflow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/latex-to-word-workflow, .gemini/skills/latex-to-word-workflow, .github/skills/latex-to-word-workflow and .opencode/skills/latex-to-word-workflow in your project.

What does Latex To Word Workflow need to run?

Going by SKILL.md and its folder, Latex To Word Workflow needs Python and Lua for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Latex To Word Workflow access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Latex To Word Workflow safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Latex To Word Workflow use?

Latex To Word Workflow is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Latex To Word Workflow use?

About 2.3k tokens (SKILL.md is roughly 9.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 6.7k tokens, read only when the agent opens those files.

What are the alternatives to Latex To Word Workflow?

Skills that share tags, products or a category with Latex To Word Workflow: Academic Paper (brycewang-stanford/Auto-Empirical-Research-Skills, 4.6k stars), Paper Covert (GRIND-Lab-Core/night_owl_research_agent, 106 stars), Export (ZimoLiao/scholaraio, 577 stars) and Thu Thesis (LeoYeAI/openclaw-master-skills, 2.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Latex To Word Workflow?

hajimi-kun (a GitHub user) maintains it in hajimi-kun/latex-to-word-workflow, which has 128 GitHub stars. The repository was last updated on July 23, 2026.

Source: hajimi-kun/latex-to-word-workflow on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Latex To Word Workflow

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

LaTeX to Word

Non-negotiable defaults

Capability boundary

Read routing

Required workflow

Bundled tools

Stop conditions

Known gotchas

Files

Compare with similar skills

Similar skills

Academic Paper

Paper Covert

Export

Thu Thesis

Scipilot Cite Skill

PDF

Related

Questions about Latex To Word Workflow