agentleFS
sunliangcodesunliangcode/md-to-docx/references/agents.md

md-to-docx / references

AGENTS.md1 starsChanged 24 days agoMITView on GitHub

md-to-docx does not call OpenAI, Anthropic, or any cloud API. Conversion runs locally. Symlink the repo to ~/.cursor/skills/md-to-docx and use SKILL.md. Thin skill wrappers in skills/claude-code/SKILL.md and skills/codex/SKILL.md. See mcp.md. Tools: convert_markdown, apply_template, validate_document, list_presets. Copy this into a custom instruction or paste when needed: Docker: see web/README.md. Try locally without installing Python. Export AI chat replies to Word via local Playground — browser-extension/README.md.

The file

Files
agents.md

Use with AI agents

md-to-docx does not call OpenAI, Anthropic, or any cloud API. Conversion runs locally.

Cursor

Symlink the repo to ~/.cursor/skills/md-to-docx and use SKILL.md.

Claude Code / Codex

Thin skill wrappers in skills/claude-code/SKILL.md and skills/codex/SKILL.md.

MCP (Claude Desktop, Cursor, etc.)

See mcp.md. Tools: convert_markdown, apply_template, validate_document, list_presets.

ChatGPT (no skill protocol)

Copy this into a custom instruction or paste when needed:

You can convert Markdown to Word using the open-source md-to-docx CLI (local, no API key):

1. Install: git clone https://github.com/sunliang11/md-to-docx && cd md-to-docx
2. Convert: ./bin/convert my-report.md --preset technical
3. Output: my-report.docx beside the source file.

Presets: technical (formal reports), academic, professional, business, report.

Do not upload documents to third-party converters unless the user asks.

Web Playground

Docker: see web/README.md. Try locally without installing Python.

Browser extension

Export AI chat replies to Word via local Playground — browser-extension/README.md.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.