doc-to-markdown
Skill0 starsChanged 3 months agoMITView on GitHub
Convert an office document (docx/doc, pptx/ppt, xlsx/xls, odt/ods/odp, rtf, epub, csv) to a markdown file with Open Knowledge Format frontmatter, via the anydoc CLI. Refuses PDFs — those need the pdf-to-markdown skill's tiered OCR/verification pipeline. Use when the user asks to convert a Word/PowerPoint/Excel/OpenDocument/RTF/EPUB/CSV file to markdown.
- Installs packages
8 other projects use a version of this.
Adopted by
Most recently taken up by
- joaoguirunas/team-ostheir own version, first seen Nov 1, 2026
- AllanSantos-DV/skill-kittheir own version, first seen Oct 15, 2026
- TbusOS/sky-skillstheir own version, first seen Oct 11, 2026
- bnwe/claude-skillstheir own version, first seen Oct 11, 2026
- Sorinpsc/claude-skillstheir own version, first seen Aug 18, 2026
- Nico0713520/dsh-doc-to-markdowntheir own version, first seen Aug 17, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- sheepmao/doc-to-markdown-skill★ 9same name
- joaoguirunas/team-os★ 6same name
- TbusOS/sky-skills★ 3same name
- seonggukchoi/skills★ 1same name
- AllanSantos-DV/skill-kit★ 0same name
- bnwe/claude-skills★ 0same name
- Nico0713520/dsh-doc-to-markdown★ 0same name
- Sorinpsc/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- context-handoffSkill
- councilSkill
- deck-design-promptSkill
- granolaSkill
- mckinsey-deckSkill
- pdf-to-markdownSkill
- url-to-markdownSkill
- wargameSkill
- yt-transcriptSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 21
Default output is <input-stem>.md in the current directory.
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
doc-to-markdown
Thin wrapper around anydoc — office document formats are a solved conversion problem, so this skill is just the CLI plus OKF frontmatter, no pipeline. Supported formats: docx, doc, pptx, ppt, xlsx, xls, odt, ods, odp, rtf, epub, csv.
Command
uv run <skill-dir>/scripts/doc_to_markdown.py <input-file> [-o OUTPUT.md] [--output-dir DIR]Default output is <input-stem>.md in the current directory.
Output
One markdown file: Open Knowledge Format (OKF) v0.2
frontmatter (type: Document, title from the first markdown heading anydoc
produced — else the filename stem —, description from the first paragraph,
resource/sources pointing at the input file's absolute path,
generated.by: machine:doc-to-markdown/anydoc), then anydoc's converted
markdown body unchanged.
PDFs go elsewhere
This skill refuses PDF input (by extension and by %PDF- magic bytes) and
points at the pdf-to-markdown skill instead — PDFs need a tiered pipeline
with routing, OCR, and verification that doesn't belong in a trivial wrapper.
Troubleshooting (exit codes)
- 0 success.
- 1 unexpected error — bad input path, or anydoc itself was invoked wrong (a bug in this script, not the document).
- 2
anydocnot on PATH — install withnpm install -g @firecrawl/anydoc(requires Node/npm). - 3 input refused — it's a PDF; use the
pdf-to-markdownskill. - 4 anydoc could not convert the document. Its stderr message is passed
through and tells you why — observed cases:
document is encrypted(password-protected),unsupported input: unrecognized file content and extension(not one of the supported formats, or a bare extension-less file),malformed document: not a readable zip archive(corrupt docx/xlsx/pptx/odt — these are zip containers),io error(permissions or path problem). Nothing is written to the output file on any exit-4 failure.
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
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.

