st0nefish/convert-doc
plugins-claude/convert-doc/skills/convert-doc/SKILL.md
Convert documents to/from markdown via pandoc — DOCX, HTML, RST, EPUB, ODT, RTF, LaTeX. Use when reading or producing any of those formats, or exporting markdown to PDF/DOCX.
development
Updated May 10, 2026
$ install --global
skillsauthnpx skillsauth add st0nefish/claude-toolkit convert-docInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 10, 2026, 4:11 AM133.9s1 file scanned
SKILL.md
- name:
- convert-doc
- description:
- >-
- allowed-tools:
- Bash, Read, Write
convert-doc
Convert documents to and from markdown using pandoc.
To markdown (primary use case)
Convert a document to GitHub-Flavored Markdown. Pandoc auto-detects the input format from the file extension.
To stdout (preferred — then read the output directly):
bash ${CLAUDE_PLUGIN_ROOT}/scripts/pandoc-wrap -t gfm input.docx
To a file:
bash ${CLAUDE_PLUGIN_ROOT}/scripts/pandoc-wrap -t gfm -o output.md input.docx
From a URL:
bash ${CLAUDE_PLUGIN_ROOT}/scripts/pandoc-wrap -t gfm https://example.com/page.html
Supported input formats
| Extension | Format |
|-----------|--------|
| .docx | Microsoft Word |
| .html | HTML |
| .rst | reStructuredText |
| .epub | EPUB |
| .odt | OpenDocument Text |
| .rtf | Rich Text Format |
| .tex | LaTeX |
Use -f <format> to override auto-detection when the extension is ambiguous or missing.
Typical workflow
- Convert the document to markdown:
bash ${CLAUDE_PLUGIN_ROOT}/scripts/pandoc-wrap -t gfm input.docx - Read the markdown output
- Work with the content as needed
From markdown (secondary use case)
To DOCX:
bash ${CLAUDE_PLUGIN_ROOT}/scripts/pandoc-wrap -o output.docx input.md
To PDF:
bash ${CLAUDE_PLUGIN_ROOT}/scripts/pandoc-wrap -o output.pdf input.md
PDF output requires a LaTeX engine. If not installed, suggest: brew install basictex (macOS) or apt install texlive (Linux).
If pandoc is not found, run /convert-doc:setup.
Related Skills
st0nefish/session-start
development
VerifiedTrustedCommunity
Start work from your description — explore the codebase and plan
1SKILL.mdUpdated May 27, 2026
st0nefish/session-orchestrate
data-ai
VerifiedTrustedCommunity
Multi-phase, multi-agent feature workflow: spec → plan → refine → divide → execute → review. Invoke when the user escalates a session-start/session-issue flow to orchestration, or asks to run a non-trivial feature (multiple files, design ambiguity, cross-cutting concerns, correctness-critical paths) through the full multi-agent workflow. For small fixes, prefer session-start.
1SKILL.mdUpdated May 27, 2026
st0nefish/session-issue
tools
VerifiedTrustedCommunity
Browse open issues, pick one, and start work on it
1SKILL.mdUpdated May 27, 2026
st0nefish/session-end
tools
VerifiedTrustedCommunity
Review, clean up, and open a PR to finalize the work
1SKILL.mdUpdated May 27, 2026