| name | document-conversion |
| description | Converts documents and URLs to markdown via tiered fallback (MCP markitdown, native tools, user notice). Use when a skill must ingest PDF, DOCX, or URL content. |
| alwaysApply | false |
| category | infrastructure |
| tags | ["conversion","markitdown","mcp","documents","pdf","docx"] |
| dependencies | ["content-sanitization","error-patterns"] |
| provides | {"infrastructure":["document-conversion","format-detection"],"patterns":["tiered-fallback-conversion","uri-based-conversion"]} |
| usage_patterns | ["document-to-markdown","url-content-extraction","file-format-conversion"] |
| complexity | basic |
| model_hint | fast |
| estimated_tokens | 500 |
| progressive_loading | true |
| modules | ["modules/format-matrix.md","modules/fallback-tiers.md","modules/uri-construction.md"] |
Document Conversion
Convert documents and URLs to markdown using a three-tier
fallback strategy. This skill is infrastructure: consumer
skills reference it via dependency rather than reimplementing
conversion logic.
When To Use
- Converting PDF, DOCX, PPTX, XLSX, HTML, or images to
markdown for downstream processing
- Any skill that ingests external documents
- File format is not plain text or markdown
When NOT To Use
- Content is already markdown or plain text
- You only need to read a small text file (use Read directly)
Format Detection
Identify the document type from the URI before converting.
| Extension | Format | Tier 1 | Tier 2 |
|---|
.pdf | PDF | Yes | Read tool (pages) |
.docx, .doc | Word | Yes | None |
.pptx, .ppt | PowerPoint | Yes | None |
.xlsx, .xls | Excel | Yes | None |
.html, .htm | HTML | Yes | WebFetch |
.csv | CSV | Yes | Read tool |
.json | JSON | Yes | Read tool |
.xml | XML | Yes | Read tool |
.png, .jpg, .jpeg, .gif, .webp | Image | Yes | Read tool (visual) |
.mp3, .wav, .m4a | Audio | Yes | None |
.zip | Archive | Yes | None |
.epub |
