BC doc-to-markdown
Convert Word documents (.doc, .docx) to clean, well-structured Markdown using MinerU's document processing engine. Ideal for turning Microsoft Word files into readable Markdown for documentation, static sites, or content migration. Features: preserves headings, lists, tables, and paragraph structure. Supports both .doc (legacy) and .docx formats. Quick mode (flash-extract) for .docx requires no API token. Full extraction mode handles complex layouts with images and embedded objects. Use when you need to: convert a Word document to Markdown, turn .docx into .md, migrate Word content to a wiki or blog, extract formatted text from a Word file, read a .doc file as Markdown, batch convert Word files. Use when asked: 'how do I convert Word to Markdown', 'turn my docx into md', 'I want to read this Word file', 'can my agent parse a Word document', 'is there a skill that converts .doc files'. Built on MinerU by OpenDataLab (Shanghai AI Lab), an open-source document intelligence engine. Handles English, Chinese, and multilingual documents. Works with local files and URLs. Output can be streamed to stdout or saved to a directory. Perfect for developers, technical writers, and content teams who work with Word documents and need Markdown output for GitHub, Notion, Obsidian, or any Markdown-based workflow.
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Shorten the description to 1024 characters.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1314 chars, limit 1024 - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 51/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 9 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 393 tokens
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1314: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 6 headings
- +3Step-by-step instructions: 9 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 55.