BC doc-parse
Parse and extract structured content from Word documents (.doc, .docx) into well-organized Markdown using MinerU. Preserves the full document hierarchy: headings, nested lists, tables, paragraphs, and formatting. Features: structural parsing that maintains document outline and heading levels. Supports both legacy .doc and modern .docx formats. Quick parse mode (flash-extract) for .docx with no token required. Full parsing with token for complex documents. Use when you need to: parse a Word document's structure, extract headings and sections from .docx, analyze document layout, get structured output from Word files, convert Word to structured Markdown. Use when asked: 'how do I parse a Word file', 'extract structure from docx', 'I need the outline of this Word document', 'can my agent read Word file structure', 'is there a skill that parses .doc files'. Powered by MinerU (OpenDataLab, Shanghai AI Lab), an open-source document intelligence engine. Handles multilingual documents (English, Chinese, and more). Works with local files and URLs. Ideal for developers, researchers, and content managers who need to programmatically extract and understand Word document structure for downstream processing, content analysis, or document migration.
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 1253 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 416 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 1253: 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.