BC doc-ocr
OCR (Optical Character Recognition) for Word documents (.docx) containing scanned pages or image-embedded content. Uses MinerU to extract text from Word files that have poor or missing text layers. Features: OCR extraction for image-based .docx files. VLM (Vision Language Model) mode for complex layouts with mixed text and images. Handles scanned document pages embedded in Word files. Converts image content to searchable, editable Markdown. Use when you need to: OCR a Word document with scanned pages, extract text from image-based .docx, read scanned content inside Word files, convert image text in .docx to editable text. Use when asked: 'how do I OCR a Word file', 'extract text from scanned docx', 'my Word file has images instead of text', 'can my agent read scanned Word documents', 'is there a skill for Word document OCR'. Powered by MinerU (OpenDataLab, Shanghai AI Lab) with advanced OCR and VLM capabilities. Supports English, Chinese, and multilingual scanned content. Ideal for offices, legal teams, and archivists who receive Word files containing scanned pages or image-only content and need to extract readable, searchable text.
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 1150 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. 10 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 375 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 1150: 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: 10 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 55.