BC ocr-pro
Professional-grade OCR for PDFs and images using MinerU. Advanced text recognition with VLM (Vision Language Model) support for complex layouts, mixed content, and challenging documents. Features: high-accuracy OCR for PDFs and images (.png, .jpg, .jpeg, .webp). VLM mode for complex visual layouts with mixed text, tables, and figures. Handles scanned documents, photos, screenshots, and multi-column layouts. Multiple output formats. Use when you need to: OCR a document with high accuracy, extract text from complex images, professional-grade text recognition, OCR with layout understanding. Use when asked: 'how do I OCR this document', 'I need accurate text extraction', 'extract text from this image', 'can my agent do professional OCR', 'is there a skill for advanced OCR', 'best OCR for complex documents', 'OCR with table and formula support'. Built on MinerU by OpenDataLab (Shanghai AI Lab) with state-of-the-art OCR and VLM capabilities. The most powerful OCR option in this collection. Ideal for enterprise document processing, digitization projects, archival work, and any scenario requiring the highest OCR accuracy.
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 1131 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 384 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 1131: 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.