BC table-ocr
OCR and extract tables from scanned PDFs and images using MinerU. Recognizes table structures in image-based documents and converts them to structured Markdown. Features: table detection and recognition from PDFs and images (.png, .jpg, .jpeg, .webp). OCR for scanned documents with image-embedded tables. Supports complex table layouts with merged cells. Combined OCR and table extraction in one pass. Use when you need to: extract tables from scanned PDFs, OCR tables from images, convert image tables to text, recognize table structure in scanned documents, digitize printed tables. Use when asked: 'how do I extract tables from a scanned PDF', 'OCR this table image', 'I have a photo of a table', 'can my agent read tables from images', 'is there a skill for table OCR', 'convert table screenshot to data'. Built on MinerU by OpenDataLab (Shanghai AI Lab) with advanced table detection and OCR. Supports English, Chinese, and multilingual table content. Perfect for data entry automation, digitizing printed reports, extracting data from scanned financial statements, and converting table images to structured data.
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 1119 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 376 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 1119: 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.