BC extract-tables-from-pdf
Extract tables from PDF documents using MinerU's table detection engine. Identifies and extracts structured table data from both native and scanned PDFs. Features: automatic table detection in PDFs. Extracts tables preserving row/column structure. OCR mode for scanned PDF tables. Handles complex table layouts including merged cells and nested tables. Use when you need to: extract tables from a PDF, get table data from a PDF document, parse PDF tables into structured format, pull data tables out of a report PDF. Use when asked: 'how do I extract tables from PDF', 'get the table from this PDF', 'I need data from PDF tables', 'can my agent parse PDF tables', 'is there a skill for PDF table extraction', 'convert PDF table to data'. Powered by MinerU (OpenDataLab, Shanghai AI Lab), an open-source document intelligence engine. Works with local files and URLs. Ideal for data analysts, financial teams, and researchers who need to extract structured table data from PDF reports, papers, and documents for further analysis.
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 1027 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 357 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 1027: 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.