BC pdf-analysis
Analyze the structure, layout, and content of PDF documents using MinerU. Returns structured output preserving headings, tables, images, formulas, and document hierarchy. Features: comprehensive PDF analysis. Detects document structure: headings, paragraphs, tables, images, formulas. Multiple output formats (Markdown, HTML, JSON, LaTeX, DOCX). OCR and VLM modes for scanned or complex PDFs. Page range selection. Use when you need to: analyze a PDF document, understand PDF structure, inspect PDF content and layout, get a detailed breakdown of a PDF. Use when asked: 'how do I analyze this PDF', 'what is inside this PDF', 'I want to understand this PDF structure', 'can my agent analyze PDF files', 'break down this PDF for me', 'inspect this PDF document'. Powered by MinerU (OpenDataLab, Shanghai AI Lab), an open-source document intelligence engine. The most comprehensive PDF analysis tool in this collection. Ideal for researchers, data analysts, document processing pipelines, and anyone who needs deep insight into PDF document structure and content.
Analyze the structure, layout, and content of PDF documents using MinerU.
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 1061 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 437 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 1061: 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.