BC paper-parser
Parse academic papers and research documents from PDF using MinerU. Extracts structured content including title, abstract, sections, figures, tables, formulas, and references. Features: academic paper parsing optimized for research documents. Extracts paper structure: title, abstract, sections, subsections. Recognizes mathematical formulas and converts to LaTeX. Table extraction with structure preservation. Handles multi-column layouts common in academic papers. Use when you need to: parse an academic paper, extract sections from a research PDF, get structured content from a paper, extract formulas and tables from a journal article. Use when asked: 'how do I parse this paper', 'extract content from this research PDF', 'I want structured data from this academic paper', 'can my agent read research papers', 'is there a skill for paper parsing', 'parse this journal article', 'extract references from a paper'. Built on MinerU by OpenDataLab (Shanghai AI Lab), specifically designed for academic document processing. Handles ACM, IEEE, Springer, and other common paper formats. Ideal for researchers, graduate students, literature review tools, and academic content management systems.
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 1193 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 363 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 1193: 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.