BC pdf-to-latex
Convert PDF documents to LaTeX source using MinerU. Extracts text, formulas, and structure from PDFs and outputs LaTeX format for academic and technical documents. Features: PDF to LaTeX conversion preserving mathematical formulas. Handles academic papers, textbooks, and technical documents. Recognizes complex equations, tables, and document structure. OCR mode for scanned PDFs. Use when you need to: convert a PDF to LaTeX, extract LaTeX from an academic paper, reproduce a PDF in LaTeX, get LaTeX source from a document. Use when asked: 'how do I convert PDF to LaTeX', 'get LaTeX from this paper', 'I want to edit this PDF in LaTeX', 'can my agent extract LaTeX from PDF', 'is there a skill for PDF to LaTeX conversion', 'turn this paper into LaTeX'. Built on MinerU by OpenDataLab (Shanghai AI Lab), an open-source document intelligence engine. Excellent at formula recognition and LaTeX output. Perfect for researchers, graduate students, and academics who need to reproduce or edit PDF papers in LaTeX for submission, revision, or reference.
As a process C 59/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches
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 1050 chars, limit 1024 - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 59/100
- 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
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 10 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 411 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 1050: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 6 headings
- +3Step-by-step instructions: 10 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.