BB mineru-precision-extract
MinerU precision extract — high-accuracy document extraction with full feature set. Convert PDFs, scanned documents, images, Word (DOC/DOCX), PowerPoint (PPT/PPTX), and HTML files into Markdown, HTML, LaTeX, DOCX, or JSON with table recognition, formula recognition (LaTeX), and advanced OCR. Choose between vlm model for highest accuracy on complex layouts, academic papers, and intricate tables, or pipeline model for zero-hallucination reliable extraction. Supports batch processing of hundreds of files, web page crawling to Markdown, and multi-format output in a single command. Use this skill when you need to: extract tables from PDFs, recognize formulas in academic papers, convert PDF to HTML or LaTeX, batch process document files, OCR scanned documents with high precision, convert documents to DOCX format, crawl web pages to structured Markdown, or process documents with complex layouts. Supports 80+ languages across Latin, Arabic, Cyrillic, Devanagari, CJK, and more script families. Handles large files with no size or page limits, unlike quick extraction modes. Built for researchers, data engineers, academic institutions, and production document pipelines that demand accuracy and reliability. Works as a Claude Code skill, MCP tool, or standalone CLI. 高精度PDF提取、表格识别、公式识别、PDF转HTML、PDF转LaTeX、PDF转DOCX、批量PDF处理、扫描件OCR、学术论文解析、多格式文档转换。支持VLM高精度模型和零幻觉Pipeline模型，80+语言支持，适用于学术研究、数据工程和生产环境文档处理。
As a process B 69/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, running it twice
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 1406 chars, limit 1024 - note
frontmatter-keyunknown frontmatter key "read_when"
Process rating: all ten parameters 69/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 6 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 32 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2940 tokens
- low 13 top-level sections: this looks like several domains in one skill
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 1405: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 26 headings
- +3Step-by-step instructions: 32 items
- +3Output format is stated explicitly
- +4Has examples (12 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.