BC mineru-fast
MinerU fast extract — zero-setup, instant document extraction. Convert PDFs, images, Word (DOCX), and PowerPoint (PPTX) to Markdown with no login, no token, no API key, no configuration required. Just install and run. Powered by the MinerU flash-extract engine with built-in OCR, table recognition, and formula extraction (LaTeX). Handles scanned documents, photos of text, academic papers, contracts, invoices, resumes, and slides out of the box. Use this skill when you need to: quickly extract text from a PDF, convert a document to Markdown without signing up, read a scanned PDF, turn a Word file into Markdown, parse a PowerPoint presentation, OCR an image, extract content from a PDF file, or get a fast document conversion with no setup. Supports 80+ languages including Chinese, English, Japanese, Korean, Arabic, Hindi, French, German, Spanish, Russian, and many more. Works with local files and remote URLs. Ideal for developers, researchers, students, and anyone who wants instant document parsing without accounts or API tokens. Use as a Claude Code skill, agent tool, or standalone CLI. PDF提取、文档转Markdown、免登录PDF转换、快速文档提取、扫描件OCR、图片转文字、Word转Markdown、PPT转Markdown、PDF解析、零配置文档转换。无需注册、无需Token，安装即用，一键提取PDF、Word、PPT、图片中的文字内容。
As a process C 62/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, consistency
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 1234 chars, limit 1024 - note
frontmatter-keyunknown frontmatter key "read_when"
Process rating: all ten parameters 62/100
- 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
- 40Consistency. Frontmatter name (mineru-fast) differs from the folder (mineru-fast-extract)
- 50Failures and branches. 0 branches, has a failure section
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 16 steps
- 100Execution cost. Instruction body is 1670 tokens
- 100Running it twice. No mutating operations
- low 10 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 1233: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 17 headings
- +3Step-by-step instructions: 16 items
- +3Output format is stated explicitly
- +4Has examples (9 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.