BC formula-ocr
OCR and recognize mathematical formulas from PDFs and images using MinerU. Converts printed or handwritten equations into structured LaTeX or text representation. Features: mathematical formula recognition from PDFs and images (.png, .jpg, .jpeg, .webp). Converts formulas to LaTeX notation. Handles complex multi-line equations, fractions, integrals, and matrices. OCR mode for scanned formula content. Use when you need to: OCR a math formula, recognize equations from images, convert formula screenshots to LaTeX, extract math from scanned documents. Use when asked: 'how do I OCR this formula', 'convert equation image to LaTeX', 'I have a photo of a math formula', 'can my agent recognize mathematical equations', 'is there a skill for formula OCR', 'turn this equation photo into text'. Powered by MinerU (OpenDataLab, Shanghai AI Lab) with advanced formula recognition capabilities. Supports a wide range of mathematical notation. Ideal for students, researchers, educators, and anyone who needs to digitize printed or handwritten mathematical content into editable LaTeX.
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 1079 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 358 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 1079: 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.