AC pptx-ocr
OCR for PowerPoint (.pptx) presentations with scanned or image-embedded slide content. Uses MinerU to extract text from image-based slides. Features: OCR extraction for image-based PPTX slides. VLM mode for complex visual content. Handles presentations with screenshots, scanned pages, or image-only slides. Converts image content to searchable text. Use when you need to: OCR a PowerPoint presentation, extract text from image-based slides, read scanned content in .pptx. Use when asked: 'how do I OCR PowerPoint slides', 'extract text from image slides', 'my presentation has images instead of text', 'can my agent OCR pptx files', 'is there a skill for PowerPoint OCR'. Built on MinerU by OpenDataLab (Shanghai AI Lab) with advanced OCR capabilities. Perfect for converting image-heavy presentations into searchable, editable text content.
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- 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
- 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 332 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 842: 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: 80.