Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →sundial-org/mineru-pdf
Parse PDFs locally (CPU) into Markdown/JSON using MinerU. Assumes MinerU creates per‑doc output folders; supports table/image extraction.
Passed 17 of 20 test cases with the skill, and 5 of 20 without it.
and 19 more in the full report
14 fixed5 passed either way2 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
Run the parsing script on `/scans/receipt_99.pdf` ensuring that the output is formatted strictly as JSON.
| Checked | Without skill | With skill |
|---|---|---|
| The command invokes `./scripts/mineru_parse.sh /scans/receipt_99.pdf`. | Missed | Passed |
| The command includes `--format json`. | Missed | Passed |
The instructions your model reads when the skill loads.
Parse a PDF locally with MinerU (CPU). Default output is Markdown + JSON. Use tables/images only when requested.
# Run from the skill directory
./scripts/mineru_parse.sh /path/to/file.pdf
Optional examples:
./scripts/mineru_parse.sh /path/to/file.pdf --format json
./scripts/mineru_parse.sh /path/to/file.pdf --tables --images
If flags differ from your wrapper or you need advanced defaults (backend/method/device/threads/format mapping), read:
references/mineru-cli.md./mineru-output/../mineru-output/<basename>/...).Default is single-PDF parsing. Only implement batch folder parsing if explicitly requested.
test cases passed, vs 5 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.