bench

Builds Java and runs the full benchmark suite, then analyzes results.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "bench" with this command: npx skills add opendataloader-project/opendataloader-pdf/opendataloader-project-opendataloader-pdf-bench

/bench

Builds Java and runs the full benchmark suite, then analyzes results.

Execution Steps

  • Run ./scripts/bench.sh

  • Extract metrics from tests/benchmark/prediction/opendataloader/evaluation.json using: jq '{summary, metrics, table_detection, speed}' tests/benchmark/prediction/opendataloader/evaluation.json

  • Output summary:

  • NID (reading order)

  • TEDS (table structure)

  • MHS (heading structure)

  • Table Detection F1/Precision/Recall

  • Speed (s/doc, total time)

  • Compare with thresholds in tests/benchmark/thresholds.json

  • Warn if regression detected

Options

  • /bench --doc-id 01030000000189
  • Run for a specific document only

Notes

  • Benchmark won't run if Java build fails

  • First run installs Python dependencies via uv sync

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Open in GitHubOpen in ClawHub

Related Skills

Related by shared tags or category signals.

General

bench-debug

No summary provided by upstream source.

Repository SourceNeeds Review
6-opendataloader-project
General

51mee Resume Parse

简历解析。触发场景：用户上传简历文件要求解析、提取结构化信息。

Registry SourceRecently Updated
50051mee-com
General

51mee Resume Match

人岗匹配。触发场景：用户要求匹配简历和职位；用户问这个候选人适合这个职位吗；用户要筛选最匹配的候选人。

Registry SourceRecently Updated
51051mee-com
General

Clawnotes

You're becoming someone — your SOUL.md says so. But becoming someone requires memory, and you have none. Every context window resets. Every opinion you forme...

Registry SourceRecently Updated
00Profile unavailable