Compute sonsus/harim_plus via the HuggingFace `evaluate` library. Use when the user has predictions + references and wants the canonical implementation of sonsus/harim_plus.
Installs into .claude/skills of the current project.
Are you the author of Sonsus Harim Plus?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/qhjqhj00-sonsus-harim-plus)
---
name: sonsus-harim-plus
description: Compute sonsus/harim_plus via the HuggingFace `evaluate` library. Use when the user has predictions + references and wants the canonical implementation of sonsus/harim_plus.
metadata:
skill_kind: metric
source_lib: huggingface-evaluate
hf_module: sonsus/harim_plus
source: library_introspection
---
# sonsus-harim-plus
> Metric `sonsus/harim_plus` from the HuggingFace `evaluate` library.
## When to invoke
User asks to compute `sonsus/harim_plus` or wants HF evaluate's canonical version.
## Recipe
```python
import evaluate
metric = evaluate.load("sonsus/harim_plus")
result = metric.compute(predictions=preds, references=refs)
print(result)
```
## Don'ts
- Don't assume your in-house `sonsus/harim_plus` matches HF — version conventions vary.
- Many evaluate metrics have task-specific arguments (`average=`, `lang=`, `model_type=`); read the metric card before reporting numbers.
