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