Compute kiracurrie22/precision via the HuggingFace `evaluate` library. Use when the user has predictions + references and wants the canonical implementation of kiracurrie22/precision.
Installs into .claude/skills of the current project.
Are you the author of Kiracurrie22 Precision?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/qhjqhj00-kiracurrie22-precision)
---
name: kiracurrie22-precision
description: Compute kiracurrie22/precision via the HuggingFace `evaluate` library. Use when the user has predictions + references and wants the canonical implementation of kiracurrie22/precision.
metadata:
skill_kind: metric
source_lib: huggingface-evaluate
hf_module: kiracurrie22/precision
source: library_introspection
---
# kiracurrie22-precision
> Metric `kiracurrie22/precision` from the HuggingFace `evaluate` library.
## When to invoke
User asks to compute `kiracurrie22/precision` or wants HF evaluate's canonical version.
## Recipe
```python
import evaluate
metric = evaluate.load("kiracurrie22/precision")
result = metric.compute(predictions=preds, references=refs)
print(result)
```
## Don'ts
- Don't assume your in-house `kiracurrie22/precision` matches HF — version conventions vary.
- Many evaluate metrics have task-specific arguments (`average=`, `lang=`, `model_type=`); read the metric card before reporting numbers.
