npx skills add majiayu000/claude-skill-registry --skill spacy --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# spaCy spaCy is "Industrial Strength" NLP. Unlike NLTK (academic), spaCy focuses on providing the **best** single algorithm for a task. v3.8 supports Python 3.13. ## When to Use - **NER (Named Entity Recognition)**: Extracting person names, dates, orgs. - **Parsing**: Dependency parsing to understand sentence structure. - **Speed**: Cython-optimized pipelines. ## Core Concepts ### Pipeline Tokenizer -> Tagger -> Parser -> NER. ### Doc / Token / Span The core data structures. Efficient memory usage. ### Prodigy The annotation tool (paid) from the same creators, tightly integrated. ## Best Practices (2025) **Do**: - **Use Transformer pipelines**: `en_core_web_trf` (Roberta-based) for high accuracy. - **Use `nlp.pipe()`**: For batch processing huge texts. **Don't**: - **Don't use for GenAI**: spaCy is for structure extraction, not text generation (LLMs). ## References - [spaCy Documentation](https://spacy.io/)
- When to Use
- Core Concepts
- Pipeline
- Doc / Token / Span
- Prodigy
- Best Practices (2025)
- References
What does the spacy skill do?
spaCy NLP library with pipelines. Use for text processing.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill spacy --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.