using-spacy-nlp
Industrial-strength NLP with spaCy 3.x for text processing and custom classifier training. Use when "installing spaCy", "selecting model for nlp" (en_core_web_sm/md/lg/trf), "tokenization", "POS tagging", "named entity recognition" (NER), "dependency parsing", "training TextCategorizer models", "troubleshooting spaCy errors" (E050/E941 model errors, E927 version mismatch, memory issues), "batch processing with nlp.pipe", or "deploying nlp models to production". Includes data preparation scripts, config templates, and FastAPI serving examples.
Third-Party Agent Skill: Review the code before installing. Agent skills execute in your AI assistant's environment and can access your files. Learn more about security
Installation for Agentic Skill
View all platforms →skilz install SpillwaveSolutions/spacy-nlp-agentic-skill/using-spacy-nlp skilz install SpillwaveSolutions/spacy-nlp-agentic-skill/using-spacy-nlp --agent opencode skilz install SpillwaveSolutions/spacy-nlp-agentic-skill/using-spacy-nlp --agent codex skilz install SpillwaveSolutions/spacy-nlp-agentic-skill/using-spacy-nlp --agent gemini
First time? Install Skilz: pip install skilz
Works with 22+ AI coding agents
Cursor, Aider, Copilot, Windsurf, Qwen, Kimi, and more...
Extract and copy to ~/.claude/skills/ then restart Claude Desktop
git clone https://github.com/SpillwaveSolutions/spacy-nlp-agentic-skill cp -r spacy-nlp-agentic-skill/skills/using-spacy-nlp ~/.claude/skills/ Need detailed installation help? Check our platform-specific guides:
Related Agentic Skills
automating-mail
by SpillwaveSolutionsAutomates Apple Mail via JXA with AppleScript dictionary discovery. Use when asked to "automate email", "send mail via script", "JXA Mail automation",...
automating-reminders
by SpillwaveSolutionsAutomates Apple Reminders using JavaScript for Automation (JXA). Use when asked to "create reminders programmatically", "automate reminder lists", "JX...
mastering-postgresql
by SpillwaveSolutionsPostgreSQL development for Python with full-text search (tsvector, tsquery, BM25 via pg_search), vector similarity (pgvector with HNSW/IVFFlat), JSONB...
automating-contacts
by SpillwaveSolutionsAutomates macOS Contacts via JXA with AppleScript dictionary discovery. Use when asked to "automate contacts", "JXA contacts automation", "macOS addre...
Agentic Skill Details
- Owner
- SpillwaveSolutions (GitHub)
- Repository
- spacy-nlp-agentic-skill
- Type
- Other
- Meta-Domain
- N/A
- Primary Domain
- N/A
- Market Score
- 98.0
Agent Skill Grade
A
Score: 98/100
Click to see breakdown
Score Breakdown
Areas to Improve
- Reference files lack links back to SKILL.md making navigation one-directional
- Quick Start example has inline comments that could be more token-efficient
- Scope section appears after Contents but before Quick Start - unusual ordering
Recommendations
- Add trigger phrases to description for discoverability
- Add table of contents for files over 100 lines
Graded: 1/18/2026
Developer Feedback
I took a look at your using-spacy-nlp skill and wanted to share some thoughts.
Links:
The TL;DR
You're at 98/100 – that's A-grade territory. This is solid work that follows Anthropic's best practices. Your strongest area is Utility (19/20) – the skill actually solves real problems developers face with spaCy. The only things holding you back are minor navigation and organization tweaks that would push you to perfect.
What's Working Well
- Reference architecture is chef's kiss – You've got 5 references, 4 scripts, and 2 assets all at one level deep. Zero nesting, perfect separation of concerns. That's exactly how PDA should work (28/30 score).
- Trigger phrases are comprehensive – Installation, NER, POS tagging, TextCategorizer, troubleshooting (E050/E941 errors), batch processing with nlp.pipe, production deployment. You've actually thought about how people search for this.
- Practical examples that matter – Your scripts aren't toy code. Data prep, config templates, FastAPI serving, evaluation with metrics. These are real-world patterns developers need.
- Token economy is tight – SKILL.md at 333 lines, every section earns its space. You're not padding things out (9/10 on token economy).
The Big One
Missing back-navigation from references to SKILL.md – Right now when someone's in references/text-classification.md or references/production.md, they can't easily get back to the main skill overview. It's a one-way trip.
Why it matters: Navigation signals are part of your PDA score, and this breaks discoverability flow. Someone deep in a reference might want to jump back to see the big picture or navigate to a different reference.
The fix: Add a simple footer to each reference file:
---
← Back to [using-spacy-nlp](../SKILL.md)
This gives you that navigation link and bumps you +1 point toward PDA perfection.
Other Things Worth Fixing
Scope section positioning – It sits between Contents and Quick Start, which is unusual. Move it after Quick Start or fold it into the metadata description. Cleaner flow, slightly better PDA.
Code comment density – Your Quick Start example has inline comments like
# Entitiesthat could be trimmed or combined. spaCy docs already use these patterns, so you don't need to over-explain.Optional metadata fields – You're not using
uses_llm,supported_platforms, ordependencies. Consider addingdependencies: spacy>=3.0since that's foundational.
Quick Wins
- Add footer links to all 5 reference files: +1 point
- Tighten code comments in Quick Start: +0.5 points
- Reorder Scope section: +0.5 points
- Total upside: +2 points → potential 100/100
The skill is genuinely useful and well-structured. These are just the final polish to get it perfect.
Checkout your skill here: SkillzWave.ai | SpillWave We have an agentic skill installer that install skills in 14+ coding agent platforms. Check out this guide on how to improve your agentic skills.
AI-Detected Topics
Extracted using NLP analysis
Report Security Issue
Found a security vulnerability in this agent skill?