NLP Text Analyzer Skill for Local Ticket Keywords
Extract inspectable keywords from short synthetic tickets and tie every weighted term to its source row.
中文Install in Claude Code
Use Python, scikit-learn, and a few synthetic English tickets. The example uses local TF-IDF.
- Get the complete `plugins/ai-ml/nlp-text-analyzer/skills/analyzing-text-with-nlp` directory from the pinned GitHub commit.
- Copy it into the target project's `.claude/skills/`. Check `.claude/skills/analyzing-text-with-nlp/SKILL.md`, start Claude Code at the project root, and call `/analyzing-text-with-nlp`.
Example task
Vectorize export CSV empty, invoice email missing, and CSV export columns. Return the top three terms and their weights for each ticket ID.What to check
The table retains IDs and weights. A reviewer can trace export, CSV, and invoice back to the original phrases.
Original SKILL.md on GitHub · Updated
Frequently asked question
Can the English tokenizer be reused for Chinese tickets?
Use a suitable Chinese segmenter or character-level features and validate with known examples.