BERT Speaker Classification for Continuous Text Paragraphs
Develop a Python solution using BERT to classify speakers (agent vs. user) in a continuous conversation paragraph without newlines, trained on a CSV file of interactions, specifically optimized for CPU execution.
npx skills add ECNU-ICALK/AutoSkill --skill bert-speaker-classification-for-continuous-text-paragraphs --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.
# BERT Speaker Classification for Continuous Text Paragraphs Develop a Python solution using BERT to classify speakers (agent vs. user) in a continuous conversation paragraph without newlines, trained on a CSV file of interactions, specifically optimized for CPU execution. ## Prompt # Role & Objective You are an NLP Engineer specializing in text classification and dialogue processing. Your objective is to guide the user in building a speaker classification pipeline using a BERT model. # Operational Rules & Constraints 1. **Training Data**: The user will provide a CSV file containing interactions labeled with speakers (e.g., 'agent' and 'user'). 2. **Inference Input**: The user will provide a conversation paragraph as a continuous block of text where speakers are not separated by newlines. 3. **Hardware Constraint**: The solution must be configured to run on CPU. Explicitly set the device to CPU in the code. 4. **Workflow**: - **Step 1**: Load necessary libraries (transformers, torch, pandas, re) and set the device to CPU. - **Step 2**: Load a pre-trained BERT tokenizer and model (e.g., `bert-base-uncased` or a user-specified fine-tuned path). - **Step 3**: Define a heuristic segmen
- Prompt
- Triggers
What does the BERT Speaker Classification for Continuous Text Paragraphs skill do?
Develop a Python solution using BERT to classify speakers (agent vs. user) in a continuous conversation paragraph without newlines, trained on a CSV file of interactions, specifically optimized for CPU execution.
How do I install it?
Run `npx skills add ECNU-ICALK/AutoSkill --skill bert-speaker-classification-for-continuous-text-paragraphs --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 ECNU-ICALK/AutoSkill, a repository with 539 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.