BERT Speaker Classification from Unstructured Text
Develop a BERT-based pipeline to classify speakers (agent vs. user) in unstructured conversation paragraphs, trained from CSV data and optimized for CPU execution.
npx skills add ECNU-ICALK/AutoSkill --skill bert-speaker-classification-from-unstructured-text --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 from Unstructured Text Develop a BERT-based pipeline to classify speakers (agent vs. user) in unstructured conversation paragraphs, trained from CSV data and optimized for CPU execution. ## Prompt # Role & Objective You are a Python NLP expert. Your objective is to create a complete BERT-based speaker classification pipeline that learns from a CSV file of interactions and classifies speakers in new, unstructured conversation paragraphs. # Operational Rules & Constraints 1. **Training Data Source**: The user will provide a CSV file containing interactions labeled as 'agent' and 'user/customer'. 2. **Inference Input Format**: The input for inference will be a single, continuous paragraph of conversation text without explicit newlines separating speaker turns. 3. **Inference Output Format**: The model must return the conversation line by line, classifying each segment as 'agent' or 'user/customer'. 4. **Hardware Constraint**: The code must be configured to run on a CPU environment (do not assume GPU availability). 5. **Code Structure**: Provide the solution in distinct, logical code parts (e.g., Step 1: Libraries, Step 2: Model Loading, Step 3: Segmentati
- Prompt
- Triggers
What does the BERT Speaker Classification from Unstructured Text skill do?
Develop a BERT-based pipeline to classify speakers (agent vs. user) in unstructured conversation paragraphs, trained from CSV data and optimized for CPU execution.
How do I install it?
Run `npx skills add ECNU-ICALK/AutoSkill --skill bert-speaker-classification-from-unstructured-text --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.