Hamel Husain
Community@hamelsmu · Portland, OR
https://hamel.dev
Agent Skills by Hamel Husain
Showing 14 vetted skills indexed across 2 GitHub repositories.
hamelsmuerror-analysis
Analyze LLM pipeline traces to categorize and prioritize failure modes.
hamelsmubuild-review-interface
Generate a browser-based annotation interface for reviewing LLM traces with Pass/Fail feedback.
hamelsmuwrite-judge-prompt
Design LLM-as-Judge evaluators for subjective criteria with binary pass/fail outcomes.
hamelsmueval-audit
Audit LLM evaluation pipelines for flaws in error analysis and evaluator design.
hamelsmuevaluate-rag
Evaluate RAG pipelines by measuring retrieval metrics and generation quality.
hamelsmuvalidate-evaluator
Calibrate LLM judges against human labels using TPR/TNR measurement and bias correction.
hamelsmugenerate-synthetic-data
Generate diverse synthetic test inputs for LLM pipeline evaluation.
hamelsmuExport liked and bookmarked tweets from Twitter/X to JSON files.
hamelsmuyoutube-transcribe
Download timestamped YouTube transcripts via the ai-transcribe command.
hamelsmukit
Fetch ConvertKit newsletters via the kit-broadcasts CLI and output JSON arrays.
hamelsmuyoutube-chapters
Generate timestamped chapter summaries for YouTube videos using AI.
hamelsmuzoom
Download Zoom meeting transcripts by meeting ID to file or stdout.
hamelsmuannotate-talk
Generate annotated blog posts from YouTube URLs or local MP4s with synchronized slide images.
hamelsmugem
Processes PDFs, images, videos, and URLs to extract insights and generate images via Gemini models.