Loading...
Loading...
Found 3 Skills
Generate a custom trace annotation web app for open coding during LLM error analysis. Use when the user wants to review LLM traces, annotate failures with freeform comments, and do first-pass qualitative labeling (open coding). Also use when the user mentions "annotate traces", "trace review tool", "open coding tool", "label traces", "build an annotation interface", "review LLM outputs", or wants to manually inspect pipeline traces before building a failure taxonomy. This skill produces a tailored Python web application using FastHTML, TailwindCSS, and HTMX.
Build a custom browser-based annotation interface tailored to your data for reviewing LLM traces and collecting structured feedback. Use when you need to build an annotation tool, review traces, or collect human labels.
A generator for character-by-character annotations, combined typesetting, chapter theme images, and full-chapter interpretations of ancient Chinese texts. It arranges the original text, character annotations, sentence annotations, wordless top illustrations, and chapter interpretations into a readable long PNG. USE WHEN the user calls ljg-classic OR requests character-by-character annotations, color interlinear notes, chapter interpretations, ancient Chinese lecture diagrams, or chapter illustrations for classical Chinese prose, ancient poems, or Confucian classics and other historical texts. NOT FOR translating a single sentence of ancient text, writing modern articles, or creating general content cards.