What problem does it solve? Long-running agent sessions generate millions of tokens of conversation history that exceed context windows, and naive compression loses critical details like file paths, error messages, and decision rationale, forcing costly re-exploration. ## Core Features & Use Cases - Anchored Iterative Summarization: Maintains persistent structured summaries with explicit sections for session intent, file modifications, decisions, and next steps, merging new content incrementally instead of regenerating from scratch. - Probe-Based Evaluation: Generates recall, artifact, continuation, and decision probes from conversation history, then scores responses across six dimensions including accuracy and artifact trail. - Structured Summarizer Script: The compression_evaluator.py script provides ProbeGenerator, CompressionEvaluator, and StructuredSummarizer classes for end-to-end compression quality checks. - Use Case: A coding agent debugging a 401 error across 178 messages hits the context limit; this Skill compresses the history into a structured summary preserving the root cause, modified files, and failing tests so work continues without re-reading files. ## Quick Start Ask the agent to compress the current conversation history into a structured summary and evaluate whether critical file and decision details survived compression.
