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 dedicated 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 and scores responses across six quality dimensions using an LLM judge rubric. - 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; the skill compresses 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 with sections for session intent, files modified, decisions, and next steps.
