What problem does it solve? Valuable reasoning, decisions, and reusable assets inside Claude conversations are trapped in ephemeral chat threads. This Skill converts manually pasted Claude material into durable, self-contained Markdown extracts that remain understandable and actionable without access to the original account, thread, Project, or Artifact. ## Core Features & Use Cases - Evidence-aware extraction: Builds turn ledgers and content element ledgers that separate stated facts from inferences, proposals, and unknowns, with fidelity labels for Artifacts, citations, files, and tool events. - Depth-controlled output: Supports rapid, balanced, and comprehensive extraction profiles (with aliases like scan, distill, and catalog) so users control granularity without sacrificing privacy or provenance checks. - Deterministic artifact writer: A bundled Python script validates metadata, derives a filesystem-safe slug from a distilled title chain, prevents accidental overwrites, and writes the final Markdown file atomically. - Use Case: You paste a long Claude Project conversation containing Artifact versions and web citations. The Skill normalizes roles, catalogs every element, runs a privacy gate, and produces a repository-ready extract with a clear resume point and open questions. ## Quick Start Paste your Claude conversation into the chat and ask the agent to extract it into a standalone Markdown artifact at balanced depth in your docs/thread-extracts folder.
