← ClaudeAtlas

experience-synthesislisted

This skill should be used when the user asks to "learn from past sessions", "extract lessons", "find what worked", "identify patterns in my workflow", "what mistakes did I make", "what decisions were made", or wants to synthesize wisdom and actionable insights from conversation history. Integrates with `/trend` for longitudinal patterns and `/optimize` for skill-gap proposals.
taxueseek/session-digger · ★ 34 · Data & Documents · score 85
Install: claude install-skill taxueseek/session-digger
# Experience Synthesis — Learning from Claude's Past ## Insight Taxonomy When analyzing conversations, extract insights in these categories (ordered by durability — values first): ### 1. Learned Values Comparative preferences and priority orderings — "X is better than Y". **Signal sources:** - User states "prefer X over Y", "X is better than Y", "X matters more than Y" - User confirms a comparative statement from Claude ("yes, readability > cleverness") - Trade-off discussions that resolve into a clear preference - Statements with "prioritize", "choose X over Y", "the most important thing is" **What to capture:** The value choice, both sides of the comparison, and the reasoning. Values are the most durable type of memory — they survive codebase rewrites. ### 2. Decisions What was chosen, why, and what alternatives were rejected. **Signal sources:** - `AskUserQuestion` tool calls + the user's response in the next tool_result - Plan mode content (`planContent` field on user records, `ExitPlanMode` tool calls) - Thinking blocks where Claude weighs options - Assistant text containing "I'll use X instead of Y because..." **What to capture:** The decision, the rationale, the alternatives considered, and the context (what problem it solved). ### 3. Mistakes & Corrections What went wrong, root cause, and how it was fixed. **Signal sources:** - Tool results with `is_error: true` - Bash results containing: error, failed, FAIL, exit code 1, stack trace, traceback, Exception -