---

name: search-conversations description: Search past Claude Code conversations. Use when user says "search conversations", "find that chat", "what did we discuss", "where did we talk about", "look up past session", "find conversation about X", "search history", "what did I ask about", "remember when we", "that discussion about". Also triggers on past-tense questions referencing prior work or possessives without context.

search-conversations

Extraction

Copypython3 ~/.claude/skills/search-conversations/scripts/extract_conversations.py --days 3

Output: Default shows files, tools, errors + conversation. --compact omits metadata.

Time modes: --days N counts from last activity (useful when returning to old projects). --all-projects or --from-today counts from today (calendar-based).

Workflow

1. Identify the lens from user intent (see Routing table below)

2. Extract recent context using the script with lens-appropriate parameters:

   Copypython3 ~/.claude/skills/search-conversations/scripts/extract_conversations.py --days N [flags]
   

   Use the Parameters table to select --days, flags, and any supplementary data to gather.

3. Apply lens questions to analyze the extracted conversations

4. Deepen the search using what you learned from the initial extraction:

   • Extract additional timeframes with the script (--days 30, --all-projects)
   • Search for specific keywords, project names, or patterns that surfaced:

     Copyqmd search "keyword from context" -c conversations -n 15 --files
     

   • Extract those specific paths: python3 ... --paths /found/conv.jsonl

   This step surfaces older context, related discussions, or cross-project patterns that complement the initial extraction.

Keep index updated: Run qmd update periodically to index new sessions.

---

Lenses

Routing

Parameters

--min-exchanges 2 or 3 filters out short sessions and reduces noise.

Core Questions

Follow-ups: find-gaps → suggest learn-anything. extract-decisions → suggest /updateclaudemd.

Supplementary Search Patterns

When recent extraction doesn't surface enough, use these qmd queries to find specific sessions:

---

Synthesis

Principles

1. Prioritize significance — 3-5 key findings, not exhaustive lists
2. Be specific — file paths, dates, project names
3. Make it actionable — every finding suggests a response
4. Show evidence — quotes or references
5. Keep it scannable — clear structure, no walls of text

Structure

Copy## [Analysis Type]: [Scope]

### Summary
[2-3 sentences]

### Findings
[Organized by whatever fits: categories, timeline, severity]

### Patterns
[Cross-cutting observations]

### Recommendations
[Actionable next steps]

Length

Default: 300-500 words. Expand only when data warrants it.