From memorylane
Summarizes recent screen activity by grouping into apps and tasks with time estimates from MemoryLane timeline. Widens search if no recent data.
npx claudepluginhub deusxmachina-dev/memorylane --plugin memorylaneThis skill is limited to using the following tools:
Summarize the user's recent screen activity.
Generates time reports grouped by client/project from screen activity timelines, estimating block durations for timesheets and billing.
Synthesizes user's recent work activity, contributions, projects, and accomplishments using Glean's user_activity, memory, search, and meeting tools.
Analyzes conversation histories from AI tools (Claude, Codex, Gemini, Qwen, Cursor) to generate themed daily/period work summaries filtered by date or time window.
Share bugs, ideas, or general feedback.
Summarize the user's recent screen activity.
Call browse_timeline(startTime="30 minutes ago", endTime="now", limit=50, sampling="recent_first").
browse_timeline(startTime="2 hours ago", endTime="now", limit=50, sampling="recent_first").From the returned entries:
Only call get_activity_details(ids) when a summary is ambiguous and the exact on-screen text would genuinely help clarify what the user was doing. Do not fetch OCR speculatively.
Format as a brief narrative followed by bullet points:
**Last 30 minutes** (N activities recorded)
You were primarily working on [main task].
- **[App Name]** (~X min) — [what you were doing]
- **[App Name]** (~X min) — [what you were doing]
If the results came from the wider 2-hour window, adjust the heading accordingly.
get_activity_details for ambiguous cases.search_context(query) if the user asks follow-up questions like "what was I doing in Chrome?" or "find that thing I was reading about X".recent_first sampling is used instead of uniform because the user cares most about what just happened, and the window is short enough that uniform sampling would not add value.