Explore skills

Use when the user asks how to do something, wants a skill for a task, or wants to discover and install new agent capabilities.

Use when a task spans multiple files or workstreams and benefits from parallel implementation by an agent team.

Create, load, or summarize tasks via Graphiti MCP; triggers on 'tasks', 'list tasks', 'add task', usable by any model (Claude, Gemini).

Use when executing a multi-task plan where each task is independent, or when the user wants parallel or isolated task execution with review.

Lisa - intelligent assistant for memory and tasks. Triggers on 'lisa', 'hey lisa', or addressing lisa directly.

Use this skill when the user wants to plan a piece of implementation work and add it to the lauren queue (the lauren todo / backlog). Typical phrasings include "add this to lauren", "add this to the lauren todo", "lauren this", "let's make a lauren plan for X", or "plan this with lauren". The plan is then executed end-to-end by `lauren vibe` in the background.

Use when the user wants a changelog, release notes, or asks what changed since the last release.

Diagnostic-and-fix pipeline for systematic context engineering — fix agent context, context engineering, context optimization pipeline, diagnose context problems. Chains context-fundamentals (attention, budgeting), context-optimization (KV-cache, partitioning, observation masking), context-compression (summarization, anchored iterative, tokens-per-task), context-degradation (lost-in-middle, poison

Design Gmail, Drive, Sheets, and Calendar automations with scope-aware plans. Use for repeatable daily task automation with explicit OAuth scopes and audit-ready outputs.

Delegate complex tasks to OpenCode subagent, use when >=2 file modifications or batch operations

NotebookLM connector skill pack for Claude Code and Codex CLI. It enables direct Q&A queries on your Google NotebookLM content via MCP, with options to export and manage sources, triggered by phrases like "connect NotebookLM" or "use NotebookLM in Claude Code".

Use when the user invokes /board or wants to view, create, move, or manage tasks on the Harness Board.