How this skill is triggered — by the user, by Claude, or both
Slash command
/b17z-sage:sage-memoryThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
When saving to Sage (checkpoints or knowledge), **always use a background Task** to avoid blocking the conversation for 2-5 seconds.
When saving to Sage (checkpoints or knowledge), always use a background Task to avoid blocking the conversation for 2-5 seconds.
Task(subagent_type='general-purpose', model='haiku', run_in_background=true,
prompt='Call sage_save_checkpoint with core_question="...", thesis="...", confidence=0.X, trigger="...". Return the result.')
Use background Task for these MCP tools:
sage_save_checkpoint - Full research checkpointsage_save_knowledge - Persist reusable insightsage_autosave_check - Auto-checkpoint at breakpointsThese operations generate embeddings (2-5 seconds). Running them directly blocks the conversation. The background Task pattern:
# WRONG - blocks conversation
sage_save_checkpoint(core_question="...", thesis="...", confidence=0.8)
# RIGHT - non-blocking
Task(subagent_type='general-purpose', model='haiku', run_in_background=true,
prompt='Call sage_save_checkpoint(...). Return result.')
npx claudepluginhub joshuarweaver/cascade-featured --plugin b17z-sageGuides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Resolves in-progress git merge or rebase conflicts by analyzing history, understanding intent, and preserving both changes where possible. Runs automated checks after resolution.