From tracerelay
Route ongoing research, analysis, investigation, prior-work continuation, schema drift inspection, and memory-backed follow-up tasks into TraceRelay automatically.
How this skill is triggered — by the user, by Claude, or both
Slash command
/tracerelay:task-evolution-memoryThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill for requests that sound like:
Use this skill for requests that sound like:
structure_subject for new structured runs or schema growth.continue_prior_work when the user references prior work on the same subject.inspect_latest_changes when the user wants to understand retries or schema evolution.plan_next_step before any generic search or external action.analyze_information_gaps to confirm whether the current gap is values or structure.prepare_search_queries when you need grounded search terms instead of broad guesses.task_trace when the user wants the full branching view.schema_status when the user asks which keys or relations were added.When the request is obviously about structured continuation or runtime inspection, prefer TraceRelay MCP tools before free-form explanation. Use TraceRelay's gap analysis and query planning before web search so learned facts and missing slots shape the next action.
npx claudepluginhub kawayuta/tracerelay --plugin tracerelayResearches and plans knowledge work tasks like drafting communications, strategic decisions, meeting prep, or analysis projects before execution.
Orchestrates research workflows from question definition to evidence-based findings documentation for technical, requirements, literature, and codebase topics.
Coordinates AI reasoning across complex multi-step tasks using stigmergic signals: managing information freshness, assumption decay, and sub-task output handoff. Activates during long contexts, after compression, or when parallel sub-tasks must converge.