What problem does it solve?
It solves the problem of insufficient or single-thread external knowledge when building a math modeling solution, where multiple domain angles (methods, theory, industry context, sensitivity analysis) must be retrieved and cross-validated.
Core Features & Use Cases
- Parallel specialist external knowledge gathering: Runs 2–3 specialist research queries in multi/hybrid mode to cover different knowledge needs at once.
- Compact, decision-ready evidence summaries: Produces a short summary capped in length per specialist plus DOI/URL lists for traceable sources.
- Conflict-aware aggregation: Keeps all findings when specialists disagree and labels the controversial points for later modeler/writer review.
- Graceful fallback strategy: If the host skill is unavailable or specialists fail, it degrades to sequential retrieval such as paper-search or webcrawl.
Quick Start
Use the external-context skill in multi or hybrid mode to ask several specialists to search for the model's classic literature, the problem domain's industry benchmarks, and sensitivity-analysis methods, then collect the aggregated output in the workdir path workdir/{task_id}/refs/external_context.md.