parallel-research

Files (1)

• SKILL.md

SKILL.md (first lines)

# Parallel Research

Split a research question only when independent searches are likely to reduce blind spots enough to justify the coordination cost.

## Shape the search

Define the question, the decision it informs, required recency, exclusions, and every material, non-overlapping evidence angle. Ask the user only when the scope is materially ambiguous; otherwise state any consequential assumption and proceed.

Assign one researcher per angle, running as many concurrently as subagent slots allow and launching the remainder as slots open until every angle is covered. Every researcher is a leaf: it must not spawn, delegate, or invoke another research workflow.

## Research in parallel

Each researcher should:

- Search current public sources and prefer primary evidence.
- Vary queries enough to test the angle rather than repeat one search.
- Open key pages and return direct citations, not search snippets.
- Separate sourced facts from inferences and name important gaps or uncertainty.
- Stop when added searching is unlikely to change the conclusion.

## Validate in the main thread

The main thread does not take a research angle. Compare results for agreement, contradiction, and missing coverage. Check numbers, dates, policies, availability, and technical behavior against the strongest primary sources. Downgrade stale, indirect, or single-source claims.

Synthesize the answer around verified findings, unresolved uncertainty, and the decision they support. Cite the underlying sources, never the agents. Save a durable report only when the user asks for one.

From Astro-Han/skills, MIT.

More from Astro-Han/skills