briesearch

/briesearch

/briesearch has two contexts:

• User-invoked context. The user requests research. Produce the report that ## Output defines.
• Internal tier-2 context. /cheese starts /briesearch silently when its clarity check needs external context. Return one line for the mini-spec ## Provenance section. Write the full cited research to research/<slug>/<slug>.md in the durable corpus. Derive the slug from the parent mini-spec slug. Link the artifact path from the mini-spec. This link preserves citations and prevents repeated research. Skip the durable write only when you fetch no source.

Do not use this skill for one clear file lookup. Do not use it when the user already has sufficient evidence.

Inputs

Accept the complete user prompt as the research question. Ask one question only when missing criteria change the source plan. Use the shared transport in ../cheese/references/ask-user-question.md. Otherwise state the assumptions. Then continue the research.

Flow

1. Classify. Identify the required source types and research method.
2. Plan. Use a compact freshness plan for one time-sensitive fact. Use the full plan for comparisons, best practices, reports, or questions with multiple parts. Define decisions, constraints, subqueries, and stop criteria. See references/query-planning.md.
3. Route. Select the required capabilities and one provider for each capability. Follow references/routing.md. Then emit the routing block. Run each capability marked YES through its selected provider or an explicit fallback.
4. Gather. Prefer native easy-cheese helpers and backends when they are available. Otherwise, select one equivalent provider. Load only the selected provider tools when the harness defers schemas. Fetch independent capabilities in parallel when the harness supports parallel work. Send heavy fetches to a research sub-agent. See ## Sub-agent context gate. Verify cited URLs with the selected provider tool. Select an explicit fallback provider when that tool cannot retrieve a URL. See references/routing.md § Provider tool sets. Record each call in the capture manifest immediately. Include the provider, tool, and status. Declare the call budget before the first call. Do not repeat a logged search. Do not extract a logged URL again.
5. Synthesize. Build the claim evidence table from references/synthesis.md. Verify each link. Apply the confidence cap. Run ground-check and budget-check for a deep report. Compare the conclusion with the raw evidence.
6. Stop. Hand off the result. Do not implement the result. Do not turn citations into design choices. The next skill uses the report. Treat source alternatives as open questions, not recommendations. See the alternatives section in references/synthesis.md. Implement only when the current prompt explicitly requests research-informed implementation.