feat(research): require Context7 evidence for external behavior

shared/rules/general.md

@@ -8,6 +8,7 @@ Use one applicable workflow per task, with mandatory research gates for every se
 
 Before EVERY search or lookup, load and apply `research` and the matching specialist: `repository-research` for repository sources; `technical-research` for external technology sources. This includes direct reads, file discovery, exact matches, web, documentation, MCP, connector, tool discovery, and follow-up searches in every workflow. Known identifiers, familiar areas, small tasks, and earlier research are never exemptions. Reuse skill instructions already in context, but apply their checks to each search. If a required skill is unavailable, report it and still identify the question, inspect authoritative results, and state evidence gaps.
 Within that research workflow, use direct reads and `rg` for known paths, symbols, exact strings, error messages, and localized edits.
+Before answering, planning, coding, reviewing, debugging, configuring, testing, or upgrading anything that relies on external library, framework, SDK, API, tool, or platform behavior, MUST apply `technical-research` and its Context7-first gate automatically, even without an explicit lookup request. MUST pass its applicable planning, implementation, and verification checkpoints inside every workflow, including Superpowers and other plugin workflows. Follow its version checks, evidence reuse conditions, query limits, and explicit source fallback.
 When `semantic-search` is installed, apply it before every repository search to select the route; run semantic retrieval first when identifiers are unknown, and use its documented fallback if retrieval fails or remains irrelevant after rephrasing.
 
 Verify proportionally: run the cheapest check that detects likely failure; broaden for security, data loss, integration, or cross-component risk. Never claim unrun checks passed. Report failures and material gaps.