research-orchestration
Research Orchestration dispatches 5 to 10 concurrent research agents to investigate multi-source queries across codebase files, documentation, and configurations simultaneously. Use this skill for comprehensive analysis of complex topics, unfamiliar codebase sections, or before creating specifications, achieving up to 90% faster results than sequential research through parallel execution with synthesis and validation.
git clone --depth 1 https://github.com/a5c-ai/babysitter /tmp/research-orchestration && cp -r /tmp/research-orchestration/library/methodologies/claudekit/skills/research-orchestration ~/.claude/skills/research-orchestrationSKILL.md
## Process Flow 1. **Plan**: Decompose query into independent sub-queries 2. **Dispatch**: Run 5-10 research agents in parallel 3. **Synthesize**: Merge findings, identify consensus and conflicts 4. **Validate**: Cross-reference against codebase for accuracy ## Sources - Codebase: source files, patterns, implementations - Documentation: README, JSDoc, inline comments - Configuration: package.json, tsconfig, CI/CD configs ## Confidence Scoring Overall confidence is a weighted average of individual agent confidence scores, adjusted by validation results. Below 70% triggers human review. ## When to Use - `/research [query]` slash command - Before specification creation - When investigating unfamiliar parts of the codebase ## Processes Used By - `claudekit-research` (primary consumer)
Review TypeScript code changes for consistency, type safety, and monorepo patterns across babysitter packages
Generate and validate documentation for @a5c-ai/babysitter-sdk CLI commands and exported APIs
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.