research-orchestration
SkillAI & modelsThis skill lets your AI split a research question across several smaller research agents that work at the same time. Their findings are combined into one report and validated before you see the result. It suits broad questions that need input from multiple sources.
Available today. Use it from your connected AI after setup.
No other account needed.
Add the skill, then ask your AI to research a topic. It will distribute the work across parallel research agents and return one combined, validated report.
Then ask your AI: use the research-orchestration skill
What your AI can do with it
- Run 5 to 10 research agents in parallel on a single question
- Gather information from multiple sources in one pass
- Combine the agents' findings into a single synthesized report
- Validate the results before presenting them
- Cover broad topics from several angles in a single request
What this skill tells your AI
The instructions your AI receives, as published by a5c-ai/babysitter in library/methodologies/claudekit/skills/research-orchestration/SKILL.md and read by ahel’s review.
Process Flow
- Plan: Decompose query into independent sub-queries
- Dispatch: Run 5-10 research agents in parallel
- Synthesize: Merge findings, identify consensus and conflicts
- 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)
Signals
- GitHub stars
- 2k
- Forks
- 106
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
research-orchestration- Source
- github.com/a5c-ai/babysitter