Agent-Skills.md

Agent Skills: research-orchestration

Parallel research agent orchestration dispatching 5-10 concurrent agents for comprehensive multi-source research with synthesis and validation.

UncategorizedID: a5c-ai/babysitter/research-orchestration

Repository

a5c-ai/babysitter
a5c-aiLicense: MIT
1,52087

Install this agent skill to your local

pnpm dlx add-skill https://github.com/a5c-ai/babysitter/tree/HEAD/library/methodologies/claudekit/skills/research-orchestration

Skill Files

Browse the full folder contents for research-orchestration.

Download Skill

Loading file tree…

library/methodologies/claudekit/skills/research-orchestration/SKILL.md

Skill Metadata

Name
research-orchestration
Description
Parallel research agent orchestration dispatching 5-10 concurrent agents for comprehensive multi-source research with synthesis and validation.

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)