feature-research

Coordinate seven research agents to produce research and feature spec files.

1|Updated Mar 4, 2026
One-click install
npx skills add https://github.com/yandy-r/claude-plugins --skill feature-research
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: feature-research
Source: https://github.com/yandy-r/claude-plugins/tree/main/.cursor-plugin/skills/feature-research
Command: npx skills add https://github.com/yandy-r/claude-plugins --skill feature-research

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Orchestrates a comprehensive feature research workflow by coordinating seven specialized research agents to produce structured research artifacts.

Core Features & Use Cases

  • Parallel research: api-researcher, business-analyzer, tech-designer, ux-researcher, security-researcher, practices-researcher, recommendations-agent produce seven research-*.md files and a feature-spec.md under docs/plans/[feature-name]/.
  • Flexible dispatch: standalone parallel sub-agents by default, or an agent team via --team on Claude Code bundles.
  • Validation and consolidation: outputs are prepared for plan-workflow.
  • Outputs directory scoping: docs/plans/[feature-name]/

Quick Start

Run /feature-research with the desired feature-name and optional flags like --team and --description to start the multi-agent research process.

Frequently Asked Questions about feature-research

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I coordinate multi-agent research for a new software feature?

Multi-agent feature research is coordinated by dispatching seven specialized agents to analyze APIs, business logic, tech design, UX, security, and practices. This produces structured research artifacts and a feature specification under the docs/plans/[feature-name]/ directory.

What is the best way to generate a feature specification before starting development planning?

Generating a feature specification before planning is best done by running parallel research agents that consolidate findings into a feature-spec.md. This ensures all architectural and business requirements are validated before entering the plan-workflow phase.

Can I dispatch research agents as an agent team on Claude Code?

Yes, you can dispatch research agents as an agent team on Claude Code by using the --team flag. Without this flag, the agents run as standalone parallel sub-agents to produce the research documentation.

How do I validate research artifacts for plan-workflow prerequisites?

Validating research artifacts for plan-workflow prerequisites involves consolidating outputs from multiple research agents into structured markdown files. The coordinated workflow automatically prepares these artifacts to satisfy conformance checks before planning begins.

What research dimensions are covered when exploring a new software feature?

Exploring a new software feature covers API integration, business analysis, technical design, UX research, security analysis, development practices, and overall recommendations. Seven dedicated agents independently research these dimensions to ensure comprehensive project scoping.

Does multi-agent feature research require any external dependencies to run?

No external dependencies are required to run multi-agent feature research. The skill operates independently using its internal scripts to orchestrate the research agents and generate the markdown documentation.