research

Coordinate parallel codebase, web, and constraints research into structured findings.

1|Updated Apr 1, 2026

Search Tags:#research #multi-agent #orchestration #lifecycle #claude-code #cortex

Ready to run

npx skills add https://github.com/charleshall888/cortex-command --skill research-charleshall888

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: research
Source: https://github.com/charleshall888/cortex-command/tree/main/plugins/cortex-core/skills/research
Command: npx skills add https://github.com/charleshall888/cortex-command --skill research-charleshall888

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Parallel research orchestration across Codebase, Web, and Requirements & Constraints to produce structured findings and streamline decision-making for Cortex Core initiatives.

Core Features & Use Cases

Core angle dispatch: always runs Codebase, Web, and Requirements & Constraints angles in parallel, with orchestrator-chosen extras for diverse insights.
Lifecycle mode vs standalone: writes to cortex/lifecycle/{lifecycle-slug}/research.md when a slug is provided; otherwise returns a concise in-chat synthesis.
Configurable scope: accepts topic, tier, and criticality to shape depth and breadth of investigation and outputs.
Use cases: planning feature work, evaluating architecture decisions, vetting research directions before committing to implementation.

Quick Start

Provide a topic and, optionally, a lifecycle-slug to persist results; the skill will dispatch research angles and present a synthesized report.

Frequently Asked Questions about research

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

FAQPage Schema

How do I orchestrate multi-angle research across my codebase and the web?▼

Multi-angle research orchestration runs Codebase, Web, and Requirements & Constraints angles in parallel to produce structured findings. The orchestrator dispatches agent prompts for each angle and synthesizes the results into a structured report.

What is the best way to evaluate architecture tradeoffs before implementation?▼

Evaluating architecture tradeoffs requires coordinated research across codebase constraints, web sources, and project requirements. Dispatching parallel research angles generates angle-based findings that highlight tradeoffs to streamline decision-making.

How do I persist research findings to a lifecycle path in Claude Code?▼

To persist research findings in Claude Code, provide a lifecycle-slug when initiating research. The tool writes the synthesized report directly to cortex/lifecycle/{lifecycle-slug}/research.md for lifecycle tracking.

Can I configure the scope and depth of parallel research tasks?▼

Yes, research scope and depth are configurable by providing a topic, tier, and criticality. These parameters shape the breadth and depth of the investigation, allowing the orchestrator to choose extra research angles for diverse insights.

Do I need a lifecycle-slug to run a research synthesis?▼

No, a lifecycle-slug is optional for running research synthesis. Without a slug, the tool returns a concise in-chat synthesis directly in the conversation instead of writing a markdown file to the lifecycle path.