10x-research

Researches codebases by spawning parallel sub-agents and synthesizing findings into structured documents.

Updated May 20, 2026
One-click install
npx skills add https://github.com/ZawilecxD/trAInR --skill 10x-research-zawilecxd
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: 10x-research
Source: https://github.com/ZawilecxD/trAInR/tree/main/.cursor/skills/10x-research
Command: npx skills add https://github.com/ZawilecxD/trAInR --skill 10x-research-zawilecxd

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Answering questions about a large codebase requires reading many files and tracing connections across components, which is slow and error-prone when done manually. This Skill orchestrates parallel research agents and produces a single, well-structured research document with file:line evidence. ## Core Features & Use Cases - Parallel sub-agent research: Spawns Explore and general-purpose agents concurrently to investigate different dimensions of a question, then synthesizes their findings. - Scope clarification: Asks targeted questions about scope, depth, and focus before researching ambiguous queries. - Structured research documents: Writes a Markdown artifact with YAML frontmatter, code references, architecture insights, and historical context under context/changes/<change-id>/research.md, with optional GitHub permalinks. - Use Case: Ask "how does authentication work in this repo" and receive a comprehensive document tracing the auth flow with exact file:line references and links to prior decisions. ## Quick Start Invoke the 10x-research skill and ask a research question such as how the Supabase authentication flow is implemented across the codebase.

Frequently Asked Questions about 10x-research

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

FAQPage Schema
How do I research a large codebase with AI agents?

Invoke the skill with a research question, and it decomposes the query into research areas, spawns 2-4 parallel sub-agents to explore files and patterns, then synthesizes findings into a structured document with file:line references.

How to generate a codebase research document automatically?

The skill writes a Markdown research document to context/changes/<change-id>/research.md with YAML frontmatter, summary, detailed findings, code references, and architecture insights. It gathers git metadata before writing and never uses placeholder values.

What types of sub-agents does codebase research use?

It uses Explore agents for fast file and pattern searches and general-purpose agents for deep multi-file analysis. Agents run in parallel, each focused on a specific research dimension with requests for file:line references.

Does the research skill work with archived changes?

It reads context/archive directories as supplementary historical context but refuses to write research documents into archived change folders. You must open a new change instead of modifying archived ones.

Can I ask follow-up questions after a codebase research report?

Yes, follow-up questions append a new timestamped section to the same research document. The frontmatter fields last_updated and last_updated_by are refreshed, and new sub-agents are spawned as needed.