breadth-reader

To summarize a large codebase quickly, you need an automated tool that scans directories and surfaces structural hotspots. This skill automates that process by spawning parallel Explore subagents to review files and produce a concise, structured synopsis for fast onboarding.

Exploring and summarizing large documentation sets at scale requires parallel breadth task execution. This skill utilizes a fork-context environment to spawn subagents that concurrently read and review documentation, generating a high-level summary that reduces manual surveying time.

Running parallel breadth tasks for data exploration requires a fork-context environment. The execution setup must also provide the Read, Glob, Grep, Bash, and Task toolset to enable the Explore subagents to perform concurrent analysis on your datasets.

Yes, you can use subagents to review datasets and surface key content hotspots. The skill spawns Explore subagents that apply parallel analysis across your data sources, identifying structural patterns and delivering a high-level synopsis for quick decision-making.

Fork-context parallelism for scanning large data sources works by spawning multiple Explore subagents simultaneously. Each subagent handles a slice of the review and exploration process, which aggregates into a structured summary without overwhelming manual cognitive load.