Research

Delegate noisy investigation work to subagents so your context window stays clean. When you need to answer "how does X work" or "what broke in this test run" by reading twenty files, send a subagent to do the digging and get back a distilled answer with evidence instead of polluting your context with seventeen irrelevant files. The key insight is simple: your context is your most limited resource, and reading everything to find the relevant bits permanently degrades your subsequent decisions. Use this liberally for log analysis, codebase surveys, and PR summaries. Skip it when you need to edit the files anyway or when it's just a quick grep.

skills.sh installs: 22K
GitHub stars: 684
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add warpdotdev/common-skills --skill research --agent claude-code

Installs into .claude/skills of the current project.

Files

Research

Use this skill to answer a question by delegating the work of finding the answer to a subagent, so that the byproducts of that work — file contents, log noise, dead-end reads — never enter your own context. You get back a distilled answer plus the evidence that supports it, and you stay sharp for the actual task.

Why this matters

Your context window is your most valuable and limited resource. Reading twenty files to discover that three of them mattered permanently pollutes your context with seventeen files of noise, degrading every subsequent decision you make. A subagent absorbs that noise on your behalf and hands you only the signal. Think of it as asking a colleague to dig through the archives and report back, rather than dumping the whole archive on your desk.