This walks you through building a research framework before you dive deep into a topic. It starts by drafting an initial structure from Claude's knowledge, then spins up a web search agent to find recent additions and gaps, and finally outputs two YAML files: one with your research targets and execution config (batch size, parallel agents), another with field definitions organized by detail level. The workflow is pretty rigid about its prompts, which means consistent output but less flexibility if you want to tweak the search strategy. Best for structured competitive analysis or technology comparisons where you need a repeatable framework. Once you have the outline, you'd use the follow-up commands to actually execute the deep research phase.
npx skills add https://github.com/weizhena/deep-research-skills --skill research