This is a methodology for breaking down research tasks into 1-5 subtopics, running targeted searches (3-5 per subtopic), then synthesizing everything into a cited answer. It's process guidance, not tooling. You get a three-step framework: plan your subtopics upfront, gather info systematically, then review and synthesize with sources. The value is in forcing you to think before you search rather than going down rabbit holes. Works well for comparative analysis or multi-faceted questions where you'd otherwise just start Googling randomly. If you already research methodically, you probably won't need this. If you tend to over-search or lose track of what you're looking for, the structure helps.
npx -y skills add dougtrajano/pydantic-ai-skills --skill web-research --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
sickn33/antigravity-awesome-skills
moizibnyousaf/ai-agent-skills
github/awesome-copilot