Web Research provides a disciplined, reproducible process for multi-source web investigations. The skill enforces a planning step (create a research folder and research_plan.md), decomposes work into distinct subtopics, and spawns research subagents that perform bounded web searches and write findings to local files. After subagents finish, the skill guides synthesis into a coherent, cited report.
Use this skill for complex information-gathering tasks where sources must be tracked, findings must be auditable, and results require synthesis — for example competitive analyses, literature surveys, or investigative summaries. It’s valuable when you need clear provenance and repeatable workflows.
Intended for agent runtimes with web_search, file I/O, and task/subagent spawning capabilities. Works well with CLIs or agent frameworks that provide controlled web access and local file tools.
This skill has not been reviewed by our automated audit pipeline yet.