Step-by-step implementation of deep research using the Claude Code agent framework! Powerful and simple skills. I explain how to implement deep research step by step, because deep research is the first application of an agent framework. Comparing how different frameworks implement deep research reveals which framework is truly powerful.
11 files for Claude Code: deep-research, plan-research, refine-question, synthesize-findings and 7 more — 1,589 tokens loaded in every session.
CLAUDE.md A 1,589 tok .claude/skills/citation-validator/SKILL.md A 58 tok .claude/skills/got-controller/SKILL.md A 62 tok .claude/skills/question-refiner/SKILL.md A 69 tok .claude/skills/research-executor/SKILL.md A 55 tok .claude/skills/synthesizer/SKILL.md A 65 tok .claude/commands/deep-research.md A 18 tok .claude/commands/plan-research.md A 18 tok .claude/commands/refine-question.md A 16 tok .claude/commands/synthesize-findings.md A 13 tok .claude/commands/validate-citations.md A 13 tok These files are liangdabiao/Claude-Code-Deep-Research-main's own configuration — they tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.