Breaks down research papers into atomic concepts where each piece gets both a math formula and a working code implementation. You trace every definition to specific papers and repos, creating a structured knowledge base that maps theory to practice bidirectionally. Useful when you're reading complex systems papers and need to verify that every mathematical concept actually has corresponding code, or vice versa. The workflow is thorough but rigid: decompose, survey papers for formulas, survey codebases for implementations, then compile everything with explicit gap analysis. Works well for formal methods research where you need rigorous grounding, less so for exploratory work where the mapping isn't clean.
npx skills add https://github.com/lingzhi227/agent-research-skills --skill atomic-decomposition