Research Workflow
6 articles
Claude Code Skills Get Stale. Audit Them Quarterly.
Skills, memory entries, and hooks decay as models improve. In research, the decay can reach published findings and policy. A quarterly audit protocol.
Building a Literature Surveillance System
Building a literature-surveillance workflow on Google Scholar and Semantic Scholar alerts, with an AI assistant adding the glue and a verification layer.
The Data We Forgot We Had: A Tagging System
Tag datasets by the questions they can answer, not just what they contain. A question-first system makes dormant research data discoverable when new questions…
47 Scripts to 15: Cleaning a Research Codebase
Research projects accumulate code debt. An AI agent can map dependencies, identify dead code, and reorganize months of accumulated scripts, with…
From Methods Paragraph to Working Pipeline with AI
A well-written methodology section is almost executable code, and AI assistants have narrowed the gap between describing a procedure and implementing it.
One Context File: Teaching AI Your Research Project
Every new coding session with AI starts the same way: re-explaining the project. A single CLAUDE.md file loads automatically every session.