Claude Code

24 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.

May 2026 · Methodology

What AI Impact Looks Like in the Slow Data

Usage telemetry sees AI adoption; slow public data sees household conditions. The same AI tooling can read both at the cadence either one needs.

May 2026 · Methodology

A Pre-Analysis Plan for Your Coding Agent

A three-layer architecture for keeping reasoning agents disciplined: rule, gate, and verification.

May 2026 · Methodology

Building a Literature Surveillance System

Free tools like Google Scholar alerts and Semantic Scholar already monitor academic literature. What an AI coding assistant adds is the glue: combining sources, following citation networks, and catching the quiet failures that make AI-gathered references dangerous.

Apr 2026 · Methodology

Connecting Claude to Outside Services: FRED, Census, and Beyond

How to connect Claude Code to external data sources like FRED, Census, and Google Scholar, bringing integrated research workflows into natural conversation.

Mar 2026 · Methodology

Hooks: Automation Without Asking

Hooks are automatic triggers that run without asking - like auto-save, but for research tasks. A power-user feature, entirely optional.

Mar 2026 · Methodology

Reading Our Analysis Files: How Claude Sees Our Research Code

How Claude Code explores research projects using three core tools: Read (look at a file), Glob (find files by pattern), and Grep (search inside files).

Feb 2026 · Methodology

Why It Forgot Everything: Understanding Context

Understanding how AI context windows work, why sessions reset, and how to work with this fundamental limitation of large language models.

Feb 2026 · Methodology

Reading Your Own Data: What Claude Code /insights Reveals at Every Stage

How to interpret your Claude Code /insights report at beginner and intermediate levels - same data, different lessons.

Feb 2026 · Methodology

Your First Session: What Claude Code Is and Isn't

A practical walkthrough of what Claude Code can and cannot do, with prompting patterns and a complete first-task example.

Feb 2026 · Methodology

Monitoring Government Data Portals

A case study in tracking California health data releases with Claude Code.

Jan 2026 · Methodology

Staging LinkedIn Posts with Browser Automation

A case study in form-filling workflows that keep humans in the loop. Browser automation handles navigation and data entry while the human retains final approval.

Jan 2026 · Methodology

Context Window Budgeting: Treating Tokens as a Finite Resource

Treating tokens as a finite resource, and knowing when to spawn agents versus work directly.

Jan 2026 · Methodology

End-of-Session Hygiene: What to Capture Before Context Resets

What to capture before context resets, and how five minutes of capture saves twenty minutes tomorrow.

Jan 2026 · Methodology

Creating Skills for Research

Skills are recipe cards for research tasks. Write the steps once, save them in a file, and Claude Code follows those instructions whenever needed.

Dec 2025 · Methodology

Building Our Research System: Putting It All Together

How CLAUDE.md, skills, hooks, and MCP servers combine into a personal research system that becomes more valuable over time. Part 5 of the Advanced Tier series.

Dec 2025 · Methodology

Creating Helpers: When to Delegate Work

When to create separate Claude Code helpers for focused work, how to design tasks that are easy to hand off, and patterns for running multiple helpers at the same time.

Dec 2025 · Methodology

The Cold Start Problem: Why the First Five Minutes Matter Most

Why the first five minutes of an AI session matter most, and how CLAUDE.md solves the context problem.

Dec 2025 · Methodology

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 counterfactual tests to verify nothing broke.

Nov 2025 · Methodology

Robust API Collection: Pagination, Rate Limits, Failure Recovery

Collecting location data from Google Places API at scale requires handling rate limits, pagination, and failure recovery. A naive script fails in predictable ways.

Nov 2025 · Methodology

400 Labels to 94% Accuracy: Validating Grocery Store Data

Google Places returned thousands of 'grocery stores.' Many weren't. Here's how a classifier separates real grocery stores from gas stations and liquor stores.

Oct 2025 · Methodology

7 Copy-Paste Cycles to 1 Command: What Changes with Agent-Based Coding

The difference between chatbot-based coding and agent-based coding is categorical, not incremental. Here's what changes when AI can read your entire codebase.

Oct 2025 · Methodology

From Methods Paragraph to Working Pipeline: AI-Assisted Implementation

A well-written methodology section is almost executable code. The gap between describing a procedure and implementing it has narrowed dramatically with agent-based coding tools.

Oct 2025 · Methodology

One Context File, Zero Re-Explanations: 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. Write the context once; the agent reads it every time.

Sep 2025 · Methodology