Claude Code

What It Covers

Petra Wille shares her first four weeks using Claude Code for content creation, revealing setup challenges, workflow experiments, and debugging processes. Teresa Torres provides troubleshooting guidance on context management, model selection, and building custom tools for writing workflows, comparing Claude Code capabilities to browser-based Claude for newsletter production and research tasks.

Key Questions Answered

• •Context File Architecture: Claude Code requires layered instruction files including global ClaudeMD initialization files plus folder-specific briefings for tone, style, and project details. Setup takes approximately half a day to reach functional performance. Files cascade from global to local directories, making it easy to misconfigure which context Claude actually sees during specific tasks.
• •Model and Mode Selection: Switch models using slash model command to optimize speed and cost. Haiku model handles simple tasks like calendar review and task management significantly faster than default Sonnet. Disable thinking mode for routine work by checking the indicator under the prompt line, as most tasks don't require extended reasoning capabilities.
• •Content Retrieval Excellence: Claude Code excels at searching local files for past content, finding references across books, blog posts, and transcripts that authors forgot existed. This capability proves valuable for user interview analysis, customer service ticket review, and identifying when specific topics were previously discussed. Local file access eliminates document upload limitations present in browser versions.
• •Web Fetch Debugging: When Claude spirals during web searches, stop execution and ask directly what it's doing and why instructions seem confusing. Claude will identify conflicting information in system prompts or ClaudeMD files causing the confusion. This conversational debugging reveals which context elements need adjustment to improve task performance.
• •Custom Tool Development: Build reusable slash commands, sub-agents, and hooks for repetitive workflows like headline generation, SEO analysis with API integration, and fact-checking that validates claims against interview transcripts or research papers. Bundle related tools into plugins. This infrastructure enables rigorous work previously too time-consuming, like maintaining Zettelkasten note systems for literature reviews.