Move the Prompt Tools API Into Your Own Scripts Before Workbench Closes on August 17
The legacy Workbench and three experimental prompt endpoints shut down on August 17, 2026. Here is how to count what actually depends on them, plus working local replacements for templatize_prompt and improve_prompt with real output.
When Instructions Fade in Long Conversations: Measuring Adherence and Pulling It Back
System-prompt instructions quietly lose their grip as a conversation grows. This piece turns that drift into a number you can track, then fixes it with prompt structure and mid-conversation re-anchoring, backed by runnable code and measured results.
When the Same Model Name Starts Behaving Differently: A Startup Canary for Unattended Pipelines
An in-place Opus upgrade can change your output, and an unattended publishing pipeline will never notice. Here is a lightweight startup canary that fingerprints behavior, catches drift, and halts the batch — with measured cost and latency.
Designing Skills That Stabilize Output: Template Fixing and Decision Guides in Claude Code
A practical design guide for stabilizing wobbly Claude Code skill output: stating when to use it, decision-guide tables, fixing quality with references templates, and traceability rules, with code from real operations.
Holding the Line on Claude's Output Shape With <output_format> — A Pattern From My Indie App Copy Pipeline
How I keep multilingual App Store copy from drifting across 100+ locales by leaning on the <output_format> tag, with the prompts and validators I actually run.
Writing Effective Custom Instructions for Claude Projects
A practical guide to writing Claude Projects custom instructions that actually shape Claude's behavior — covering role definition, output constraints, and project-specific context sharing.
9 Practical Claude System Prompt Examples — Templates That Work in Production
Nine production-ready Claude system prompt templates for support, code review, JSON extraction, education, persona consistency, and more — with the design rationale for each pattern.
Read Your Own Code as Someone Else's: Coaxing Tougher Reviews from Claude Code
When you review code you just wrote, the rough edges become invisible. Here's how I summon Claude Code as a mid-career engineer reading someone else's code, plus the prompts I actually use in production.
Turning Claude Code Into a Design Sparring Partner
How to use Claude Code as a sparring partner for design decisions rather than a code generator. The questioning craft I have refined while running four sites and several apps as a solo developer.