Stream Chain

This is the infrastructure for chaining Claude prompts together where each step feeds into the next. You get two modes: custom chains where you pass your own prompts in sequence, or predefined pipelines for analysis, refactoring, testing, and optimization. The real value is in avoiding the copy-paste loop when you're doing multi-step transformations. Security audits that flow from vulnerability scan to categorization to fixes, or data pipelines that extract, normalize, validate, and report. Each step gets the full output from the previous one as context. The pipelines are opinionated but customizable through config files if you find yourself running the same chains repeatedly. It's streaming JSON under the hood, which matters for longer workflows.

Install to Claude Code

npx -y skills add spencermarx/open-code-review --skill stream-chain --agent claude-code