Steer decisions, not prompts.A decision layer for coding agents.Decide once. Every build follows. tl;drA Claude Code skill. It captures the decisions you make as you talk and build, across sessions, and asks you only about new ones that are hard to undo or felt by users. Sessions → none of them knows what the others decided. Prompts → prompt hell. You re-steer the same calls, prompt after prompt. Specs → spec-driven dev. The spec is stale by build two. Back to prompting. Decisions → signals. Decided once, it steers every build after. Decisions, not diffs. Only the ones hard to undo, or felt by users. Each keeps its why. And what was ruled out, so agents stop re‑arguing it. You stay at the top. Never variable names. Single player, for now. Get started · ~1 min · needs Claude Codecopy $ npx skills add smarchone/signals -g # then, in Claude Code: > /signals why sqlite? # answers from your decisions > /signals build the first slice # builds what you discussed > /signals exec drop sqlite for pg # the panel argues, you decide made with ♥ · @smarchone/signals
AI NEWS JOURNAL
Hacker News Show HNAI NEWS / JOURNAL
Show HN: A simple decision layer for coding agents
memory workflow for decisions (why's & why not's) Comments URL: https://news.ycombinator.com/item?id=50602894 Points: 1 # Comments: 0
翻訳サービスが停止中のため原文を表示しています。