context-engineering-advisor
仓库创建 2026年2月5日最近提交 9 天前SkillHot 收录 20 天前
▸ 精选理由
把零散上下文转为可控检索与短期记忆策略,提升代理可靠性。
这个 Skill 做什么
诊断并纠正上下文堆砌问题,提供边界、检索与结构化上下文实践。
帮你判断是把上下文堆一堆(context stuffing)还是有意识地组织(context engineering),并给出边界划分、检索与结构化上下文的实操建议。当 AI 工作流变得臃肿、难以控制或经常出错时拿来用。特点是提供战术层面的修复方法,比如有界域、episodic retrieval 和 Research→Plan→Reset→Implement 循环。
▸ 展开 SKILL.md 英文原文
Diagnose context stuffing vs. context engineering. Use when an AI workflow feels bloated, brittle, or hard to steer reliably.
6.0k
Stars
735
Forks
40
仓库内 Skill
+382
7 日增星
安装 / 使用
给你的 Agent 一句话(通用)
帮我安装这个 skill:https://raw.githubusercontent.com/deanpeters/Product-Manager-Skills/main/skills/context-engineering-advisor/SKILL.md或 curl 直取 SKILL.md
curl -fsSL "https://raw.githubusercontent.com/deanpeters/Product-Manager-Skills/main/skills/context-engineering-advisor/SKILL.md"SKILL.MD 节选查看完整文件 ↗
## Purpose
Guide product managers through diagnosing whether they're doing **context stuffing** (jamming volume without intent) or **context engineering** (shaping structure for attention). Use this to identify context boundaries, fix "Context Hoarding Disorder," and implement tactical practices like bounded domains, episodic retrieval, and the Research→Plan→Reset→Implement cycle.
**Key Distinction:** Context stuffing assumes volume = quality ("paste the entire PRD"). Context engineering treats AI attention as a scarce resource and allocates it deliberately.
This is not about prompt writing—it's about **designing the information architecture** that grounds AI in reality without overwhelmivia SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有