🚨 Prompt engineering 正式宣告过时。
Anthropic 刚刚发布了构建真正能落地的 AI agents 的实战指南。
这是一份长达 30 多页的深度指南,名为《The Complete Guide to Building Skills for Claude》,它悄然将话题从“prompt engineering”转向了真正的执行设计。
以下是核心要点:
Skill 不仅仅是一个 prompt。 它是一个结构化的系统。
你将指令打包到一个 https://t.co/aldvvbZeVI 文件中,可选添加脚本、参考资料和资产,从而一次性教会 Claude 一个可重复的工作流,而不是在每次对话中反复解释。
但真正的解锁关键是他们所称的“渐进式披露”(progressive disclosure)。
它不再将所有信息一股脑塞进上下文中:
• 轻量级的 YAML frontmatter 会告诉 Claude 何时使用该 skill • 完整指令仅在相关时才加载 • 额外文件仅在需要时才访问
减少上下文臃肿。提升精准度。
他们还引入了一个绝佳的比喻:
MCP 给了 Claude 一个厨房。 Skills 则给了它菜谱。
没有 skills:用户连接了工具,却不知道下一步该做什么。 有了 skills:工作流自动触发,最佳实践被内置其中,API 调用变得一致。
他们概述了 3 种主要模式:
1) 文档与资产创建 2) 工作流自动化 3) MCP 增强
他们还强调了大多数构建者都会忽略的一点:测试。
触发准确率。 工具调用效率。 失败率。 Token 用量。
这无关乎巧妙的措辞。
而是关于在 LLMs 之上设计一个执行层。
Skills 可跨 https://t.co/taoTr8bSkU、Claude Code 和 API 使用。一次构建,到处部署。
“只要写个更好的 prompt”的时代正在终结。
Anthropic 刚刚向所有人交出了一份将聊天转化为基础设施的蓝图。
在此下载指南:https://t.co/0SgDRAMhSg
🚨 Prompt engineering is officially outdated.
Anthropic just released the real playbook for building AI agents that actually work.
It’s a 30+ page deep dive called The Complete Guide to Building Skills for Claude and it quietly shifts the conversation from “prompt engineering” to real execution design.
Here’s the big idea:
A Skill isn’t just a prompt. It’s a structured system.
You package instructions inside a https://t.co/aldvvbZeVI file, optionally add scripts, references, and assets, and teach Claude a repeatable workflow once instead of re-explaining it every chat.
But the real unlock is something they call progressive disclosure.
Instead of dumping everything into context:
• A lightweight YAML frontmatter tells Claude when to use the skill • Full instructions load only when relevant • Extra files are accessed only if needed
Less context bloat. More precision.
They also introduce a powerful analogy:
MCP gives Claude the kitchen. Skills give it the recipe.
Without skills: users connect tools and don’t know what to do next. With skills: workflows trigger automatically, best practices are embedded, API calls become consistent.
They outline 3 major patterns:
1) Document & asset creation 2) Workflow automation 3) MCP enhancement
And they emphasize something most builders ignore: testing.
Trigger accuracy. Tool call efficiency. Failure rate. Token usage.
This isn’t about clever wording.
It’s about designing an execution layer on top of LLMs.
Skills work across https://t.co/taoTr8bSkU, Claude Code, and the API. Build once, deploy everywhere.
The era of “just write a better prompt” is ending.
Anthropic just handed everyone a blueprint for turning chat into infrastructure.
Download the guide here: https://t.co/0SgDRAMhSg