一种将原始材料——文章、演讲、框架、近期AI工作或仅仅一个想法——转化为战略性和互动技能的代理技能。这是自下而上的综合，而非内容格式化。

它的作用

技能蒸馏器是一种创造技能的技能。它从四个切入点开始：

来自源材料（/skill-distillery https://example.com/article）——给它一个URL、文件或粘贴内容。它会读取源代码，从下而上提取原则和心理模型，然后与你协作设计技能架构。

来自描述（/skill-distillery）——描述你想要的内容。如果你的描述很详细，它会直接提出一种方法。如果描述模糊，它会和你头脑风暴直到想法清晰。

来自近期工作（/skill-distillery capture）——刚做了AI相关的事情，想保存这个过程？它提取可重复的工作流程、决策点和陷阱，然后将它们打包成可重复使用的技能。

审计现有技能（'/技能-酿酒厂审计~/。

Skill Distillery

An agent skill that turns raw material — articles, talks, frameworks, recent AI work, or just an idea — into strategic, interactive skills. Bottom-up synthesis, not content reformatting.

What it does

Skill-distillery is a skill that creates skills. It works from four entry points:

From source material (/skill-distillery https://example.com/article) — Give it a URL, file, or pasted content. It reads the source, extracts principles and mental models bottom-up, then collaboratively designs the skill architecture with you.

From a description (/skill-distillery) — Describe what you want. If your description is detailed, it proposes an approach directly. If it’s vague, it brainstorms with you until the idea is clear.

From recent work (/skill-distillery capture) — Just did something with AI and want to save the process? It extracts the repeatable workflow, decision points, and gotchas, then packages them as a reusable skill.

Audit an existing skill (/skill-distillery audit ~/.claude/skills/my-skill) — Runs any skill through a seven-lens evaluation framework: rigor and evals, gotchas, synthesis quality, architecture, interactive design, spec compliance, and cross-agent compatibility. Produces a rated assessment with prioritized improvements.

The approach

Most skill creators assume you already know what you want to build. Skill-distillery starts earlier — from raw material — and works bottom-up.

A 5,000-word article doesn’t become a skill by restructuring paragraphs into SKILL.md format. It becomes a skill when you extract the 5 principles that make the approach work, the mental model that organizes the domain, and the decision heuristics someone needs while doing the work. Then you design an interactive architecture around those extracted elements.

The workflow is collaborative: extract → validate → choose a rigor lane → plan evals → propose architecture → build. Every phase has a checkpoint where you confirm before proceeding. The skill suggests interactive patterns from proven skills (discovery phases, mode detection, conditional loading, wait gates) as opinionated defaults you can override.

Skill-distillery now right-sizes the output for three lanes:

• Quick Personal — Lean SKILL.md, 1-3 smoke prompts, no README or publication prep by default
• Team Internal — Shared workflow with enough evals and documentation for safe reuse
• Public Polished — README, eval pack, fresh-agent test, and compatibility review

Best experience on Claude Code

Skill-distillery works with any agent that supports skills, but it’s designed to shine on Claude Code thanks to:

• AskUserQuestion — Tappable multiple-choice options for strategy decisions
• Parallel research agents — Spawns Sonnet agents for fast, scoped research when needed
• Agent tool — Launches specialized subagents for deep research