---
name: Maestro Knowhow
slug: maestro-knowhow
category: AI Engineering
description: Maestro Knowhow captures reusable knowhow into .workflow/knowhow/ from an intent you provide. It infers the content type, extracts the content, and writes the entry using the workflow instructions.
github: "https://github.com/catlog22/maestro-flow/tree/master/.codex/skills/maestro-knowhow"
language: TypeScript
stars: 530
forks: 65
install: "npx degit https://github.com/catlog22/maestro-flow/tree/master/.codex/skills/maestro-knowhow ~/.claude/skills/maestro-knowhow"
installs_to: ~/.claude/skills/maestro-knowhow
source_path: .codex/skills/maestro-knowhow/SKILL.md
collection_size: 25
category_size: 2451
collection_url: "https://dirskills.com/collections/catlog22/maestro-flow"
added: 2026-08-26T05:11:53.270Z
last_synced: 2026-08-26T05:11:53.270Z
canonical_url: "https://dirskills.com/skills/maestro-knowhow"
---

# Maestro Knowhow

Maestro Knowhow captures reusable knowhow into .workflow/knowhow/ from an intent you provide. It infers the content type, extracts the content, and writes the entry using the workflow instructions.

**Install:**

```bash
npx degit https://github.com/catlog22/maestro-flow/tree/master/.codex/skills/maestro-knowhow ~/.claude/skills/maestro-knowhow
```

## README

<purpose>
Intent-driven knowhow precipitation path (沉淀路径) — captures reusable knowledge into `.workflow/knowhow/`. No fixed grammar — state your intent; the `knowhow` step infers the content type and extracts the content. Type keywords still work as deterministic shortcuts:

| Type | Keywords | Prefix |
|------|----------|--------|
| session | `session` / `compact` / 压缩 | KNW- |
| template | `template` / `tpl` / 模板 | TPL- |
| recipe | `recipe` / `rcp` / 配方 / 步骤 | RCP- |
| reference | `reference` / `ref` / 参考 | REF- |
| decision | `decision` / `dcs` / `adr` / 决策 | DCS- |
| tip | `tip` / `note` / 技巧 / 记录 | TIP- |
</purpose>

<dispatch>
Read `~/.maestro/workflows/knowhow.md` and follow the execution document directly. Do not create a Session or Run just to load this document.

Pass the full `$ARGUMENTS` to the workflow as its intent (the first `capture` argument is implied). The workflow infers the content type, extracts the content, and writes the entry.
</dispatch>