Files
superpaper/SKILL.md
T
dela a4017ad44d feat: make SuperPaper the family parent of superfig and supertensor
House the two figure toolkits as git submodules under SuperPaper.
The parent owns paper-note orchestration; children keep their own
history, macros, and lint. DESIGN.md is the family contract.
2026-08-17 09:41:42 +08:00

69 lines
3.1 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
---
name: superpaper
description: >-
Reconstruct a paper's argument thread and write structured Chinese
lecture notes with a claims/symbols/derivation ledger, then route
figures to superfig, supertensor, or (later) superderive. Use when
the user asks for 读论文, 论文笔记, 脉络梳理, 公式推导, 抽象公式图像化,
arXiv notes, paper notes, or $superpaper. Not for drawing a single
architecture figure (use superfig) or a tensor-shape figure (use
supertensor) or for turning a lecture video into notes
(use youtube-render-pdf / bilibili-render-pdf).
---
# superpaper
论文侧的 `youtube-render-pdf`:**编排层**,不是 figure 包。输入一篇论文,输出
`ledger.yaml` + 结构化中文笔记。图一律委派给子仓库,不要在笔记里
`\usepackage{superfig}` / `supertensor`。
本目录是家族母仓库。子仓库在 `superfig/` 与 `supertensor/`(git submodule)。
完整合同见 `DESIGN.md`。笔记脚手架(`scripts/`、模板、schema)按 DESIGN 的 PR 1 落地;在此之前按下面路由手工委派。
## When to use
- 读论文、梳理脉络、展开公式推导、把抽象公式变成图。
- 需要一张以上的图,或需要符号表 / claim 覆盖。
Do **not** use when the user only wants one architecture figure (`superfig`)
or one tensor-shape figure (`supertensor`), or when the source is a lecture
video.
## Route figures (do not draw here)
| 信号 | toolkit | 子仓库 |
|---|---|---|
| 架构 / 流水线 / 数据流 / 状态 / 依赖 / 谁吃谁 | `superfig` | `superfig/SKILL.md` |
| 轴、形状、转置、broadcast、gather、分片、收缩 | `supertensor` | `supertensor/SKILL.md` |
| 必须被看见的逐步改写 | v1:笔记 `align`;v2:`superderive` | — |
| 数值曲线 / 柱状 / 散点 | screenshot 或 matplotlib | 本家族不画 |
| 表 / 照片 / 装置 / UI | screenshot | — |
混类信号拆成下一整数 id,禁止 `F1a`。默认偏向不出图。
## Workflow
1. 读 `DESIGN.md` 的输入契约与 ledger schema。
2. 先写 `ledger.yaml`(claims / symbols / derivations / figure plan),再写笔记。
3. 公式三拍:中文动机 → `\[` / `align` → 扁平符号表。
4. 每张计划图写一份自包含 `F*.request.md`,开一个 figure agent,**只**把对应子仓库的 `SKILL.md` 给它。
5. 笔记用 PDF `\includegraphics` 嵌入子仓库产物。禁止 `\input` standalone 源。
6. 改术语或改图:先改 ledger,再改那一处。
## Spawn recipe
```
$superpaper <源> 请 spawn 多 sub agents,隔离上下文:
- 1 个 outline agent:写 ledger.yaml + outline.md + 节边界
- N 个 writer agents:各写 sections/sec-XX.tex,引用 ledger id
- 每个计划重绘图 1 个 figure agent:只读 F*.request.md,调用对应子仓库 skill
- 1 个 consistency agent:符号、术语、claim 覆盖、路由一致性
```
必须拆 agent 当且仅当:正文 > 12 页,或顶层节 > 4,或重绘图 ≥ 2,或用户显式要求 spawn。
## Output
`ledger.yaml`、`notes.tex` / `notes.pdf`、各图的 PNG 预览 + `.tex` + 向量产物。
交付时说明哪些图走了哪个子仓库。