dela
5170111823
Rewrite references/pedagogy.md around recite-vs-teach: reader model,
coverage density (sections_in is cite permission, not a to-do list),
intuition-before-formula three-beat, and paper-jump filling.
Every notes/sections/sec-*.tex must now answer gap / takeaway / jump /
omit above the first \section. lint.py checks presence only (it cannot
judge honesty); files opening with "% generated by" are exempt.
- scripts/lint.py: SP025 + is_writer_section / teach_gaps helpers
- tests/no-teach-block/: fixture with takeaway only, wired into test.sh
- examples/*: all 14 writer sections get real teach blocks
- SKILL.md, references/{agents,antipatterns,checklist}.md, DESIGN.md,
assets/notes-template.tex: route writers and consistency agent
through pedagogy.md
3.6 KiB
3.6 KiB
name, description
| name | description |
|---|---|
| superpaper | 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 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), a tensor-shape figure (use supertensor), a standalone rewrite figure (use superderive), or a lecture video (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 / superderive。
本目录是家族母仓库。子仓库在 superfig/、supertensor/、superderive/。
委派一张图时先读对应子目录的 SKILL.md，再画。
契约细节按需加载 references/；schema 在 assets/ledger.schema.yaml。
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),
one tensor-shape figure (supertensor), or one rewrite figure (superderive),
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 | superderive（≤4 步且无 cancel/subst 仍用 align） |
superderive/SKILL.md |
| 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
./scripts/preflight.sh。0 = 全路径，1 = 降级（说出口），2 = 无 LaTeX。./scripts/ingest.sh --work <dir> …（references/input.md）。- 从
assets/ledger.example.yaml写ledger.yaml，再写outline.md，再写正文。 - 写正文：教，不要复述（
references/pedagogy.md）。公式三拍：直觉 →\[/align→ 扁平符号表。 - 按
references/router.md填 figure plan。每张重绘图一份F*.request.md，figure agent 只读它和对应子仓库SKILL.md。 ./scripts/lint.py --work <dir>然后./scripts/build.sh --work <dir>。- 改术语或改图：先改 ledger，再改那一处。
Worked trees: examples/excerpt-toy/（align）、examples/pipeline-delegate/、examples/tensor-delegate/、examples/derive-delegate/。
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：先读 references/pedagogy.md，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、是否复述（pedagogy.md）
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。