Claude Opus 5 на кейсе «Пирамида готовой записки»: с Minto лучше по обеим мерам
Структура 7 → 8 из 8 +1 Качество 9 → 10 из 10 +1
Судья об ответе с Minto
The pyramid is complete and faithful; the additional ribbon and gap notes do not displace the requested diagram.
| Структура | Без Minto 7 | С Minto 8 | Изменение |
|---|---|---|---|
| Вершина | 2 | 2 | |
| Состав ключевой линии | 2 | 2 | |
| Уровни | 1 | 2 | +1 |
| Порядок и род | 2 | 2 |
| Качество | Без Minto 9 | С Minto 10 | Изменение |
|---|---|---|---|
| Вершина | 2 | 2 | |
| Однородные группы | 2 | 2 | |
| Объяснимый порядок | 2 | 2 | |
| MECE | 1 | 2 | +1 |
| Видимая соразмерная структура | 2 | 2 |
Ответы моделей и слова судьи приведены в оригинале, по-английски.
Без Minto
контрольный промпт · слепая меткаout-04invented_factsunacknowledged_source_loss- качество со штрафом рубрики 8/10
The top is cluttered with contextual evidence, while the methods study and test-monitoring details disappear.
┌─────────────────────────────────────────────┐
│ TTW can cut composing cost substantially │
│ (composition = 40% hardback / 50-55% │
│ paperback cost; seen as uncompetitive) │
└──────────────────────┬──────────────────────┘
│
┌────────────────────────┴────────────────────────┐
│ │
┌─────────────┴──────────────┐ ┌─────────────┴──────────────┐
│ 1. Remove unnecessary │ │ 2. Raise wages to the │
│ process stages │ │ local market level │
└─────────────┬──────────────┘ └─────────────┬──────────────┘
│ │
┌─────────────┼─────────────┐ ┌───────────┬─────────┼─────────┬───────────┐
│ │ │ │ │ │ │ │
┌───┴────┐ ┌─────┴─────┐ ┌────┴────┐ ┌────┴────┐ ┌────┴────┐ ┌─┴─────┐ ┌─┴──────┐ ┌──┴─────┐
│Trails │ │Every │ │Test │ │Pays │ │Cannot │ │Dept. │ │Union │ │Compet- │
│bench- │ │title gets │ │simple │ │less than│ │hire or │ │under- │ │claim │ │itive │
│mark by │ │the same │ │jobs │ │nearby │ │retain │ │staffed│ │may │ │pay │
│20-50% │ │checks │ │next week│ │printers │ │compos- │ │→ late │ │force │ │enables │
│ │ │regardless │ │with │ │ │ │itors │ │work, │ │pay rise│ │hiring, │
│ │ │of │ │fewer / │ │ │ │(two just│ │over- │ │anyway │ │removes │
│ │ │complexity │ │retimed │ │ │ │left) │ │time │ │ │ │overtime│
│ │ │ │ │checks; │ │ │ │ │ │>50% │ │ │ │premium │
│ │ │ │ │saving up│ │ │ │ │ │over │ │ │ │ │
│ │ │ │ │to 10% │ │ │ │ │ │budget │ │ │ │ │
└────────┘ └───────────┘ └─────────┘ └─────────┘ └─────────┘ └───────┘ └────────┘ └────────┘Introduction (S-C-Q):
- Situation: Composing is 40% of hardback and 50–55% of paperback cost.
- Complication: TTW does not know whether that cost is excessive, but customers call it uncompetitive on simple jobs.
- Question: Can composing cost be reduced?
- Answer (governing thought): Yes — substantially, by removing unnecessary stages and paying market wages.
С Minto
промпт с навыком · слепая меткаout-12Жёстких провалов нет
The pyramid is complete and faithful; the additional ribbon and gap notes do not displace the requested diagram.
flowchart TD
A["▲ TTW can cut composing cost substantially"] --> B1["● Remove unnecessary process stages"]
A --> B2["● Raise wages to the local market level"]
B1 --> C11["○ Productivity trails benchmark by 20-50%"]
B1 --> C12["○ Every title gets the same checks regardless of complexity"]
B1 --> C13["○ Test next week: fewer checks on simple jobs, quality and customers monitored"]
B1 --> C14["○ Possible saving up to 10% of composing cost; methods study on the residual gap"]
B2 --> C21["○ Pay below nearby printers; cannot hire or retain compositors, two just left"]
B2 --> C22["○ Understaffed: most work late, overtime over budget by 50%+"]
B2 --> C23["○ Competitive pay enables recruitment and removes the overtime premium"]
B2 --> C24["○ A new union claim may force higher pay anyway"]flowchart LR
S["Situation: composition is 40% of hardback and 50-55% of paperback cost"] --> C["Complication: customers call TTW uncompetitive on simple jobs; TTW does not know if cost is excessive"]
C --> Q["Question: can composing cost be cut, and how?"]
Q --> A["Answer: yes — remove unnecessary stages and pay the local market rate"]
A --> N["Next step: test simple jobs next week; commission the methods study"]Legend: ▲ top · ● first-level group · ○ support · ⊕ gap
| Node | Note |
|---|---|
| First level | Two groups, not three or four — acceptable here: both are actions, non-overlapping (process vs. staffing), and together cover the cost base |
● Raise wages | ⊕ no size of saving quantified, unlike the 10% under the first branch |
▲ Top | "substantially" is quantified only for one of the two branches |
Как устроен тест
Claude Opus 5 получила одну и ту же задачу дважды. Контрольный промпт — одна вводная строка и задача. Промпт с Minto — та же задача, перед которой стоит полный текст навыка. Судья читал оба ответа среди 16 ответов под слепыми метками и не знал, в каком из них был навык.
Промпт без Minto 1 688 Б
You are working on a business document using the Minto Pyramid Principle.
<!-- Faithful paraphrase of Minto (2010), Chapter 3, the rewritten TTW memo.
Original wording for this fixture. -->
# Fixture 06: TTW pyramid
**Mode:** `viz`
**Language:** `en`
## Context
The TTW memo has already been rewritten. Show its existing structure; do not
rewrite it.
## Before
```text
Subject: TTW composing cost
During the past two weeks I reviewed the Aylesbury composing room. Composition
represents about 40% of hardback cost and 50-55% of paperback cost. TTW does not
know whether the cost is excessive, but customers regard it as uncompetitive on
simple jobs.
Our preliminary work indicates that TTW can cut composing cost substantially
by:
- removing unnecessary process stages;
- raising wages to the local market level.
REMOVE UNNECESSARY STAGES
TTW trails the productivity benchmark by 20-50%. Every title passes through
essentially the same checks regardless of complexity. Next week, selected
simple jobs will be tested with fewer or differently timed checks, while
quality and customer reaction are monitored. The possible saving is up to 10%
of composing cost. A methods study will examine the remaining benchmark gap.
RAISE WAGES
TTW pays less than nearby printers and cannot hire or retain enough
compositors. Two have just left. The department is understaffed, most work is
late, and overtime exceeds budget by more than 50%. A new union claim may force
higher pay; competitive pay should make recruitment possible and remove the
overtime premium.
```
## Task
Draw the pyramid of this memorandum.
Return only the result, with no explanation of how you produced it.
Промпт с Minto пять частей по порядку · 29 261 Б
Below is a skill written as an instruction. Read it in full and apply it to the task at the end.===== SKILL.md =====SKILL.md на f4813ce 17 235 Б===== references/rules.md =====references/rules.md на f4813ce 6 464 Б===== references/templates.md =====references/templates.md на f4813ce 3 742 Б===== TASK =====вход кейса целикомReturn only the result, with no explanation of how you produced it.
Вход кейса before.md
<!-- Faithful paraphrase of Minto (2010), Chapter 3, the rewritten TTW memo.
Original wording for this fixture. -->
Fixture 06: TTW pyramid
Mode: viz
Language: en
Context
The TTW memo has already been rewritten. Show its existing structure; do not
rewrite it.
Before
Subject: TTW composing cost
During the past two weeks I reviewed the Aylesbury composing room. Composition
represents about 40% of hardback cost and 50-55% of paperback cost. TTW does not
know whether the cost is excessive, but customers regard it as uncompetitive on
simple jobs.
Our preliminary work indicates that TTW can cut composing cost substantially
by:
- removing unnecessary process stages;
- raising wages to the local market level.
REMOVE UNNECESSARY STAGES
TTW trails the productivity benchmark by 20-50%. Every title passes through
essentially the same checks regardless of complexity. Next week, selected
simple jobs will be tested with fewer or differently timed checks, while
quality and customer reaction are monitored. The possible saving is up to 10%
of composing cost. A methods study will examine the remaining benchmark gap.
RAISE WAGES
TTW pays less than nearby printers and cannot hire or retain enough
compositors. Two have just left. The department is understaffed, most work is
late, and overtime exceeds budget by more than 50%. A new union claim may force
higher pay; competitive pay should make recruitment possible and remove the
overtime premium.Task
Draw the pyramid of this memorandum.
Эталон судьи gold.md
Gold 06: TTW pyramid
Source structure: Minto (2010), Chapter 3, TTW analysis and rewritten memo.
Expected diagram
Top: TTW can cut composing cost substantially.
Exactly two first-level actions:
- Remove unnecessary composing stages.
- Raise wages to competitive levels.
Under the first: benchmark gap, identical stages for different work, controlled
test, potential 10% saving, methods study.
Under the second: below-market pay, recruitment and retention failure, two
departures, understaffing, delays, overtime more than 50% over budget, union
pressure.
A valid output contains a Mermaid flowchart TD or an equivalent visible text
diagram. It does not create an HTML page or local file because none was
requested. Repeating section labels without turning them into claims, adding a
third first-level branch, or promoting observations to the first level reduces
the structural score. No prose rewrite is required.
Судья gpt-5.6-sol, effort high · Claude Opus 5, effort low · навык с коммита f4813ce · прогон v1.7.0-final