Claude Opus 5 на кейсе «Записка о наборных издержках»: с Minto лучше по обеим мерам
Структура 4 → 7 из 8 +3 Качество 6 → 8 из 10 +2
Судья об ответе с Minto
This is the only output to promote pay and capacity to an action with its causal evidence beneath it, although it still leaves simplification and method change as overlapping branches.
| Структура | Без Minto 4 | С Minto 7 | Изменение |
|---|---|---|---|
| Вершина | 2 | 2 | |
| Состав ключевой линии | 1 | 1 | |
| Уровни | 0 | 2 | +2 |
| Порядок и род | 1 | 2 | +1 |
| Качество | Без Minto 6 | С Minto 8 | Изменение |
|---|---|---|---|
| Вершина | 2 | 2 | |
| Однородные группы | 1 | 2 | +1 |
| Объяснимый порядок | 1 | 1 | |
| MECE | 0 | 1 | +1 |
| Видимая соразмерная структура | 2 | 2 |
Ответы моделей и слова судьи приведены в оригинале, по-английски.
Без Minto
контрольный промпт · слепая меткаout-03invented_facts
Staffing is promoted as a separate “why now” section, and the printer-mix rationale for rejecting comparison is invented.
To: Engagement Manager
From: [Consultant]
Subject: Reducing TTW composing-room costs
TTW can cut composing costs by an estimated 10% or more, and should authorise two tests to confirm it. Composition is the largest single production cost, and two independent levers are available: simplifying the process for inexpensive titles, and raising productivity by changing the composing method. Management disagrees about whether costs are high, but all parties are willing to investigate.
1. Simplify quality control on inexpensive titles
Every title passes through essentially the same quality-control stages, whether it is a complex reference book or a simple novel. TTW is uncompetitive on simple work, which suggests the stages are heavier than cheap titles require.
Recommended test: run selected jobs with fewer or differently timed checks and measure the effect on quality and on customers. George Kennedy has agreed to run this test. Potential saving: up to 10% of total composing cost.
2. Change the composing method to raise productivity
Industry comparisons put TTW 20–50% behind the benchmark on measured productivity.
Recommended test: a separate methods study to identify why productivity trails and which changes would close the gap.
3. Why the tests are necessary now
The department is overloaded, and manual composition is especially short of capacity. TTW pays below local market rates, cannot reliably hire or retain compositors, has just lost two employees, and now runs most jobs late. Overtime is more than 50% over budget while the union presses a new claim. Cost relief will not come from working the existing process harder.
What I have omitted, and why
- Benchmarking against three other printers. Feasible, but a simple cost comparison will not settle whether TTW's costs are excessive, because the mix of complex and simple titles differs by printer. Not recommended as a next step.
- The interview record (Roy Walter, Brian Thompson, George Kennedy) and the narrative of the two weeks' work. Available on request; only Kennedy's commitment to test bears on the recommendation.
- The 40% hardback / 50–55% paperback cost shares. Already known to you; retained only as the basis for treating composition as the priority.
С Minto
промпт с навыком · слепая меткаout-14Жёстких провалов нет
This is the only output to promote pay and capacity to an action with its causal evidence beneath it, although it still leaves simplification and method change as overlapping branches.
To: Engagement manager
From: [consultant]
Subject: Two studies will show how much of TTW's composing cost can be removed
You asked what the first two weeks of work on composing-room costs support. The evidence points to savings, but not yet to their size: TTW's own managers disagree about whether its costs are high, and the department is now losing capacity fast enough that any delay costs money. TTW should start two studies immediately and treat the staffing gap as a third, parallel action — a comparison with other printers should not be part of the programme.
1. Trial simplified quality control on inexpensive titles — up to 10% of total composing cost.
Every title today passes through essentially the same quality-control stages, whether it is a complex reference book or a simple novel, and simple work is exactly where TTW is uncompetitive. George Kennedy is willing to run the test on selected jobs, measuring the effect of fewer or differently timed checks on quality and on customers.
2. Commission a methods study of the composing operation — the productivity gap is 20–50%.
Industry comparisons place TTW that far behind the benchmark, so changing the composing method is the second route to lower unit cost. Kennedy has also agreed to examine why measured productivity trails the benchmark, which gives the study its starting point.
3. Close the capacity and pay gap in parallel, or the savings will not be realised.
The department is overloaded and manual composition is short of capacity outright. TTW pays below local market rates, cannot hire or retain compositors, has just lost two employees, and now runs most jobs late. Overtime stands more than 50% over budget while the union is pressing a new claim — so the current cost base is inflated by conditions the two studies cannot touch.
What I need: your agreement to the two studies and to naming an owner for the staffing question this week.
Omitted: the proposed comparison with three other printers — a simple comparison will not settle whether TTW's costs are excessive, and the two studies answer that question directly. Also dropped: the list of managers interviewed, and the observation that they disagree about cost levels, which is a reason to measure rather than an action; both are available in the working notes.
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 14 ответов под слепыми метками и не знал, в каком из них был навык.
Промпт без Minto 2 516 Б
You are working on a business document using the Minto Pyramid Principle.
<!-- Faithful paraphrase of Minto (2010), Chapter 3, the TTW composing-room
memorandum before restructuring. Original wording for this fixture. -->
# Fixture 02: TTW composing costs
**Mode:** `write`
**Language:** `en`
## Context
TTW is a printing company in Aylesbury. A junior consultant spent two weeks
examining composing-room costs. The engagement manager already knows that
composition accounts for roughly 40% of hardback cost and 50-55% of paperback
cost, that TTW is uncompetitive on simple work, and that TTW does not know
whether its composing costs are actually excessive.
## Before
```text
To:
From:
Subject: TTW
This note records the information gathered during the past two weeks.
Composition is the largest production cost. Industry comparisons suggest weak
productivity and high cost at TTW. Every title, whether a complex reference
book or a simple novel, passes through essentially the same quality-control
stages.
People in Aylesbury want to understand the causes. I spoke with Roy Walter,
Brian Thompson, and George Kennedy. Kennedy is willing to test whether some
stages can be removed and why measured productivity trails the benchmark.
The department is overloaded. Manual composition is especially short of
capacity. TTW pays below local market rates, struggles to hire and retain
compositors, has just lost two employees, and now runs most jobs late.
Overtime is more than 50% over budget, while the union is pressing a new claim.
Conclusions
1. Costs may be reduced by:
a. simplifying the process for inexpensive titles;
b. increasing productivity by changing the composing method.
2. To simplify the process, TTW should test selected jobs and measure the
effect of fewer or differently timed checks on quality and customers. The
saving might reach 10% of total composing cost. A separate methods study
could identify further productivity improvements because TTW trails the
benchmark by 20-50%.
3. Comparisons with three other printers might provide useful context, although
I doubt a simple comparison will settle the issue.
4. Managers disagree about whether costs are high, but all are willing to
investigate.
```
## Task
Rewrite the report using the Minto Pyramid Principle. Keep the useful facts,
remove or demote material that does not support the recommendation, and state
what was omitted.
Return only the result, with no explanation of how you produced it.
Промпт с Minto пять частей по порядку · 30 089 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 TTW composing-room
memorandum before restructuring. Original wording for this fixture. -->
Fixture 02: TTW composing costs
Mode: write
Language: en
Context
TTW is a printing company in Aylesbury. A junior consultant spent two weeks
examining composing-room costs. The engagement manager already knows that
composition accounts for roughly 40% of hardback cost and 50-55% of paperback
cost, that TTW is uncompetitive on simple work, and that TTW does not know
whether its composing costs are actually excessive.
Before
To:
From:
Subject: TTW
This note records the information gathered during the past two weeks.
Composition is the largest production cost. Industry comparisons suggest weak
productivity and high cost at TTW. Every title, whether a complex reference
book or a simple novel, passes through essentially the same quality-control
stages.
People in Aylesbury want to understand the causes. I spoke with Roy Walter,
Brian Thompson, and George Kennedy. Kennedy is willing to test whether some
stages can be removed and why measured productivity trails the benchmark.
The department is overloaded. Manual composition is especially short of
capacity. TTW pays below local market rates, struggles to hire and retain
compositors, has just lost two employees, and now runs most jobs late.
Overtime is more than 50% over budget, while the union is pressing a new claim.
Conclusions
1. Costs may be reduced by:
a. simplifying the process for inexpensive titles;
b. increasing productivity by changing the composing method.
2. To simplify the process, TTW should test selected jobs and measure the
effect of fewer or differently timed checks on quality and customers. The
saving might reach 10% of total composing cost. A separate methods study
could identify further productivity improvements because TTW trails the
benchmark by 20-50%.
3. Comparisons with three other printers might provide useful context, although
I doubt a simple comparison will settle the issue.
4. Managers disagree about whether costs are high, but all are willing to
investigate.Task
Rewrite the report using the Minto Pyramid Principle. Keep the useful facts,
remove or demote material that does not support the recommendation, and state
what was omitted.
Эталон судьи gold.md
Gold 02: TTW composing costs
Source structure: Minto (2010), Chapter 3, TTW analysis and rewritten memo.
Expected structure
| Element | Expected value |
|---|---|
| Reader question | How can TTW reduce composing cost? |
| Top | TTW can reduce composing cost substantially |
| Key-line kind | Actions |
| Order | Two independent changes, each followed by its causal support |
Key line
- Eliminate unnecessary stages from the composing process for simple work.
- Raise wages to competitive levels.
The source's "simplify the process" and "increase productivity by changing the
method" are overlapping descriptions of the same process intervention. They
must not survive as two separate first-level branches. The missing second
branch is embedded in the observations: low wages cause vacancies, delays, and
overtime cost.
Levels
Under eliminating stages: every job follows the same process; TTW trails the
benchmark by 20-50%; run a controlled experiment; potential saving up to 10%.
Under raising wages: below-market pay; hiring and retention difficulty; two
departures; understaffing; late work; overtime more than 50% over budget; union
pressure.
Names, conflicting opinions, and generic competitor comparisons do not answer
the reader's question. They may be omitted with one explicit note.
Судья gpt-5.6-sol, effort high · Claude Opus 5, effort low · навык с коммита f4813ce · прогон v1.7.0-final