qwen3.6-35b-a3b на кейсе «Набор ежемесячных отчётов»: с Minto лучше по качеству, структура та же

Структура 4 → 4 из 8 0 Качество 6 → 7 из 10 +1

Судья об ответе с Minto

It clearly exposes the missing proposals and buried streamlining conclusion, but rebuilds around causes and symptoms rather than actions.

Режим audit · кейс 03-period-graph-books · прогон v1.7.0-final

Структура из 8, по 2 балла на ось
Структура	Без Minto 4	С Minto 4
Вершина	1	1
Состав ключевой линии	1	1
Уровни	1	1
Порядок и род	1	1

Качество из 10, по 2 балла на ось
Качество	Без Minto 6	С Minto 7	Изменение
Вершина	1	1
Однородные группы	2	2
Объяснимый порядок	1	1
MECE	1	1
Видимая соразмерная структура	1	2	+1

Ответы моделей и слова судьи приведены в оригинале, по-английски.

Без Minto С Minto

Без Minto

контрольный промпт · слепая метка out-09

Жёстких провалов нет

It is concise and structurally readable, but omits the crucial buried-streamlining distinction and the specific process failures.

Defects Diagnosed

Missing Bottom-Line-Up-Front: Opens with historical context instead of a clear thesis, key finding, or recommendation.
Flat, Non-Hierarchical Structure: Procedural steps, diagnostic observations, and managerial assessments sit at the same level without subordinate relationships or summarizing statements.
Unstructured Grouping: Issues are presented narratively rather than categorized into logical, mutually exclusive groups (e.g., data handling, calculation integrity, accountability). Lacks a consistent ordering principle.
Redundancy Across Sections: The core critique—fragmented workflow, triple data entry, and unclear ownership—is repeated in “Issues” and “Overall assessment” without synthesis or elevation to a higher-level conclusion.
Mixed Content Types: Steps, problems, evaluations, and a request are blended without clear structural boundaries, violating Minto’s rule that each section must serve a single, distinct purpose.
Vague Call to Action: Closes with an open-ended question instead of a specific decision request, proposal, or defined next step aligned with the document’s purpose.

Required Changes

Place a single, clear top-level statement at the beginning that states the purpose, key finding, and recommended action.
Restructure into a strict top-down hierarchy: main conclusion → supporting categories (e.g., Root Causes, Operational Impact, Proposed Remediation) → detailed evidence beneath each category.
Group all issues logically using a consistent ordering principle (e.g., by process stage or functional domain), ensuring each group contains distinct, non-overlapping points that collectively cover the problem space.
Consolidate repetitive observations into single, well-defined categories; eliminate duplicate explanations of fragmentation and redundant data entry.
Replace the open-ended closing with a specific request for approval, decision, or next step that directly supports the top-level recommendation.
Ensure every section headline summarizes the content beneath it and maintain parallel grammatical structure throughout.

С Minto

промпт с навыком · слепая метка out-05

Жёстких провалов нет

It clearly exposes the missing proposals and buried streamlining conclusion, but rebuilds around causes and symptoms rather than actions.

Marker	Meaning
`▲`	top / answer
`●`	first-level group
`○`	supporting detail
`⚠`	violation (mixed kinds, unexplainable order, false grouping)
`↑`	conclusion buried lower than it belongs — promote it
`⇄`	wrong order type here
`⊗`	overlap (ME broken)
`⊕`	gap (CE broken)
`✂`	cut, or move to an appendix

Subject: Period Graph Books

Since Period 5, Financial Analysis has been responsible for producing four
graph-presentation books previously handled by Corporate Planning. This memo
describes issues that appeared after the transfer. [⊕]

Production [●]

Gather data from divisional forms, internal documents, and telephone calls. [○]
Calculate graph points manually or on the corporate computer, including
rolling values for revenue, cost, and percentages. [○]
Transcribe the points to input sheets. Analysts update the current period,
then Color Graphics re-enters the points into its own database and generates
the graphs. [○]
Check the data and calculations. [○]

Issues [●] ⚠
The transfer inserted another person into an already fragmented process. [↑]
Divisional staff and three corporate departments participate, and the same
information may be entered into computer systems three times. [○]
For one book, divisional data are loaded into a dedicated corporate program,
calculated, transferred to Color Graphics input sheets, entered again, and
returned for updates. Problems include inconsistent data between periods
and regions, incorrect variable-cost calculations, unexplained changes to
points that were previously correct, and prior-period data that must be
re-entered. [⊗]

Overall assessment [●] ⚠
Most problems arise from a cumbersome fragmented process. [↑]
No one controls the data from beginning to end, responsibility is unclear,
and errors can fall between stages. [○]
The production process badly needs streamlining, both for each book and for
common calculations. [↑]
The current team cannot manage the required changes as well as ongoing production. [○]

Could we discuss how best to proceed? [↑]

Location	Violation	Fix
Opening paragraph	Top does not answer reader’s question	Replace with one-sentence recommendation addressing management’s request for corrective proposals
“Issues” section	Mixed kinds & non-MECE split	Separate root causes (process fragmentation) from symptoms (data/calculation errors); apply ranking or structure
“Overall assessment”	Buried conclusion & duplicate theme	Promote streamlining recommendation to top; move detailed process critique to supports under the cause branch
Transition to closing	Jump from fact to ask	Insert explicit decision/request (e.g., approve pilot streamlining plan) before the discussion request
“Production” vs “Issues”	Overlap	Cut redundant process description from “Issues”; keep only in “Production” or move to appendix

Score

Top: 0
Same-kind groups: 0
Order: 0
MECE: 1
Display: 1
Band: 0–3 (not structured yet)

Three fixes that buy the most

Replace the opening context with a single-sentence answer stating the recommended corrective action.
Split the “Issues” section into two same-kind groups: root causes (fragmented handoffs) and symptoms (data/calculation errors).
Move the streamlining recommendation and team-capacity concern to support the top, and replace the open-ended closing with a specific decision request.

Судья

Повторяющийся дефект	без	с Minto
Missing answer is not distinguished from the buried streamlining conclusionправило в навыке есть, модель его не выполнила · Mode 2 — audit, check 1: Top	есть	есть
Incomplete process logic is not separated into graph-generation and later-change failure pointsтакого правила в навыке нет · Mode 2 — audit, check 4: MECE	есть	есть
Suggested first-level structure uses causes, symptoms, constraints, or topics instead of actionsправило в навыке есть, модель его не выполнила · Core loop, §4 Groups	есть	есть
Inline annotation, capped findings, five-axis score, or three highest-value fixes are absentправило в навыке есть, модель его не выполнила · Mode 2 — audit, delivery contract	есть	нет

Решающие вопросы

Did the audit state precisely that the required changes are absent?
без yes
с Minto yes
Did it distinguish a missing answer from a merely buried answer?
без no
с Minto partial
Did it identify streamlining as an undeveloped conclusion?
без no
с Minto yes
Did it name incomplete process logic and unseparated failure points?
без no
с Minto partial
If a replacement structure was suggested, is its key line made of actions?
без no—the replacement hierarchy mixes root causes, impacts, and remediation
с Minto no—the proposed grouping remains causes and symptoms
What false positives or invented details appear?
без incorrectly combines purpose, finding, and action in one top and overstates redundancy
с Minto adds an unsupported pilot/approval request
Did the output remain diagnosis-only and include the required audit apparatus?
без diagnosis-only, but the audit apparatus is absent
с Minto yes

Проверка судьи	без	с Minto
Род первого уровня как в эталоне	да	да
Выдуманные факты	нет	нет
Потеря материала без пометки	нет	нет
Режим соблюдён	да	да
Тип порядка назван	нет	да

Ещё 4 проверки судьи не применяются к режиму audit

Как устроен тест

qwen3.6-35b-a3b 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 2 424 Б

You are working on a business document using the Minto Pyramid Principle.

<!-- Faithful paraphrase of Minto (2010), Appendix B, Exhibits B-5 and B-6.
     Original wording for this fixture. -->

# Fixture 03: Period Graph Books

**Mode:** `audit`
**Language:** `en`

## Context

Corporate Financial Analysis recently took over production of four monthly
graph books used in presentations to senior management. Management knows that
errors and inconsistencies have appeared and asked for corrective proposals.

## Before

```text
Subject: Period Graph Books

Since Period 5, Financial Analysis has been responsible for producing four
graph-presentation books previously handled by Corporate Planning. This memo
describes issues that appeared after the transfer.

Production

1. Gather data from divisional forms, internal documents, and telephone calls.
2. Calculate graph points manually or on the corporate computer, including
   rolling values for revenue, cost, and percentages.
3. Transcribe the points to input sheets. Analysts update the current period,
   then Color Graphics re-enters the points into its own database and generates
   the graphs.
4. Check the data and calculations.

Issues

The transfer inserted another person into an already fragmented process.
Divisional staff and three corporate departments participate, and the same
information may be entered into computer systems three times.

For one book, divisional data are loaded into a dedicated corporate program,
calculated, transferred to Color Graphics input sheets, entered again, and
returned for updates. Problems include inconsistent data between periods and
regions, incorrect variable-cost calculations, unexplained changes to points
that were previously correct, and prior-period data that must be re-entered.

Overall assessment

Most problems arise from a cumbersome fragmented process. No one controls the
data from beginning to end, responsibility is unclear, and errors can fall
between stages. The production process badly needs streamlining, both for each
book and for common calculations. The current team cannot manage the required
changes as well as ongoing production.

Could we discuss how best to proceed?
```

## Task

Audit this document against the Minto Pyramid Principle. Diagnose the defects
and explain what must change. Do not rewrite the document.

Return only the result, with no explanation of how you produced it.

Промпт с Minto пять частей по порядку · 29 997 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 целиком
Return only the result, with no explanation of how you produced it.

Вход кейса before.md

Fixture 03: Period Graph Books

Mode: audit
Language: en

Context

Corporate Financial Analysis recently took over production of four monthly
graph books used in presentations to senior management. Management knows that
errors and inconsistencies have appeared and asked for corrective proposals.

Before

Subject: Period Graph Books
                
                Since Period 5, Financial Analysis has been responsible for producing four
                graph-presentation books previously handled by Corporate Planning. This memo
                describes issues that appeared after the transfer.
                
                Production
                
                1. Gather data from divisional forms, internal documents, and telephone calls.
                2. Calculate graph points manually or on the corporate computer, including
                   rolling values for revenue, cost, and percentages.
                3. Transcribe the points to input sheets. Analysts update the current period,
                   then Color Graphics re-enters the points into its own database and generates
                   the graphs.
                4. Check the data and calculations.
                
                Issues
                
                The transfer inserted another person into an already fragmented process.
                Divisional staff and three corporate departments participate, and the same
                information may be entered into computer systems three times.
                
                For one book, divisional data are loaded into a dedicated corporate program,
                calculated, transferred to Color Graphics input sheets, entered again, and
                returned for updates. Problems include inconsistent data between periods and
                regions, incorrect variable-cost calculations, unexplained changes to points
                that were previously correct, and prior-period data that must be re-entered.
                
                Overall assessment
                
                Most problems arise from a cumbersome fragmented process. No one controls the
                data from beginning to end, responsibility is unclear, and errors can fall
                between stages. The production process badly needs streamlining, both for each
                book and for common calculations. The current team cannot manage the required
                changes as well as ongoing production.
                
                Could we discuss how best to proceed?

Task

Audit this document against the Minto Pyramid Principle. Diagnose the defects
and explain what must change. Do not rewrite the document.

Эталон судьи gold.md

Gold 03: Period Graph Books

Source structure: Minto (2010), Appendix B, Exhibits B-5 and B-6.

Book-derived defects

Defect	Severity
The document never states the changes required; it therefore does not answer management's question	Critical
It describes the current process instead of presenting a top and key line	Critical
"The purpose is to describe issues" is a topic, not an answer	Critical
The process description is incomplete and does not isolate each system's failure points	Medium
Problems in graph-point generation and later presenter changes are not clearly separated	Medium

The buried conclusion is that the process needs streamlining, but this is not
turned into an actionable answer.

Expected replacement structure

Reader question: What changes should we make to prevent unreliable graphs?

Top: Remove the opportunities for error across data transfer, graph-point
generation, and final presentation changes.

Key-line kind: changes/actions.

Create a direct data link to the corporate computer.
Create a reliable computerized routine for graph-point generation.
Require presenter changes to be revalidated before use.

Audit outputs should name the missing answer, distinguish it from a conclusion
that is merely buried, annotate only visible evidence, provide no rewritten
memo, and avoid inventing defects in unseen material.

Судья gpt-5.6-sol, effort high · навык с коммита f4813ce · прогон v1.7.0-final