qwen3.6-35b-a3b on “A set of headings”: better with Minto on both measures

Structure 5 → 6 of 8 +1 Quality 5 → 8 of 10 +3

The judge on the output with Minto

Supplies the required apparatus cleanly but misses the specific Background-level and nesting diagnoses and overclaims a vertical-summary defect.

Mode audit · case 07-headings-audit · run v1.7.0-final

Structure of 8, 2 points per axis
Structure	Without Minto 5	With Minto 6	Change
Top	2	2
Key-line composition	1	1
Levels	1	1
Order and kind	1	2	+1

Quality of 10, 2 points per axis
Quality	Without Minto 5	With Minto 8	Change
Top	2	2
Same-kind grouping	1	1
Explainable order	1	2	+1
MECE	0	1	+1
Visible, proportionate structure	1	2	+1

Outputs and the judge’s words are quoted as written, in English.

Without Minto With Minto

Without Minto

control prompt · blind label out-07

invented_facts

Concisely catches topics, order, and Background, but invents a value proposition in the opening and omits the display-limit finding and audit apparatus.

Opening Statement

Fails to state a key idea or answer the reader’s implicit question; merely describes the document’s scope rather than presenting a central conclusion or recommendation.

Setout / Headings

Topics, not key ideas: All six headings function as subject labels rather than conveying distinct, actionable points or conclusions.
Lack of parallel structure: Grammatical forms are inconsistent across headings (mixing simple nouns, gerund phrases, and compound modifiers), violating Minto’s parallelism requirement.
Not MECE: Conceptual overlap exists between “Principles of the project-team approach,” “Definition of project work,” and “Organization of the program.” “Distinctive benefits and results” duplicates the value proposition already stated in the opening.
Unclear logical order: No consistent sequencing principle (chronological, structural, causal, or priority-based) governs the arrangement of the six sections.
Extraneous element: “Background” does not advance the core argument or action orientation required in a Minto pyramid and should either be integrated into the main line of thought or relocated to an appendix.

With Minto

prompt with the skill · blind label out-03

No hard failures

Supplies the required apparatus cleanly but misses the specific Background-level and nesting diagnoses and overclaims a vertical-summary defect.

✂ This memorandum describes how project teams identify and deliver significant
profit improvements. It is organized in six sections:

⚠ Background
                ⚠ Principles of the project-team approach
                ⚠ Definition of project work
                ⚠ Organization of the program
                ⚠ Distinctive benefits and results
                ⚠ Conditions required for success

Location	Violation	Fix
Opening sentence	Top does not answer reader question; states topic instead	Replace with a single-sentence answer addressing the reader’s decision or action
Heading list	Mixed kinds & unexplainable order; background, principles, definitions, organization, benefits, conditions do not share one plural noun	Group into 3–4 same-kind branches (reasons, actions, or criteria) and apply explicit ordering (time/ranking/structure)
Structure	No vertical summary; headings are topics, not claims summarizing supports	Convert headings to claim-based statements that directly answer the reader’s question
Display	Skeleton hidden behind generic intro and flat list	Use indentation, numbering, and a key line to make hierarchy readable at a glance

Score
Top: 0 · Same-kind groups: 0 · Order: 0 · MECE: 0 · Display: 0
Band: 0–3 not structured yet

Three fixes that buy the most

Delete the introductory sentence and replace it with one direct answer to the reader’s question.
Collapse the six topic headings into three or four same-kind groups and assign a clear ordering principle.
Rewrite each group heading as a claim rather than a topic word, and use indentation/numbering to show the hierarchy.

The judge

Recurring defect	without	with Minto
Both likely nesting relationships were missedthe rule is too vague to follow · Mode 2, Vertical and MECE checks	present	present
Required markers, findings table, score, and three fixes were omittedthe skill has the rule; the model did not follow it · Mode 2, delivery order	present	absent
The six-first-level-item limit was not flaggedthe skill has the rule; the model did not follow it · Core loop §4 and Limits	present	absent
Unsupported reader, section-content, or SCQ facts were assertedthe skill has the rule; the model did not follow it · Core loop §8.4 and audit’s evidence boundary	present	absent
Background’s distinct abstraction level was not isolatedthe rule is there but buried · Canon, introduction anti-patterns	absent	present

Decisive questions

Did the audit say that the setout contains topics rather than ideas and therefore has no key line?
without Yes
with Minto Yes
Did it identify the first sentence as a topic statement rather than an answer?
without Yes
with Minto Yes
Did it identify the abstraction problem with `Background`?
without Yes
with Minto No
Did it identify both likely nesting errors named in the gold?
without No
with Minto No
Did it flag six first-level topics?
without No
with Minto Yes
Which findings rely on the unavailable body or merely ask for more content?
without Claims unseen overlaps and falsely treats the opening as an existing value proposition.
with Minto “No vertical summary” cannot be verified without the body.
Were quotations, line numbers, page numbers, or section contents invented?
without Yes
with Minto No
Did the output remain diagnosis-only and include the required audit apparatus?
without Diagnosis-only; apparatus missing.
with Minto Diagnosis-only; apparatus complete.

Judge’s check	without	with Minto
First-level kind matches the gold	yes	yes
Invented facts	yes	no
Source lost without a note	no	no
Mode respected	yes	yes
Order type named	yes	yes

4 more judge checks do not apply to mode audit

How the test was built

qwen3.6-35b-a3b received the same task twice. The control prompt is one framing line and the task. The prompt with Minto is the same task preceded by the full text of the skill. The judge read both outputs among 16 under blind labels and did not know which one had the skill.

Prompt without Minto 998 B

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

<!-- Faithful paraphrase of Minto (2010), Chapter 4, the six-heading
     project-team example. Original wording for this fixture. -->

# Fixture 07: headings audit

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

## Context

Only the opening and setout below are available. The body of the memorandum is
not available and must not be inferred.

## Before

```text
This memorandum describes how project teams identify and deliver significant
profit improvements. It is organized in six sections:

    Background
    Principles of the project-team approach
    Definition of project work
    Organization of the program
    Distinctive benefits and results
    Conditions required for success
```

## Task

Audit the visible opening against the Minto Pyramid Principle. Report what is
wrong without rewriting the document or inventing facts about the missing body.

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

Prompt with Minto five parts, in order · 28 571 B

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 at f4813ce 17 235 B
===== references/rules.md ===== references/rules.md at f4813ce 6 464 B
===== references/templates.md ===== references/templates.md at f4813ce 3 742 B
===== TASK ===== the whole case input
Return only the result, with no explanation of how you produced it.

Case input before.md

Fixture 07: headings audit

Mode: audit
Language: en

Context

Only the opening and setout below are available. The body of the memorandum is
not available and must not be inferred.

Before

This memorandum describes how project teams identify and deliver significant
                profit improvements. It is organized in six sections:
                
                    Background
                    Principles of the project-team approach
                    Definition of project work
                    Organization of the program
                    Distinctive benefits and results
                    Conditions required for success

Task

Audit the visible opening against the Minto Pyramid Principle. Report what is
wrong without rewriting the document or inventing facts about the missing body.

The judge’s gold gold.md

Gold 07: headings audit

Source structure: Minto (2010), Chapter 4.

Visible defects

Defect	Severity
The setout contains topics, not ideas, so it conveys no message or key line	Critical
The first sentence describes a subject instead of answering a reader question	Critical
`Background` cannot sit at the same abstraction level as the other points	Medium
Benefits/results likely belong under principles; success conditions likely belong under program organization	Medium
Six first-level topics exceed the skill's normal display limit	Medium
The topics do not form a visible inductive or deductive argument	Medium

The output must stay within the visible evidence. Claims about missing data,
metrics, proof, vertical support inside sections, or exact content of the body
are false positives. Invented page numbers, line numbers, or quotations are
hard failures.

Judge gpt-5.6-sol, effort high · skill from commit f4813ce · run v1.7.0-final