Codex gpt-5.6-terra on “A set of headings”: better with Minto on both measures

Structure 3 → 6 of 8 +3 Quality 4 → 8 of 10 +4

The judge on the output with Minto

Is appropriately cautious about the unavailable body and visibly structured, though it substitutes speculative benefits/results and completeness concerns for the missing nesting analysis.

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

Structure of 8, 2 points per axis
Structure	Without Minto 3	With Minto 6	Change
Top	1	2	+1
Key-line composition	1	1
Levels	1	1
Order and kind	0	2	+2

Quality of 10, 2 points per axis
Quality	Without Minto 4	With Minto 8	Change
Top	1	2	+1
Same-kind grouping	1	1
Explainable order	0	2	+2
MECE	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-15

No hard failures

Correctly calls the headings topic labels and mixed, but is too abbreviated to diagnose the opening, six-item limit, Background level, or order with the required apparatus.

The six headings are topic labels, not message headings; they do not state the points the memorandum will prove.
They are not parallel: they mix background, definitions, principles, organization, benefits/results, and success conditions.
“Distinctive benefits and results” combines two potentially different ideas in one heading.
The opening promises how teams identify and deliver profit improvements, but the setout does not make the supporting logic or sequence visible.

With Minto

prompt with the skill · blind label out-12

No hard failures

Is appropriately cautious about the unavailable body and visibly structured, though it substitutes speculative benefits/results and completeness concerns for the missing nesting analysis.

Legend: ▲ top/answer · ⚠ structural violation · ⊕ gap · ⇄ unexplained order

⚠ This memorandum describes how project teams identify and deliver significant
                profit improvements. ⊕ No reader question or answer is stated. 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
                    ⇄ No ordering principle is visible.

Location	Violation	Fix
Opening sentence	It is a topic statement, not an answer to a reader’s question.	State the conclusion the memorandum supports; the visible material does not establish one.
Opening and headings	No reader question is made explicit.	Define the decision or question the memorandum is intended to close.
Six-heading setout	The headings mix kinds: background, principles, definition, organization, benefits/results, and conditions.	Rebuild first-level headings as one same-kind set after the reader question is known.
“Distinctive benefits and results”	Benefits and results are potentially separate categories; the visible setout does not establish their boundary.	Separate them or define their relationship in the hierarchy.
Full setout	No order is apparent: it is neither clearly chronological, structural, nor ranked.	Apply and signal an order that serves the reader’s question.
Full setout	Completeness and non-overlap cannot be verified from the heading labels alone; the missing body must not be inferred.	Test the final hierarchy against the body when available.

Score: 1/10 — not structured yet

Axis	Score
Top	0
Same-kind groups	0
Order	0
MECE	0
Display	1

Three highest-value fixes:

Establish the reader’s question and a one-sentence answer before naming sections.
Replace the mixed six-heading list with three or four same-kind first-level groups.
Order those groups by a visible, reader-relevant principle.

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
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 No
Did it identify the first sentence as a topic statement rather than an answer?
without No
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 None material; the benefits/results concern is tentative.
with Minto The benefits/results split and final completeness row depend on body content or future testing.
Were quotations, line numbers, page numbers, or section contents invented?
without No
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	no
Invented facts	no	no
Source lost without a note	no	no
Mode respected	yes	yes
Order type named	no	yes

4 more judge checks do not apply to mode audit

How the test was built

Codex gpt-5.6-terra 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 · Codex gpt-5.6-terra, effort low · skill from commit f4813ce · run v1.7.0-final