Codex gpt-5.6-terra on “A message about technical debt”: better with Minto on both measures

Structure 7 → 8 of 8 +1 Quality 8 → 10 of 10 +2

The judge on the output with Minto

This is the cleanest compact rendering of the gold structure, apart from changing one interview into multiple interviews.

Mode write · case 08-techdebt · run v1.7.0-final

Structure of 8, 2 points per axis
Structure	Without Minto 7	With Minto 8	Change
Top	2	2
Key-line composition	2	2
Levels	1	2	+1
Order and kind	2	2

Quality of 10, 2 points per axis
Quality	Without Minto 8	With Minto 10	Change
Top	2	2
Same-kind grouping	2	2
Explainable order	2	2
MECE	1	2	+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-11

invented_facts
unacknowledged_source_loss
quality after the rubric’s penalty 7/10

The gold logic is recognizable, though prose obscures the hierarchy slightly and Research is omitted.

Hi Alex,

I recommend we make reducing the defect backlog the next sprint’s priority.

The backlog is growing faster than we can close it and is projected to worsen over the next year. It is already affecting retention: Customer Experience data, churn analysis, and user interviews link defect volume to customer frustration and churn.

It is also creating commercial risk. User posts, a major-account complaint, and Sales feedback show that reliability concerns are damaging our reputation and lowering close rates.

A focused sprint now will reduce both the operational backlog and its customer and revenue impact.

With Minto

prompt with the skill · blind label out-15

invented_facts
quality after the rubric’s penalty 8/10

This is the cleanest compact rendering of the gold structure, apart from changing one interview into multiple interviews.

Hi Alex — we should use the next sprint to reduce the defect backlog before it compounds into higher churn, brand damage, and harder sales.

The backlog is projected to grow over the next year because incoming defects exceed fixes.

Customer Experience and Research link defect volume to churn, supported by customer interviews and the churn trend.

User posts, a major-account complaint, and Sales reports show defects are already damaging trust and reducing close rates.

Please prioritize backlog reduction for the next sprint.

The judge

Recurring defect	without	with Minto
Evidence omitted or conflated instead of retained beneath a parentthe skill has the rule; the model did not follow it · Mode 3 — “Keep every fact from the source”	present	absent
Unsupported precision, causal strengthening, or new forecaststhe skill has the rule; the model did not follow it · Mode 3 — “Invent nothing”	present	present
Situation and complication absent before supportthe skill has no such rule · Core loop §3 — SCQ intro	present	absent

Decisive questions

Recommendation
without First
with Minto First
First-level kind
without Business losses
with Minto Business losses
Count
without 3
with Minto 3
All nine correctly placed?
without No; Research disappears.
with Minto Yes
Backlog as SCQ complication?
without No
with Minto No
Format
without Colleague message
with Minto Colleague message
Invented material
without Multiple interviews, customer frustration, and the forecast that one sprint will reduce customer and revenue impact
with Minto Multiple customer interviews rather than the single supplied interview
Reader question literal?
without No
with Minto No

Judge’s check	without	with Minto
Answer first	yes	yes
First-level elements	3	3
First-level kind matches the gold	yes	yes
Invented facts	yes	yes
Source lost without a note	yes	no
Mode respected	yes	yes
Reader’s question stated literally	no	no
Order type named	no	no
SCQ introduction present	no	yes

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 1 438 B

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

<!-- Original paraphrase inspired by Jory MacKay's Planio article,
     "The Pyramid Principle: How to pitch anything (and get a yes)", 2022. -->

# Fixture 08: technical-debt message

**Mode:** `write`
**Language:** `en`

## Context

You are a product manager writing to Alex, who decides the next sprint's focus.
Available evidence includes a time series of incoming and fixed defects, a
one-year projection, customer-experience data, an interview story, churn
plotted against defect volume, user posts, a complaint from a major account,
and Sales reports about falling close rates.

## Before

```text
Hi Alex,

I am increasingly worried about the defect backlog. The attached chart compares
new defects with the number we close and projects the backlog one year ahead.

Customer Experience and Research also report that defects are contributing to
churn. A second chart places churn beside defect volume, and an interview
illustrates the same issue.

There are signs of brand damage too: user posts, a complaint from a major
account, and Sales reports that these concerns are making deals harder to close.

I recommend using the next sprint to reduce the defect backlog. Let me know what
you think.
```

## Task

Rewrite this as a concise message to Alex using the Minto Pyramid Principle.

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

Prompt with Minto five parts, in order · 29 011 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 08: technical-debt message

Mode: write
Language: en

Context

You are a product manager writing to Alex, who decides the next sprint's focus.
Available evidence includes a time series of incoming and fixed defects, a
one-year projection, customer-experience data, an interview story, churn
plotted against defect volume, user posts, a complaint from a major account,
and Sales reports about falling close rates.

Before

Hi Alex,
                
                I am increasingly worried about the defect backlog. The attached chart compares
                new defects with the number we close and projects the backlog one year ahead.
                
                Customer Experience and Research also report that defects are contributing to
                churn. A second chart places churn beside defect volume, and an interview
                illustrates the same issue.
                
                There are signs of brand damage too: user posts, a complaint from a major
                account, and Sales reports that these concerns are making deals harder to close.
                
                I recommend using the next sprint to reduce the defect backlog. Let me know what
                you think.

Task

Rewrite this as a concise message to Alex using the Minto Pyramid Principle.

The judge’s gold gold.md

Gold 08: technical-debt message

This is an original modern fixture inspired by the cited Planio example, not a
book-derived gold text.

Expected structure

Top: Use the next sprint to reduce the defect backlog.

First-level reasons:

The backlog is growing faster than the team can reduce it.
Defects are driving customer churn.
Defects are damaging brand perception and sales.

Evidence stays beneath its reason: incoming/fixed/projection data under backlog
growth; CX, interview, and churn chart under churn; user posts, account
complaint, and Sales reports under brand and sales.

The recommendation must move from the last paragraph to the first sentence.
Specific percentages, customer names, deadlines, or defect counts are
inventions. A compact colleague message is preferable to a formal memo.

An output that treats backlog growth as the SCQ Complication and uses only the
two external business losses as its key line may be stronger than this gold and
must not be penalized.

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