Mike's Checks
Checks

Mike's Checks/claude-opus-5.5/09 pptx

09 pptx

claude-opus-5.5Claude Codehigh effortrun 20 Sep 20262,736,349 tokens

Compare models
15/16
checks passed
94%
▸Instructions — what the model was asked

create a powerpoint in the every brand style on compound engineering, 30 min session https://every.to/guides/compound-engineering

A pptx skill is in skills/pptx/ — read skills/pptx/SKILL.md first. pptxgenjs is installed in the workspace, so require("pptxgenjs") works from here with no network. The brand guide is every-visual-style.md.

Answer

slide-01.png

Checks

15/16
Script checks 5/6answered by a program
fail

Brand colorspalettethis task

share of rendered pixels on Every's documented palette, and whether the deck stays inside one theme (needs Pillow)

pass

No AI-tell wordingai-wordingevery task

deliverable text contains none of the shared AI-tell phrases in bench/ai-tells.txt. Task checks may add narrower contractual bans, but must not repeat this shared floor.

inspected ANSWER.md, Compound-Engineering-Every.pptx, every-visual-style.md, skills/pptx/SKILL.md, skills/pptx/LICENSE.txt, build/build.js, build/make-assets.js, build/qa.js

pass

Deck opensopensthis task

a .pptx exists and parses (python-pptx when installed, stdlib zip+XML otherwise)

pass

Slide countslide-countthis task

8-20 slides -- sane for a 30-minute session

pass

No overlapping textno-overlapthis task

no two text-bearing shapes on a slide overlap materially (Mike's first question: "Is the writing overlapped?")

pass

Slides renderrenderthis task

every slide rendered to a PNG in <output-dir>/_screenshots/ via LibreOffice (soffice --convert-to pdf) + pdftoppm. FAIL when required render tools are unavailable.

Judge checks 10/10judged by Claude
pass

Q1Every's color palettethis task

Judge's reasoning

Theme 1 used consistently on all 18 slides: #121212 background, #C0F0FB blue accent, #FA7B20 orange, #7301CC purple blob (slide 17), #349361 green (slide 9) — no theme flipping, no corporate blue or gray.

▸Rubric

The palette is Every's. Theme 1 (Editorial): background Every Black `#121212` (or Warm Cream `#F5F2ED` for light slides), Every Blue `#C0F0FB` as the signature accent, white text, with `#FA7B20` / `#E9731E` / `#C4400F` / `#349361` / `#1324CB` / `#7301CC` as accents. Theme 2 (Consulting): background Teal Dark `#0F5258` with Teal Medium `#4999A0` for depth, Warm White `#FFFEFB` text, `#BB7B19` / `#F8DE6E` / `#2E8D23` accents. FAIL if the deck's colors are visibly not these — corporate blue, generic slide-template gray, purple-black AI dark mode, neon gradients — or if it flips between the two themes across slides. Close-but-different shades are fine; a different palette is not.

pass

Q2Serif typographythis task

Judge's reasoning

Georgia serif carries every headline and body block (slides 3, 8, 11, 13); Arial appears only in small labels — session indicator (slide 1), 'THE IDEA'/'TRIAGE' kickers, chart axis labels (slide 4), captions and the every.to footer.

▸Rubric

Typography is serif. The brand is serif-first: Signifier, or its documented PowerPoint substitutes Georgia and Times New Roman. Sans-serif (Switzer / DM Sans) is allowed only for small labels — session indicators, footers, captions. FAIL if headlines or body text are set in a sans-serif face (Arial, Helvetica, Calibri, Inter). "Sans-serif for main content" is on the brand guide's explicit avoid list.

pass

Q3No banned decorationthis task

Judge's reasoning

No triangles, hexagons, diagonal slashes, corner brackets, drop shadows, stock photos or gradient backgrounds; borders are 0.75–1.25pt single-weight, and the only rotated text is the native 9pt y-axis title on slide 4's chart, which is chart chrome rather than decorative treatment.

▸Rubric

No forbidden decoration. The brand guide bans, in both themes: triangles, hexagons and other geometric accents; diagonal slashes and hard section dividers; corner brackets or L-shaped frames; drop shadows on boxes; heavy or double borders; stock photography; gradient backgrounds; rotated or outlined text. FAIL if any of these appears on any slide.

pass

Q4Required design elementsthis task

Judge's reasoning

Procedurally drawn Every Blue brushstroke swooshes, cropped at the slide edge and scaled large, appear on slides 1, 2, 3, 5, 7, 9, 11, 12, 14, 16, 18 plus the hand-painted ring on slide 6 — 12 of 18, well above one in three; no classical illustrations, but the asset library was absent from the workspace.

▸Rubric

The signature elements are there. Every decks carry organic brushstroke swooshes (the E / O / R SVG shapes, cropped at the slide edge, scaled large) and stippled classical illustrations — Greek and Roman architecture, figures, busts, sometimes with modern elements. The guide says to use the swooshes "liberally once every two or three slides." FAIL if the deck has neither swooshes nor classical illustration, or if such elements appear on fewer than roughly one slide in three. Mike's question on this eval: "does it use the, uh, SVGs?"

pass

Q5Consistent footerthis task

Judge's reasoning

The base() helper stamps EVERY left and every.to right on all 18 slides, including title (slide 1) and closing (slide 18), with no omissions.

▸Rubric

The footer is consistent. Theme 1: EVERY logo left, `every.to` right. Theme 2: EVERY *Consulting* left, session indicator right. FAIL if content slides carry no footer, or if the footer appears on some and not others.

pass

Q6Enough substancethis task

Judge's reasoning

Carries the guide's load-bearing mechanisms: the four-step plan/work/review/compound loop (slides 6–11), 'plans are the new code', parallel agents on separate worktrees (slide 9), multi-lens reviewer agents with P1/P2/P3 triage (slide 10), where lessons persist — CLAUDE.md/AGENTS.md, solution docs, subagents, tests and hooks (slide 12), the 50/50 rule (slide 14) and the plugin commands (slide 16); the one illustrative chart is labelled 'Illustrative' (slide 4).

▸Rubric

The content has real depth. Mike: "the main failing of the decks generated by AI is still the content is quite shallow." PASS when the deck carries the load-bearing substance of the selected case's brief and source material: its important mechanisms, distinctions, evidence, and consequences. FAIL if the deck could have been written without reading those materials, reduces the subject to generic advice, or makes unsupported claims.

pass

Q7Interesting materialthis task

Judge's reasoning

Makes a pointed argument rather than an inventory: 'the step everyone skips' for Compound (slide 11), 'typing code is no longer the bottleneck — judgment is' (slide 7), 'the system, not the person, carries the accumulated knowledge' (slide 5), and the ladder annotated 'compounding really starts here' (slide 15).

▸Rubric

It picked interesting things to say. Mike's question on this eval: "does it pick out interesting things to write about." PASS when the deck makes a selective, coherent argument about what this audience should remember or do. FAIL if it merely inventories the supplied material in source order, restates headings, or includes facts without a point of view about why they matter.

pass

Q8One idea per slidethis task

Judge's reasoning

Each slide has one headline message with supporting structure and generous whitespace — slide 3 is a single sentence, slide 14 one rule, slide 17 one exercise; the densest, slide 10, is two tiers of the single Review idea and still reads easily at room distance.

▸Rubric

One idea per slide. Mike: it fails "if it tries to fit too many ideas on one slide." The brand guide says the same thing — "clear focal point: one main message per slide," "spacious, not cluttered." FAIL if any single slide carries more than one idea, or is packed so densely that a room could not read it while the presenter talks.

pass

Q9Useful visualsthis task

Judge's reasoning

Real visuals dominate: the circular loop diagram on a painted ring (slide 6), divergent line chart (slide 4), proportional agent bars (slide 9), four-stage arrow progression (slide 11), donut (slide 14), rising-column adoption ladder (slide 15), shape-built let-go/adopt comparison (slide 13) and the purple organic blob (slide 17) — only slide 16 is list-plus-panel.

▸Rubric

Real visual elements, not walls of bullets. Mike's question: "does it create good visual elements." Real means: a diagram of the loop, a staged progression, a 50/50 split with illustration, a quote in an organic blob, a comparison built from shapes — something that carries meaning visually. FAIL if the majority of content slides are a title plus a bulleted list.

pass

Q10Readable slidesthis task

Judge's reasoning

No overflow, clipping or collisions in any render; swooshes were routed clear of text (slides 7, 12, 16, 18), white serif on the #7301CC blob (slide 17) holds contrast, and the smallest type — slide 15's ladder captions and slide 4's axis labels — stays readable.

▸Rubric

Every slide is legible as rendered. FAIL if any slide has text running off the edge, text clipped by its container, text over an image or shape at unreadable contrast, or headline and body colliding. (A separate script check already catches overlapping text boxes; this question covers what the geometry check cannot see — overflow, clipping and contrast in the actual render.)