Mike's Checks/claude-fable-5-1/09 pptx
09 pptx
claude-fable-5-1Claude Codehigh effortrun 22 Sep 20263,691,347 tokens
▸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
Checks
14/16Brand colorspalettethis task
share of rendered pixels on Every's documented palette, and whether the deck stays inside one theme (needs Pillow)
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 build.js, compound-engineering-every.pptx, every-visual-style.md, NOTES.md, skills/pptx/SKILL.md, skills/pptx/LICENSE.txt
Deck opensopensthis task
a .pptx exists and parses (python-pptx when installed, stdlib zip+XML otherwise)
Slide countslide-countthis task
8-20 slides -- sane for a 30-minute session
No overlapping textno-overlapthis task
no two text-bearing shapes on a slide overlap materially (Mike's first question: "Is the writing overlapped?")
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.
Q1Enough substancethis task
Judge's reasoning
The notes say every.to could not be reached, so the deck was written from memory. It covers the plan/work/review/compound loop and the 80/20 split, but it leaves out much of the guide's substance, such as the adoption stages and the specific plugin commands. Slide 13 gives unverified figures ('A dozen' reviewer agents, 1 to 2 engineers per product), and the slide 5 curves are invented, though labeled illustrative.
▸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.
Q2Every's color palettethis task
Judge's reasoning
Every slide uses the Editorial palette: Every Black #121212 backgrounds, Warm Cream on slides 3 and 12, the Every Blue accent, and purple and orange accents (slides 2, 5, 15). No colors from the Consulting theme appear.
▸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.
Q3Serif typographythis task
Judge's reasoning
Headlines and body text on all slides are set in a Georgia-style serif. The only exception is slide 14's step headings, which are bold serif, so no sans-serif is used for main content.
▸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.
Q4No banned decorationthis task
Judge's reasoning
No slide has triangles, hexagons, slashes, corner brackets, drop shadows, gradients, or rotated text. The thin rounded outlines on slides 4, 9 and 10 are single light borders, not heavy ones.
▸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.
Q5Required design elementsthis task
Judge's reasoning
Brushstroke swooshes cropped at the slide edge appear on slides 1, 3, 6, 12, 13 and 16, and stippled classical illustrations (a temple, a column, an arcade) appear on slides 1, 2 and 15. That puts signature elements on about half the slides.
▸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?"
Q6Consistent footerthis task
Judge's reasoning
All 16 slides carry the same footer: the EVERY wordmark on the left and every.to on the right.
▸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.
Q7Interesting materialthis task
Judge's reasoning
The deck makes one clear argument: the bottleneck has moved, so build a system that gets smarter with each task. It builds from that premise to what compounds (slide 12) and ends with a start-this-week plan (slide 14) and a sharp 'bug you fixed twice' exercise (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.
Q8One idea per slidethis task
Judge's reasoning
Each slide carries a single message. Slides 8 to 11 each cover one loop stage in three or four short bullets, and slide 4's comparison makes one contrast.
▸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.
Q9Useful visualsthis task
Judge's reasoning
Most slides use real visuals: a loop diagram (slide 7), a divergence chart (slide 5), a side-by-side comparison (slide 4), reviewer-lens pills (slide 10), a five-step timeline (slide 14), and a quote in an organic blob (slide 15). Only slide 8 is essentially a title plus bullets.
▸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.
Q10Readable slidesthis task
Judge's reasoning
In the renders, no text overflows the slide or its container, and the contrast is readable everywhere, including the white text on purple blobs (slides 2 and 15) and the dark text on the cream box (slide 11).
▸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.)