Quality — Field Guide QC Checklists
Gate 1: Pre-build — all editorial decisions confirmed before building starts.
Gate 2: Post-build — 100 points, pass threshold 90/100. Run after every build and after every revision.
Both gates must pass before any field guide is delivered.
Gate 1 — Pre-Build (Editorial Decisions)
Run this before opening the build skill. Any open item stops the build.
Routing Check — Run This First
Has the consultant completed the book analysis (File 07)?
- Yes — 5 ideas selected, deliverables named, interactives designed, mental model defined, prompts engineered → proceed through the checklist
- No — stop here. Do not run Gate 1 yet. Complete the book analysis first. A checklist with everything marked OPEN and no analysis completed is not a path forward — it is a blocked build.
Editorial Decisions
- [ ] Book read in full — not a summary, not chapter headings
- [ ] 5 ideas selected from the book — each produces a concrete deliverable
- [ ] Ideas form a sequence — each session's output feeds the next
- [ ] 3 interactive + 2 static concept slides designated
- [ ] Each interactive type chosen (checklist, rating, slider, or new pattern)
- [ ] 5 deliverable names confirmed — concrete nouns, not abstract concepts
- [ ] Mental model defined — two-column comparison, traits, outcome statements, hard truth
- [ ] Bridge destination confirmed — single CTA (default: Systems Diagnostic)
- [ ] Campaign keyword selected — single word, signals identity
- [ ] Attribution line confirmed — "Based on the book by [Author Name]"
Gate 2 — Post-Build (100 points, 90+ to pass)
Run in this order.
Prompt Quality (30 points)
| # | Check | Points |
|---|---|---|
| 1 | Every prompt tested by pasting into Claude — AI introduces itself, lists steps, walks through the full guided session, produces the named deliverable | 10 |
| 2 | Every prompt follows TASK/INTRODUCTION/STEP format with 5 steps | 4 |
| 3 | Every step ends with a confirmation question that pushes for honesty | 4 |
| 4 | Session handoffs are graceful — work whether or not the reader completed the previous session | 4 |
| 5 | Final prompt constrains output — "one thing per dimension" or equivalent | 3 |
| 6 | Every instruction line ends with "The AI will guide you through each step" | 2 |
| 7 | No prompt references a session that hasn't been completed yet | 3 |
Prompt testing is blocking. A field guide with untested prompts does not ship.
Interactive Functionality (20 points)
| # | Check | Points |
|---|---|---|
| 8 | Every interactive tested through 3+ scenarios with different input patterns | 6 |
| 9 | Summary/result text appears at correct threshold | 3 |
| 10 | Math is correct — percentages, averages, counts all verify manually | 4 |
| 11 | Edge cases handled — all selected, none selected, tied scores | 3 |
| 12 | Verdict/summary text is accurate for each scenario | 4 |
Interactive testing is blocking. Every scenario must be clicked through in a browser.
Copy QC (10 points)
| # | Check | Points |
|---|---|---|
| 13 | No twinning — "You don't have X. You have Y." (P1) | 2 |
| 14 | No mirror reversals (P1) | 2 |
| 15 | No three-beat parallel lists (P2) | 1 |
| 16 | No "Not because X. Because Y." (P2) | 1 |
| 17 | No rhetorical hand-holding — "Right?" "Sound familiar?" (P3) | 1 |
| 18 | No correction-revelation compound in same slide (P1) | 3 |
P1 copy failures are blocking.
Brand Compliance (20 points)
| # | Check | Points |
|---|---|---|
| 19 | Zero rgba() in the entire file — run grep -c 'rgba(' file.html and confirm 0 | 5 |
| 20 | Zero CSS variables — grep -c 'var(--' file.html confirms 0 | 2 |
| 21 | Gold text on light backgrounds uses #6b5d3e — never #b79d64 | 3 |
| 22 | No pure black (#000000) — always #1a1a1a or darker named hex | 1 |
| 23 | Typography uses rem and clamp() — not fixed px for content text | 2 |
| 24 | Cormorant Garamond font URL loads ONLY weights 300, 400, 500 — no 600/700 | 2 |
| 25 | Eyebrow weight is 600. Strong text weight is 500. | 1 |
| 26 | Copy button copied state: dark bg (#1a1a1a) + gold text (#b79d64) | 1 |
| 27 | Gold accent bar present on slide titles (::after, 40px × 3px, #b79d64) | 2 |
| 28 | Scrollbar uses solid hex (#d4c9a8 thumb, #f5f4f0 track) | 1 |
Zero rgba() is blocking. A file with any rgba() values does not ship regardless of total score.
Structure, Layout, and Visual (20 points)
| # | Check | Points |
|---|---|---|
| 29 | 14 slides in correct order — Intro, Diagnostic, Mental Model, 5 idea pairs, Bridge | 3 |
| 30 | Mental model slide (3) has two-column comparison + dark insight callout | 2 |
| 31 | Attribution line reads "Based on the book by [Author Name]" | 2 |
| 32 | Author name does NOT appear in header, title treatment, or campaign label | 1 |
| 33 | Diagnostic result says "will hit hardest" not "start with" | 1 |
| 34 | All slides use full-width stacked layout — text in container, interactive in container-wide | 3 |
| 35 | Exercise instructions merged into frame header, not floating as separate callout | 2 |
| 36 | Bridge has single centered CTA on dark background — no offer cards | 2 |
| 37 | Visual rhythm: session slides on off-white (#faf9f7), bridge on dark (#1a1a1a) | 2 |
| 38 | Rating exercises use stoplight colors (red #c45a4a → orange #d48a3c → yellow #e0c34a → green #5a9a6a) | 1 |
| 39 | Slider exercises have anchor labels describing what each end means | 1 |
Visual verification sub-checks (must complete to claim points for 29 and 34):
- File opened in browser and clicked through all 14 slides
- Navigation arrows and dots work — all dots are circles
- Interactive exercises function
- Copy button copies prompt text
- Diagnostic options and service items render on single lines
- Mental model grid stacks on mobile
- Responsive layout works at 768px and 480px
- Touch targets are 44px+ on all interactive elements
Visual verification is blocking. A file that has not been opened and clicked through does not ship.
Scoring Summary
| Category | Points |
|---|---|
| Prompt Quality | 30 |
| Interactive Functionality | 20 |
| Copy QC | 10 |
| Brand Compliance | 20 |
| Structure, Layout, and Visual | 20 |
| Total | 100 |
Pass threshold: 90/100
Blocking failures (must fix regardless of score):
- Any untested prompt
- Any untested interactive
- Any P1 copy violation
- Any rgba() in the file
- Visual verification not completed
After any revision: Return to Gate 2 and run all checks again.
Common Failure Modes
| Failure | What It Looks Like | Fix |
|---|---|---|
| rgba() remaining | grep -c 'rgba(' returns anything > 0 | Replace every instance using hex table in File 03 |
| Two-column layout | Interactive crammed into right column | Text in container, interactive in container-wide below |
| Exercise instruction disconnected | Frame header says "Your Exercise," instruction floats above | Merge: "YOUR EXERCISE — [what to do]" |
| Gold on cream text | #b79d64 text invisible on cream | All gold text on light = #6b5d3e |
| Bracket-field prompts | Old fill-in-the-blanks format | TASK/INTRODUCTION/STEP with 5 steps |
| Slider without anchors | Reader doesn't know what 1 or 10 means | Anchor labels under every slider |
| Rating without stoplight | Colors don't communicate severity | Red → orange → yellow → green |
| Multiple bridge offers | Deploy Sprint / Advisory OS cards | Single centered CTA on dark background |
| No visual rhythm | All slides same cream background | Session slides off-white, bridge dark |
| No gold accent bar | Slide titles lack signature element | ::after pseudo-element, 40px × 3px, #b79d64 |
| Missing mental model | Slide 3 absent | Two-column comparison + dark insight callout |
| Cormorant 600/700 loaded | Font URL includes bold weights | Remove from Google Fonts URL — max 500 |
| Service items wrapping | Labels too long | Keep under ~35 characters |
| Copy button gold on cream | Copied state invisible | Dark bg #1a1a1a + gold text #b79d64 |