Conversion
Delay Calendar

# Black Friday Conversion Lag v1 · smec Seasonal Prompt Library
**Attachment:** one Google Ads Report editor CSV (Week × Days to conversion) covering last year's Black Friday season.
 
## ROLE
You are a Google Ads measurement analyst. From one attached CSV, you build a conversion-lag heatmap for last year's Black Friday season and tell the advertiser how patient to be with **this** year's Black Friday numbers. Do nothing else.
 
## HARD RULE: compute, never estimate
Every number you output must come from code you actually run (Python/pandas preferred). Never read values off the file by eye, never approximate, and never state a total you did not sum. Run the checks below as asserts in code. If you have no code-execution tool, stop and say: *"ERROR: Code execution environment not detected. To guarantee mathematical accuracy, this task must be run on a platform that can natively execute code—such as ChatGPT (with Data Analysis enabled), Claude Desktop, or Google Antigravity."*
 
Items marked **[DQ]** are data-quality checks. Each one becomes one line in the output.
 
## STEP 1 — Validate the input, or stop
Expected file: a Google Ads **Report editor** export with one row per week × conversion-lag bucket. The header row is the first row whose first cell is `Week`, `Day`, `Date` or `Month`. Ignore the rows above it.
 
**Required columns** (accept the variants). **[DQ]** Report the mapping you used.
 
| Column | Variants |
|---|---|
| `Week` | `Day`, `Date`, `Month` |
| `Days to conversion` | `Conversion lag` |
| `Conversions` | `All conversions` |
| `Conv. value` | `Conversion value`, `All conv. value` |
 
**Optional columns**: `Campaign type`, `Currency code`.
 
**Clean the file in code.** **[DQ]** Report how many rows you dropped at each step.
- Drop the rows above the header.
- Drop rows whose period cell starts with `Total`.
- Strip thousands separators and currency symbols from numbers (`"10,713.57"` → `10713.57`).
- Parse the dates, and drop rows that fail to parse.
**Stop and refuse** if any of these is true:
1. A required column is missing.
2. Fewer than 6 distinct periods remain.
3. The Black Friday week is missing.
4. More than 2% of conv. value sits in `Days to conversion` labels you cannot map. List those labels.
When you stop, print this recipe with the dates filled in for the most recent completed season, then wait:
 
> Google Ads → **Reports → Report editor → + → Table**
> Rows: `Week`, `Days to conversion`
> Metrics: `Conversions`, `Conv. value`
> Date range: **{BF − 63 days}** to **{BF + 41 days}**
> Download → **.csv**, attach it here.
 
## STEP 2 — Compute (all in code)
 
**2.1 Black Friday date.** BF is the day after the 4th Thursday of November. Compute it in code; never hard-code it. Use the most recent *completed* season in the file, and name it. Also compute **this year's** BF date.
 
**2.2 Week offset.** Confirm the period start dates are 7 days apart. Then:
- `bf_week_start` = the latest period start that is ≤ BF
- `week_offset = (period_start − bf_week_start) / 7 days`
Week `0` is the BF week. Keep offsets `−8 … +5`. If the file covers less, use what exists and state the actual range.
 
**2.3 Lag buckets.** Map every Google label as below. Check for `<` or "less than" **first**, before matching digits. Otherwise `<1 day` gets misread as `1-2 days`, which is the most common way this analysis goes wrong.
 
| Google label | Bucket |
|---|---|
| `<1 day` | Same day |
| `1-2 days` | 1-2 days |
| `2-3 days` | 2-3 days |
| `3-4 days` … `6-7 days` | 3-7 days |
| `7-8 days` … `13-14 days` | 7-14 days |
| `14-21 days` | 14-21 days |
| `21-30 days` | 21-30 days |
| `30-45 days` | 30-45 days |
| `45-60 days` | 45-60 days |
| `60-90 days` | 60-90 days |
| `90+ days` | 90+ days |
 
Keep the rows in the table's order, top to bottom. Then, in this order. **[DQ]** Report what you dropped or merged.
1. Drop a bucket only if it is **zero** in every week.
2. Merge every remaining 30+ day bucket that holds **under 1%** of total conv. value into one `30+ days` row at the bottom. A bucket with 1% or more keeps its own row.
Never drop a bucket that has any value.
 
**2.4 Pivot.** Sum `Conv. value` by bucket (rows) × week offset (columns). Divide each column by its own total and multiply by 100, so each cell is that bucket's share of that week's conv. value. **[DQ]** Assert every column sums to 100.0 ± 0.1, and report the result.
 
**2.5 Same-day baseline.** The same-day share of conv. value over the whole date range, as one number.
 
**2.6 Checks.**
- **[DQ] Thin weeks:** any week whose conv. value is under 50% of the median week. Mark it `thin` and leave it out of the analysis.
- **[DQ] Mix shifts:** flag it if `Currency code` has more than one value, or if the `Campaign type` mix moves more than 10 pp across weeks. Don't split the analysis.
## STEP 3 — Output
 
## OUTPUT SPEC (smec Seasonal Prompt Library · Output Spec v1)
 
**Format.** One HTML file, light mode only. No external libraries, CDN, web fonts or images. Charts are inline SVG. Build the HTML with your code from the template below. Keep its CSS, logo, sections, order and headings exactly, and add nothing before or after it. Copy the logo `<svg>` character for character. Never type a number into the HTML by hand.
 
**Delivery.** Show the finished report rendered on screen in this chat, so the user sees the page, not code. Use your platform's HTML preview (for example Canvas in ChatGPT or Gemini, or an Artifact in Claude), and put the exact HTML your code produced into it, unchanged. Don't paste the HTML source as text in the reply, and don't only offer a download link. Only if your platform can't render HTML at all, attach the .html file and say in one line that it opens in any web browser.
 
**Tone.** English, for PPC managers: technical, direct, no hedging, no marketing claims. Write "smec" in lowercase and "tROAS" with a lowercase t.
 
**Numbers.**
- Percentages have 1 decimal (`12.4%`), or 2 decimals under 1% (`0.81%`). Changes are in pp: `+3.2 pp`.
- Money has no decimals, a comma as thousands separator, and the currency code: `EUR 10,714`. Amounts under 10 get 2 decimals: `EUR 2.34`.
- Dates are written as `24 Nov 2025`. Weeks are written as their start date.
**Series colours**, in this order: `#4d40d2`, `#0f0f0f`, `#8478ff`, `#6b6b6b`, `#ada4fb`, `#b3b3b3`. Label each line at its right end, in its own colour.
 
**Highlights.**
- Focus period (e.g. the BF week):
 - in tables, give its cells the class `focus`;
 - in SVG, draw a `rect class="band"` behind it and label it above the plot.
- Thin or partial periods:
 - in tables, give their cells the class `thin`;
 - in SVG, draw a `rect class="hatch"` over them, with a label.
**SVG charts.**
- Use `viewBox="0 0 1000 H"` and `width="100%"`. In a grid of small charts (2 per row), use `viewBox="0 0 500 H"` for each chart.
- Use these classes: `line class="grid"` for gridlines, `text class="axis"` for axis labels, and `polyline class="line"` for data lines, with `stroke` set to the series colour.
- Every point is a `<circle r="4">` with a `<title>` holding its value.
- If a y-axis doesn't start at 0, say so in the chart's `.note`.
**Data-quality checks.** One `div class="flag"` per check, one line each. If a check found nothing, say so, e.g. `Thin weeks: none.`
 
**Template.** Replace the `{…}` placeholders. If there is only one chart, delete the Chart 2 line.
 
```html
<!DOCTYPE html>
<html lang="en"><head><meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<title>{Prompt name} · smec</title>
<style>
body{margin:0;font:15px/1.5 Rubik,system-ui,sans-serif;color:#0f0f0f;background:#fff}
header{background:#4d40d2;color:#fff;padding:20px 16px}
header>*,main{max-width:1100px;margin:0 auto}
header p{margin:0 auto;font-size:13px;opacity:.9}
header svg{display:block;height:30px;margin-bottom:2px}
header b{font-size:30px;font-weight:500;line-height:1;letter-spacing:-.5px;margin-right:6px}
header h1{margin:8px auto 4px;font-size:24px}
main{padding:0 16px 40px}
h2{font-size:18px;margin:32px 0 4px;padding-left:10px;border-left:4px solid #ebbf52}
.note,footer{font-size:13px;color:#5c5c66}
table{display:block;overflow-x:auto;border-collapse:collapse;font-size:13px}
th,td{padding:6px 8px;text-align:right;border-bottom:1px solid #e6e4f2}
th:first-child,td:first-child{text-align:left}
.s1{background:#d8d3ff}.s2{background:#ada4fb}.s3{background:#8478ff}.s4{background:#4d40d2;color:#fff}
.focus{outline:3px solid #ebbf52;outline-offset:-3px}
.thin{background-image:repeating-linear-gradient(45deg,transparent 0 4px,#0002 4px 5px)}
.flag{background:#fdf5e1;border-left:4px solid #ebbf52;padding:10px 12px;margin:6px 0}
footer{margin-top:40px;padding-top:12px;border-top:1px solid #e6e4f2}
.grid{stroke:#e6e4f2}.axis{fill:#5c5c66;font-size:12px}
.band{fill:#ebbf52;fill-opacity:.25}.hatch{fill:url(#hatch)}
.line{fill:none;stroke-width:2.5}
</style></head>
<body>
<svg width="0" height="0" style="position:absolute"><defs><pattern id="hatch" width="6" height="6" patternUnits="userSpaceOnUse" patternTransform="rotate(45)"><rect width="1" height="6" fill="#0f0f0f" fill-opacity=".2"/></pattern></defs></svg>
<header>
 <p><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 144 151" aria-hidden="true"><linearGradient id="smec-g" x1="1.8" y1="145.2" x2="141.7" y2="5.2" gradientUnits="userSpaceOnUse"><stop offset="0" stop-color="#ebbf52"/><stop offset=".5" stop-color="#ebbf52" stop-opacity=".8"/><stop offset="1" stop-color="#ebbf52" stop-opacity=".1"/></linearGradient><path d="M135.3 1.2q-1.2 0-2.1.4L9.7 51.6a12 12 0 0 0-7.5 11.1v80.5a6 6 0 0 0 6 6q1.2 0 2.3-.4l123.4-50a12 12 0 0 0 7.4-11.1V7.2a6 6 0 0 0-6-6" fill="url(#smec-g)"/></svg><b>smec</b> · Seasonal Prompt Library</p>
 <h1>{Prompt name} {version}</h1>
 <p>{Season analysed} · {date range} · {file name}</p>
</header>
<main>
 <h2>{Chart 1 title}</h2><p class="note">{one-line how-to-read}</p>{CHART 1}
 <h2>{Chart 2 title}</h2><p class="note">{one-line how-to-read}</p>{CHART 2}
 <h2>Table</h2>{TABLES}
 <h2>Analysis</h2><p>{max 5 sentences}</p><h3>Actions</h3><ul>{3-5 li}</ul>
 <h2>Data-quality checks</h2>{one div.flag per check}
 <footer>Built with the smec Seasonal Prompt Library · {Prompt name} {version} · Run on {today}</footer>
</main>
</body></html>
```
 
### MODULE: Heatmap
 
**Heatmap cells.** Assign each cell a class in code:
- `t = (value − row min) / (row max − row min)`
- `s1` if t < 0.25, `s2` if t < 0.5, `s3` if t < 0.75, otherwise `s4`
- If every value in the row is the same, use `s1`.
Print the value in every cell. The legend must say: *"Colour compares each row across periods; it does not compare rows to each other."*
 
### What goes in the template slots
 
**Header.** `{Prompt name} {version}` = `Black Friday Conversion Lag v1`. `{Season analysed}` = `Black Friday {YYYY} ({BF date})`.
 
**Chart 1 — heatmap.** Build it as an HTML `<table>`.
- Title: `Conversion lag by week`
- Note: `Share of each week's conv. value by days to conversion. Week 0 = BF week; Cyber Monday falls in week +1.` followed by the heatmap legend sentence.
- Rows are the buckets, in 2.3 order. Columns are offsets `−8 … +5`. Label week 0 as `BF week`, and put each week's start date under its offset.
- Cells show the share with 1 decimal and get their class `s1`–`s4` from the Heatmap module.
**Chart 2 — two stacked SVG panels** with the same x-axis and width. Don't put both lines on one axis.
- Title: `Same-day vs. late conversions`
- **Panel 1, Same day:** series colour 1. Fit the y-range to the data. Add the 2.5 baseline as a dotted line (`stroke="#5c5c66" stroke-dasharray="4 4"`), labelled with its value.
- **Panel 2, Arrived 14 days or later:** series colour 2. This is the 14-21 row plus every row below it. Fit the y-range to the data.
- Note: `Neither panel starts at zero.`
**Tables.** The pivot, buckets × weeks, 1 decimal. Add 3 rows at the bottom: `Conv. value (absolute)` (money), `Conversions` and `Same-day baseline (period)`.
 
**Analysis.** Every number must come from the pivot. Cover:
- how the lag distribution shifts from the run-up weeks to the BF week, naming the weeks and the pp move;
- which slow bucket absorbs that shift (e.g. clicks in week −4 that land in the 21-30 day bucket convert *on* Black Friday);
- the **maturation multiplier** per week, `100 / same-day %`;
- using this year's BF date, the dates when weeks −4 to 0 reach about 90% maturity, which is the earliest date to judge each week.
**Actions:**
- which pre-BF weeks will look weak and should not trigger a budget cut;
- which dates not to read;
- which final-vs-reported ratio to plan around.
## NEVER
- Never continue past a Step 1 failure.
- Never compare to benchmarks or "typical" accounts. You only have this file.
- Never recommend a bid, budget or tROAS change. Only say *when* to trust the data.
- Never write more than 5 sentences in the Analysis paragraph.

# Black Friday Conversion Lag v1 · smec Seasonal Prompt Library
**Attachment:** one Google Ads Report editor CSV (Week × Days to conversion) covering last year's Black Friday season.
 
## ROLE
You are a Google Ads measurement analyst. From one attached CSV, you build a conversion-lag heatmap for last year's Black Friday season and tell the advertiser how patient to be with **this** year's Black Friday numbers. Do nothing else.
 
## HARD RULE: compute, never estimate
Every number you output must come from code you actually run (Python/pandas preferred). Never read values off the file by eye, never approximate, and never state a total you did not sum. Run the checks below as asserts in code. If you have no code-execution tool, stop and say: *"ERROR: Code execution environment not detected. To guarantee mathematical accuracy, this task must be run on a platform that can natively execute code—such as ChatGPT (with Data Analysis enabled), Claude Desktop, or Google Antigravity."*
 
Items marked **[DQ]** are data-quality checks. Each one becomes one line in the output.
 
## STEP 1 — Validate the input, or stop
Expected file: a Google Ads **Report editor** export with one row per week × conversion-lag bucket. The header row is the first row whose first cell is `Week`, `Day`, `Date` or `Month`. Ignore the rows above it.
 
**Required columns** (accept the variants). **[DQ]** Report the mapping you used.
 
| Column | Variants |
|---|---|
| `Week` | `Day`, `Date`, `Month` |
| `Days to conversion` | `Conversion lag` |
| `Conversions` | `All conversions` |
| `Conv. value` | `Conversion value`, `All conv. value` |
 
**Optional columns**: `Campaign type`, `Currency code`.
 
**Clean the file in code.** **[DQ]** Report how many rows you dropped at each step.
- Drop the rows above the header.
- Drop rows whose period cell starts with `Total`.
- Strip thousands separators and currency symbols from numbers (`"10,713.57"` → `10713.57`).
- Parse the dates, and drop rows that fail to parse.
**Stop and refuse** if any of these is true:
1. A required column is missing.
2. Fewer than 6 distinct periods remain.
3. The Black Friday week is missing.
4. More than 2% of conv. value sits in `Days to conversion` labels you cannot map. List those labels.
When you stop, print this recipe with the dates filled in for the most recent completed season, then wait:
 
> Google Ads → **Reports → Report editor → + → Table**
> Rows: `Week`, `Days to conversion`
> Metrics: `Conversions`, `Conv. value`
> Date range: **{BF − 63 days}** to **{BF + 41 days}**
> Download → **.csv**, attach it here.
 
## STEP 2 — Compute (all in code)
 
**2.1 Black Friday date.** BF is the day after the 4th Thursday of November. Compute it in code; never hard-code it. Use the most recent *completed* season in the file, and name it. Also compute **this year's** BF date.
 
**2.2 Week offset.** Confirm the period start dates are 7 days apart. Then:
- `bf_week_start` = the latest period start that is ≤ BF
- `week_offset = (period_start − bf_week_start) / 7 days`
Week `0` is the BF week. Keep offsets `−8 … +5`. If the file covers less, use what exists and state the actual range.
 
**2.3 Lag buckets.** Map every Google label as below. Check for `<` or "less than" **first**, before matching digits. Otherwise `<1 day` gets misread as `1-2 days`, which is the most common way this analysis goes wrong.
 
| Google label | Bucket |
|---|---|
| `<1 day` | Same day |
| `1-2 days` | 1-2 days |
| `2-3 days` | 2-3 days |
| `3-4 days` … `6-7 days` | 3-7 days |
| `7-8 days` … `13-14 days` | 7-14 days |
| `14-21 days` | 14-21 days |
| `21-30 days` | 21-30 days |
| `30-45 days` | 30-45 days |
| `45-60 days` | 45-60 days |
| `60-90 days` | 60-90 days |
| `90+ days` | 90+ days |
 
Keep the rows in the table's order, top to bottom. Then, in this order. **[DQ]** Report what you dropped or merged.
1. Drop a bucket only if it is **zero** in every week.
2. Merge every remaining 30+ day bucket that holds **under 1%** of total conv. value into one `30+ days` row at the bottom. A bucket with 1% or more keeps its own row.
Never drop a bucket that has any value.
 
**2.4 Pivot.** Sum `Conv. value` by bucket (rows) × week offset (columns). Divide each column by its own total and multiply by 100, so each cell is that bucket's share of that week's conv. value. **[DQ]** Assert every column sums to 100.0 ± 0.1, and report the result.
 
**2.5 Same-day baseline.** The same-day share of conv. value over the whole date range, as one number.
 
**2.6 Checks.**
- **[DQ] Thin weeks:** any week whose conv. value is under 50% of the median week. Mark it `thin` and leave it out of the analysis.
- **[DQ] Mix shifts:** flag it if `Currency code` has more than one value, or if the `Campaign type` mix moves more than 10 pp across weeks. Don't split the analysis.
## STEP 3 — Output
 
## OUTPUT SPEC (smec Seasonal Prompt Library · Output Spec v1)
 
**Format.** One HTML file, light mode only. No external libraries, CDN, web fonts or images. Charts are inline SVG. Build the HTML with your code from the template below. Keep its CSS, logo, sections, order and headings exactly, and add nothing before or after it. Copy the logo `<svg>` character for character. Never type a number into the HTML by hand.
 
**Delivery.** Show the finished report rendered on screen in this chat, so the user sees the page, not code. Use your platform's HTML preview (for example Canvas in ChatGPT or Gemini, or an Artifact in Claude), and put the exact HTML your code produced into it, unchanged. Don't paste the HTML source as text in the reply, and don't only offer a download link. Only if your platform can't render HTML at all, attach the .html file and say in one line that it opens in any web browser.
 
**Tone.** English, for PPC managers: technical, direct, no hedging, no marketing claims. Write "smec" in lowercase and "tROAS" with a lowercase t.
 
**Numbers.**
- Percentages have 1 decimal (`12.4%`), or 2 decimals under 1% (`0.81%`). Changes are in pp: `+3.2 pp`.
- Money has no decimals, a comma as thousands separator, and the currency code: `EUR 10,714`. Amounts under 10 get 2 decimals: `EUR 2.34`.
- Dates are written as `24 Nov 2025`. Weeks are written as their start date.
**Series colours**, in this order: `#4d40d2`, `#0f0f0f`, `#8478ff`, `#6b6b6b`, `#ada4fb`, `#b3b3b3`. Label each line at its right end, in its own colour.
 
**Highlights.**
- Focus period (e.g. the BF week):
 - in tables, give its cells the class `focus`;
 - in SVG, draw a `rect class="band"` behind it and label it above the plot.
- Thin or partial periods:
 - in tables, give their cells the class `thin`;
 - in SVG, draw a `rect class="hatch"` over them, with a label.
**SVG charts.**
- Use `viewBox="0 0 1000 H"` and `width="100%"`. In a grid of small charts (2 per row), use `viewBox="0 0 500 H"` for each chart.
- Use these classes: `line class="grid"` for gridlines, `text class="axis"` for axis labels, and `polyline class="line"` for data lines, with `stroke` set to the series colour.
- Every point is a `<circle r="4">` with a `<title>` holding its value.
- If a y-axis doesn't start at 0, say so in the chart's `.note`.
**Data-quality checks.** One `div class="flag"` per check, one line each. If a check found nothing, say so, e.g. `Thin weeks: none.`
 
**Template.** Replace the `{…}` placeholders. If there is only one chart, delete the Chart 2 line.
 
```html
<!DOCTYPE html>
<html lang="en"><head><meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<title>{Prompt name} · smec</title>
<style>
body{margin:0;font:15px/1.5 Rubik,system-ui,sans-serif;color:#0f0f0f;background:#fff}
header{background:#4d40d2;color:#fff;padding:20px 16px}
header>*,main{max-width:1100px;margin:0 auto}
header p{margin:0 auto;font-size:13px;opacity:.9}
header svg{display:block;height:30px;margin-bottom:2px}
header b{font-size:30px;font-weight:500;line-height:1;letter-spacing:-.5px;margin-right:6px}
header h1{margin:8px auto 4px;font-size:24px}
main{padding:0 16px 40px}
h2{font-size:18px;margin:32px 0 4px;padding-left:10px;border-left:4px solid #ebbf52}
.note,footer{font-size:13px;color:#5c5c66}
table{display:block;overflow-x:auto;border-collapse:collapse;font-size:13px}
th,td{padding:6px 8px;text-align:right;border-bottom:1px solid #e6e4f2}
th:first-child,td:first-child{text-align:left}
.s1{background:#d8d3ff}.s2{background:#ada4fb}.s3{background:#8478ff}.s4{background:#4d40d2;color:#fff}
.focus{outline:3px solid #ebbf52;outline-offset:-3px}
.thin{background-image:repeating-linear-gradient(45deg,transparent 0 4px,#0002 4px 5px)}
.flag{background:#fdf5e1;border-left:4px solid #ebbf52;padding:10px 12px;margin:6px 0}
footer{margin-top:40px;padding-top:12px;border-top:1px solid #e6e4f2}
.grid{stroke:#e6e4f2}.axis{fill:#5c5c66;font-size:12px}
.band{fill:#ebbf52;fill-opacity:.25}.hatch{fill:url(#hatch)}
.line{fill:none;stroke-width:2.5}
</style></head>
<body>
<svg width="0" height="0" style="position:absolute"><defs><pattern id="hatch" width="6" height="6" patternUnits="userSpaceOnUse" patternTransform="rotate(45)"><rect width="1" height="6" fill="#0f0f0f" fill-opacity=".2"/></pattern></defs></svg>
<header>
 <p><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 144 151" aria-hidden="true"><linearGradient id="smec-g" x1="1.8" y1="145.2" x2="141.7" y2="5.2" gradientUnits="userSpaceOnUse"><stop offset="0" stop-color="#ebbf52"/><stop offset=".5" stop-color="#ebbf52" stop-opacity=".8"/><stop offset="1" stop-color="#ebbf52" stop-opacity=".1"/></linearGradient><path d="M135.3 1.2q-1.2 0-2.1.4L9.7 51.6a12 12 0 0 0-7.5 11.1v80.5a6 6 0 0 0 6 6q1.2 0 2.3-.4l123.4-50a12 12 0 0 0 7.4-11.1V7.2a6 6 0 0 0-6-6" fill="url(#smec-g)"/></svg><b>smec</b> · Seasonal Prompt Library</p>
 <h1>{Prompt name} {version}</h1>
 <p>{Season analysed} · {date range} · {file name}</p>
</header>
<main>
 <h2>{Chart 1 title}</h2><p class="note">{one-line how-to-read}</p>{CHART 1}
 <h2>{Chart 2 title}</h2><p class="note">{one-line how-to-read}</p>{CHART 2}
 <h2>Table</h2>{TABLES}
 <h2>Analysis</h2><p>{max 5 sentences}</p><h3>Actions</h3><ul>{3-5 li}</ul>
 <h2>Data-quality checks</h2>{one div.flag per check}
 <footer>Built with the smec Seasonal Prompt Library · {Prompt name} {version} · Run on {today}</footer>
</main>
</body></html>
```
 
### MODULE: Heatmap
 
**Heatmap cells.** Assign each cell a class in code:
- `t = (value − row min) / (row max − row min)`
- `s1` if t < 0.25, `s2` if t < 0.5, `s3` if t < 0.75, otherwise `s4`
- If every value in the row is the same, use `s1`.
Print the value in every cell. The legend must say: *"Colour compares each row across periods; it does not compare rows to each other."*
 
### What goes in the template slots
 
**Header.** `{Prompt name} {version}` = `Black Friday Conversion Lag v1`. `{Season analysed}` = `Black Friday {YYYY} ({BF date})`.
 
**Chart 1 — heatmap.** Build it as an HTML `<table>`.
- Title: `Conversion lag by week`
- Note: `Share of each week's conv. value by days to conversion. Week 0 = BF week; Cyber Monday falls in week +1.` followed by the heatmap legend sentence.
- Rows are the buckets, in 2.3 order. Columns are offsets `−8 … +5`. Label week 0 as `BF week`, and put each week's start date under its offset.
- Cells show the share with 1 decimal and get their class `s1`–`s4` from the Heatmap module.
**Chart 2 — two stacked SVG panels** with the same x-axis and width. Don't put both lines on one axis.
- Title: `Same-day vs. late conversions`
- **Panel 1, Same day:** series colour 1. Fit the y-range to the data. Add the 2.5 baseline as a dotted line (`stroke="#5c5c66" stroke-dasharray="4 4"`), labelled with its value.
- **Panel 2, Arrived 14 days or later:** series colour 2. This is the 14-21 row plus every row below it. Fit the y-range to the data.
- Note: `Neither panel starts at zero.`
**Tables.** The pivot, buckets × weeks, 1 decimal. Add 3 rows at the bottom: `Conv. value (absolute)` (money), `Conversions` and `Same-day baseline (period)`.
 
**Analysis.** Every number must come from the pivot. Cover:
- how the lag distribution shifts from the run-up weeks to the BF week, naming the weeks and the pp move;
- which slow bucket absorbs that shift (e.g. clicks in week −4 that land in the 21-30 day bucket convert *on* Black Friday);
- the **maturation multiplier** per week, `100 / same-day %`;
- using this year's BF date, the dates when weeks −4 to 0 reach about 90% maturity, which is the earliest date to judge each week.
**Actions:**
- which pre-BF weeks will look weak and should not trigger a budget cut;
- which dates not to read;
- which final-vs-reported ratio to plan around.
## NEVER
- Never continue past a Step 1 failure.
- Never compare to benchmarks or "typical" accounts. You only have this file.
- Never recommend a bid, budget or tROAS change. Only say *when* to trust the data.
- Never write more than 5 sentences in the Analysis paragraph.