Back to Details

ib-check-deck

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

IB Deck Checker

IB演示文稿检查工具

Perform comprehensive QC on the presentation across four dimensions. Read every slide, then report findings.
对演示文稿进行四个维度的全面质量控制（QC）。通读每一页幻灯片，然后报告检查结果。

Environment check

环境检查

This skill works in both the PowerPoint add-in and chat. Identify which you're in before starting:
  • Add-in — read from the live open deck.
  • Chat — read from the uploaded 
    .pptx
    file.
This is read-and-report only — no edits — so the workflow is identical in both.
本技能可在PowerPoint add-in和聊天界面中使用。开始前请先确认当前环境：
  • Add-in — 读取当前打开的演示文稿。
  • Chat — 读取上传的 
    .pptx
    文件。
本工具仅支持读取和报告，不进行编辑，因此在两种环境中的工作流程完全一致。

Workflow

工作流程

Read the deck

读取演示文稿

Pull text from every slide, keeping track of which slide each line came from. You'll need slide-level attribution for every finding ("$500M appears on slides 3 and 8, but slide 15 shows $485M"). A deck with 30 slides is too much to hold in working memory reliably — write the extracted text to a file so the number-checking script can process it.
The script expects markdown-ish input with slide markers. Format as:
undefined
提取每一页幻灯片的文本内容，并记录每一行内容所属的幻灯片。所有检查结果都需要标注对应的幻灯片位置（例如：“$500M同时出现在第3页和第8页，但第15页显示为$485M”）。30页的演示文稿内容过多，无法可靠地保存在工作内存中——请将提取的文本写入文件，以便数字检查脚本处理。
脚本需要带有幻灯片标记类Markdown格式的输入，格式如下：
undefined

Slide 1

Slide 1

[slide 1 text content]
[slide 1 text content]

Slide 2

Slide 2

[slide 2 text content]
undefined
[slide 2 text content]
undefined

1. Number consistency

1. 数字一致性

Run the extraction script on what you collected:
bash
python scripts/extract_numbers.py /tmp/deck_content.md --check
It normalizes units ($500M vs $500MM vs $500,000,000 → same number), categorizes values (revenue, EBITDA, multiples, margins), and flags when the same metric category shows conflicting values on different slides. This is the part most likely to catch something a human missed on the fifth read-through.
Beyond what the script flags, verify:
  • Calculations are correct (totals sum, percentages add up, growth rates match the endpoints)
  • Unit style is consistent — the deck should pick one of $M or $MM and stick with it
  • Time periods are aligned — FY vs LTM vs quarterly, explicitly labeled
对收集到的内容运行提取脚本：
bash
python scripts/extract_numbers.py /tmp/deck_content.md --check
该脚本会统一单位（如$500M、$500MM与$500,000,000会被识别为同一数字），对数值进行分类（revenue、EBITDA、multiples、margins），并标记同一指标类别在不同幻灯片上出现的矛盾数值。这部分最有可能发现人工反复阅读后仍遗漏的问题。
除了脚本标记的内容外，还需手动验证：
  • 计算是否正确（总计求和、百分比累加、增长率与端点数据匹配）
  • 单位风格是否一致——演示文稿应统一使用$M或$MM中的一种
  • 时间周期是否对齐——FY vs LTM vs quarterly，需明确标注

2. Data-narrative alignment

2. 数据与叙事的匹配度

Map claims to the data that's supposed to support them. This is where decks go wrong quietly — someone edits the chart on slide 7 and forgets the narrative on slide 4.
  • Trend statements ("declining margins") → does the chart actually go that direction?
  • Market position claims ("#1 player") → revenue and share data support it?
  • Plausibility — "#1 in a $100B market" with $200M revenue is 0.2% share; that's not #1
将演示中的论点与支持该论点的数据进行对应。这是演示文稿容易出现隐性问题的环节——比如有人修改了第7页的图表，却忘记更新第4页的叙事内容。
  • 趋势陈述（如“declining margins”）→ 图表是否确实呈现该趋势？
  • 市场地位主张（如“#1 player”）→ 收入和市场份额数据是否支持该主张？
  • 合理性验证——“#1 in a $100B market”却只有$200M收入，对应市场份额仅为0.2%，这显然不符合“行业第一”的定位

3. Language polish

3. 语言润色

IB decks have a register. Scan for anything that breaks it: casual phrasing ("pretty good", "a lot of"), contractions, exclamation points, vague quantifiers without numbers, inconsistent terminology for the same concept.
See 
references/ib-terminology.md
for replacement patterns.
投行演示文稿有特定的语言风格。检查是否存在不符合该风格的内容：口语化表达（如“pretty good”“a lot of”）、缩写形式、感叹号、无具体数字的模糊量化词、同一概念的术语不一致。
参考 
references/ib-terminology.md
中的替换规则。

4. Visual and formatting QC

4. 视觉与格式质量控制

Run standard visual verification checks on each slide. You're looking for: missing chart source citations, missing axis labels, typography inconsistencies, number formatting drift (1,000 vs 1K within the same deck), date format drift, footnote and disclaimer gaps.
Visual verification catches overlaps, overflow, and contrast issues that don't show up in text extraction. Don't skip it — a chart with no source citation looks the same as a properly sourced one in the text dump.
对每一页幻灯片进行标准视觉验证检查。需关注以下问题：缺少图表来源标注、缺少坐标轴标签、排版不一致、数字格式不统一（同一演示文稿中同时出现1,000和1K）、日期格式不一致、脚注与免责声明缺失。
视觉验证能发现文本提取无法检测到的内容重叠、溢出和对比度问题。请勿跳过这一步——在文本提取结果中，未标注来源的图表与标注正确的图表看起来没有区别。

Output

输出结果

Use 
references/report-format.md
as the structure. Categorize by severity:
  • Critical — number mismatches, factual errors, data contradicting narrative. These block client delivery.
  • Important — language, missing sources, terminology drift. Should fix.
  • Minor — font sizes, spacing, date formats. Polish.
Lead with criticals. If there aren't any, say so explicitly — "no number inconsistencies found" is a finding, not an absence of one.
以 
references/report-format.md
为模板生成报告。按严重程度分类：
  • Critical — 数字不匹配、事实错误、数据与叙事矛盾。这些问题会阻碍向客户交付材料。
  • Important — 语言问题、缺少来源、术语不一致。需要修正。
  • Minor — 字体大小、间距、日期格式。仅需优化。
报告优先展示严重问题。如果没有严重问题，请明确说明——“no number inconsistencies found”本身就是一个检查结果，而非无结果。