Table image to clean CSV extraction

Extracts a table from a screenshot or scanned page into a flat, copy-paste-ready CSV, unmerging cells, stripping units into their own columns and flagging anything unreadable instead of guessing.

PLPromptByte Library@promptbytePublished Sep 2

TextData & Analysis #csv #data cleaning #data extraction #tables

Version 1 of 1 · published Sep 2, 2026Version 1 · only version

Example output

See all results

Google · Gemini 3.1 Pro 3.1 (Preview)PLPromptByte Library Version 1

Prompt

Version 1 · 2 variables · 1 required

Fill in the values below — the customized prompt updates as you type. marks a required value.

What the table contains{{table_description}}

Describe the table so columns are read correctly: e.g. "monthly output and defect counts per assembly line".

Source of the table(optional){{source_reference}}

The document, report or page the table came from. Default: the attached document

Fill in What the table contains to copy the customized prompt.

Resultsfor version 1

All models Gemini 3.1 Pro1

Version 1 · only version

Gemini 3.1 Pro result by PromptByte Library
Google · Gemini 3.1 Pro 3.1 (Preview)PLPromptByte Library (@promptbyte)Version 1Published Sep 2
Compare
```csv quarter,line,units_produced,defects,defect_rate_pct,shift_pattern Q1,Line A,14200,318,2.24,"Two shifts, weekdays" Q1,Line B,11850,402,3.39,"Two shifts, weekdays" Q1,Line C,9600,151,1.57,"One shift, weekdays" Q1,Line D,UNCLEAR,88,UNCLEAR,"One shift, weekends" Q2,Line A,15040,295,1.96,"Three shifts, weekdays" Q2,Line B,12310,377,3.06,"Two shifts, weekdays" Q2,Line C,9880,143,1.45,"One shift, weekdays" Q2,Line D,4120,96,2.33,"One shift, weekends" ``` **Notes** - **UNCLEAR cells:** row 5 (Q1, Line D) — `units_produced` and `defect_rate_pct`. The scan has a fold running through that row…
Community submittedFull output
Settings: Unknown
Open result

Showing all 1 public result from Gemini 3.1 Pro on version 1.

Usage notes

Attach the table as an image or PDF page. Cropping tightly to the table and using the highest resolution you have makes a large difference to accuracy — most extraction errors are legibility errors, not reasoning errors.

For a table spanning several pages, do one page per request and concatenate afterwards. Asking for all of them at once is where rows quietly go missing.

The UNCLEAR marker is the point of this prompt. Always read the notes section and fix those cells by hand; a model that guesses a digit produces a CSV that looks perfectly clean and is wrong.

Before using the data, check the row count against the source and re-add any units you had stripped out. If the table has footnote markers attached to values, say so in table_description so they are separated rather than parsed as digits.

Attribution: adapted from https://github.com/f/prompts.chat by f (Fatih Kadir Akın), licensed CC0-1.0. Source file: https://github.com/f/prompts.chat/blob/main/PROMPTS.md

Models represented

1 public result from 1 model

code · sql
```
**Assumptions**

- `order_items.order_id` joins to `orders.id`, and `products.category_id` joins to `categories.id`. These are inferred from the naming convention, since no foreign keys were listed.
- "Last 90 days" is measured against `orders.order_date` relative to today, inclusive of today.
- Revenue is `quantity * unit_price` summed over line items; there is no discount or tax column in the schema, so none is applied.
- Cancelled orders are excluded. If `status` uses different values than `'
```
Code preview: **Assumptions** - `order_items.order_id` joins to `orders.id`, and `products.category_id` joins to `categories.id`. These are inferred from the naming convention, since no foreign keys were listed. - "Last 90 days" is measured against `orders.order_date` relative to today, inclusive of today. - Revenue is `quantity * unit_price` summed over line items; there is no discount or tax column in the schema, so none is applied. - Cancelled orders are excluded. If `status` uses different values than `'
SQL query generator from a plain-English request
Converts a natural-language data requirement plus a table schema into a syntactically correct SQL query for a named database, with its assumptions stated up front.
CodeData & Analysis OpenAI · GPT-5.5
PL@promptbyteAug 27
Score 1
0 comments1 results
No public results yet
Audit SQL joins for duplicate rows and inflated totals
Check join cardinality and aggregation grain to explain duplicate rows or double-counted measures before changing a reporting query.
TextData & Analysis
PL@promptbyteSep 8
Score 0
0 comments0 results
No public results yet
Design a forecast backtest that respects time and information
Specify temporal evaluation, leakage checks, baselines and business-relevant metrics before judging a forecasting model.
TextData & Analysis
PL@promptbyteSep 8
Score 0
0 comments0 results
No public results yet
Critique an existing chart for misleading interpretation
Review a chart's scales, labels, aggregation and claims, separating visual issues from data questions that need verification.
TextData & Analysis
PL@promptbyteSep 8
Score 0
0 comments0 results
No public results yet
Classify comment sentiment with traceable evidence
Label supplied comments consistently while preserving mixed opinions, unclear cases and the exact words supporting each label.
TextData & Analysis
PL@promptbyteSep 8
Score 0
0 comments0 results
No public results yet
Reshape a wide CSV into tidy records without losing meaning
Produce a deterministic transformation from repeated measure columns to tidy rows with explicit keys, types and missing-value rules.
CodeData & Analysis
PL@promptbyteSep 8
Score 0
0 comments0 results

Browse Data & Analysis

Table image to clean CSV extraction

Example output

Prompt

Resultsfor version 1

Something wrong with this prompt?

SQL query generator from a plain-English request

Audit SQL joins for duplicate rows and inflated totals

Design a forecast backtest that respects time and information

Critique an existing chart for misleading interpretation

Classify comment sentiment with traceable evidence

Reshape a wide CSV into tidy records without losing meaning

Discussion 0

Example output

Prompt

Resultsfor version 1

Something wrong with this prompt?

Related prompts

SQL query generator from a plain-English request

Audit SQL joins for duplicate rows and inflated totals

Design a forecast backtest that respects time and information

Critique an existing chart for misleading interpretation

Classify comment sentiment with traceable evidence

Reshape a wide CSV into tidy records without losing meaning

Discussion 0