Run3 Multi Condition Lookup with INDEX MATCH for Financial Data
Use INDEX-MATCH with two conditions (series code and year) to retrieve values from a source data table. Apply this when you need to pull specific data points based on multiple criteria from an unstructured data range.From its SKILL.md
npx -y skills add cxcscmu/SkillLearnBench --skill run3_Multi-Condition-Lookup-with-INDEX-MATCH-for-Financial-DataAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
1.7 KB, 392 tokens by cl100k_base, as published. Nobody here has run it
When to Use
- You have data organized by multiple dimensions (e.g., country/series code and year)
- You need to match on two or more criteria simultaneously
- VLOOKUP or HLOOKUP alone cannot handle your lookup structure
Formula Structure
Use nested INDEX-MATCH to handle two conditions:
=INDEX(data_array, MATCH(criteria1, lookup_array1, 0), MATCH(criteria2, lookup_array2, 0))
Step-by-Step Approach
- Identify your criteria: Series code (column D in Task sheet) and Year (row 10 in Task sheet)
- Locate source data: Data sheet, rows 21–40
- Set up the formula:
data_array: The values you want to retrieve (e.g., columns with actual data in Data sheet)lookup_array1: Series code column in Data sheet (find match for column D)lookup_array2: Year row in Task sheet (find match for row 10)
- Apply absolute references where needed so the formula can be copied across multiple cells
Example
=INDEX(Data.$A$21:$Z$40, MATCH($D12, Data.$A$21:$A$40, 0), MATCH(H$10, Data.$A$20:$Z$20, 0))
Key Points
- Use
MATCH(..., 0)for exact matches - Lock criteria references with
$appropriately (e.g.,$D12to keep column D fixed,H$10to keep row 10 fixed) - Ensure the lookup arrays span the correct range in the source sheet
- Test with one cell, then copy to all yellow ranges (H12:L17, H19:L24, H26:L31)
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most finance skills give in 392 tokens
Counted across 469 of the 469 authors here whose files we hold, read 2026-08-07
- Extract date vendor amount and descriptionin 15 of 469, across 3 files
- Scan folder for invoice filesin 14 of 469, across 2 files
- Rename files to standard formatin 14 of 469, across 2 files
- Show organization plan before movingin 14 of 469, across 2 files
- Generate summary CSVin 14 of 469, across 2 files
- Organize files by categoryin 13 of 469, across 1 file
- Preserve original filesin 13 of 469, across 1 file
- Flag files missing critical infoin 13 of 469, across 1 file
- Produce the requested output filein 9 of 469, across 4 files
- Build best, base, and worst case scenariosin 9 of 469, across 5 files
- Implement backoff if rate limit errors occurin 8 of 469, across 3 files
- Determine the weighted average cost of capitalin 8 of 469, across 4 files
Said here and by no other author read
- Use nested INDEX-MATCH to handle multiple lookup conditions
- Use exact match type zero in MATCH formulas
- Lock criteria references using absolute dollar notation
- Ensure lookup arrays span the correct range
- Test the formula with one cell first
- Copy the tested formula to all required ranges
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.