enrich-excel

Enrich Excel with TinyFish

Research missing data with TinyFish and write it directly into a live Excel workbook on macOS — cell by cell, in real time, via AppleScript. No file saves or reloads needed.

Pre-flight Check (REQUIRED)

Run ALL three checks before doing anything else:

# 1. TinyFish CLI installed?
which tinyfish && tinyfish --version || echo "TINYFISH_CLI_NOT_INSTALLED"

# 2. Authenticated?
tinyfish auth status

# 3. Excel running with a workbook?
osascript -e 'tell application "Microsoft Excel" to get name of active workbook'

If any check fails, stop and tell the user what to fix. Do NOT proceed.

---

Step 1 — Read the active workbook

Write a temporary AppleScript file and execute it. Do NOT use inline heredoc with osascript — it breaks in many shell environments. Always write to a temp file first.

cat > /tmp/tf_read_excel.scpt << 'APPLESCRIPT'
tell application "Microsoft Excel"
    set ws to active sheet of active workbook
    set output to ""
    repeat with r from 1 to 50
        set rv to ""
        set hasValue to false
        repeat with c from 1 to 15
            set cv to (value of cell r of column c of ws) as text
            if cv is not "missing value" and cv is not "" then
                set hasValue to true
                set rv to rv & c & ":" & cv & "|"
            else
                set rv to rv & c & ":|"
            end if
        end repeat
        if hasValue then set output to output & r & ">" & rv & linefeed
    end repeat
    return output
end tell
APPLESCRIPT
osascript /tmp/tf_read_excel.scpt

Parse the output format: row_number>col_num:value|col_num:value|...

If the sheet has more than 50 rows or 15 columns, increase the limits and re-run.

---

Step 2 — Identify what needs enrichment

From the parsed output:

1. Find the header row — the first row where multiple cells have non-empty values. These are your column labels.
2. Map columns — associate each column number with its header text (e.g., column 2 = "Company", column 3 = "Revenue").
3. Find data rows — rows after the header with at least one non-empty cell.
4. Find empty cells — in each data row, identify which columns are blank. These are what we need to fill.
5. Respect user instructions — if the user specified which columns to fill or what to research, narrow the scope accordingly.