Ad-hoc CSV work means remembering VLOOKUP, pivot syntax, and which column had the stray nulls. This bot does it from a sentence.
sonnet4 daysPythonpandasOpenAIGoogle Sheets
Claude
64ROI
65Scale
$1.1k87Saved
ROI for
README.md
Why this subagent
Ad-hoc CSV work means remembering VLOOKUP, pivot syntax, and which column had the stray nulls. This bot does it from a sentence.
It profiles the file, translates your request into pandas steps, and shows a preview before it writes anything back. Cleaning, joining, and pivoting all happen the same way, and it keeps the steps it ran so you can repeat the same fix on next month's export.
How it runs
Used at step 01 to kick off the pipeline.
Write
Used at step 01 to kick off the pipeline.
WebFetch
Used at step 01 to kick off the pipeline.
WebSearch
Used at step 01 to kick off the pipeline.
Turn the plain-English request into pandas steps for cleaning, joining, or pivoting the data.
pending
Run the transformation and show a preview of the result before writing anything back.
pending
Export the cleaned table to a new sheet and keep the steps it ran for reuse.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Turn a plain-English request into pandas operations on the uploaded CSV and return a previewed, cleaned table.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.