The result to aim for
Matéo Garcia gave Claude three cash skills linked to Pennylane. On the BFR, Claude distinguishes between failure and delay, identifies customers who focus on risk, based on lettering. On charges, it covers several hundred transactions: subscriptions, levies, potential duplications.
What was done
Post LinkedIn public signed (Matéo Garcia, September 1, 2026, page read November 10, 2026). MCP Pennylane: Claude will look for data to reconstruct the analysis ("What blocks my cash?"). It also reports incomplete data — out of title. Distinct from Cléton (invoice writing) and Cormier (invoices and payments). Hundreds of transactions and lettering are his observation, unaudited.
Before you start
Tool cited by the source: Claude (Skills, MCP Pennylane); other tools cited: Claude. Gather the information the prompt asks for. Strip confidential data that is not needed and check your tool’s access terms. Features and plans can change.
The method, in three steps.
Gather the context
Gather the information described in the prompt.
Adapt the prompt
Copy the prompt below, replace the bracketed items, then paste it into Claude.
Reread before using
Reread the result, correct it if needed and keep the final decision. Caveats are detailed below.
Your starting point.
Replace the bracketed items, then adapt the proposal to your situation. This prompt is written by the iadujour desk It is not a quotation from the source.
Extracts (unnamed): What's blocking cash? Which customers weigh on the BFR? What recurrent charges? If any data is missing, say so. No amount.
What deserves your attention
Proof level: Public declarative post. Source checked on 10 November 2026. Use described by the source, not tested by the desk. Original summary written by iadujour.fr: figures and claims are the source’s; the prompt is a desk proposal, not a quotation.
Comments.
A field note, a question, a precision on this use case? Comments are reviewed before publication.
Published comments
Loading comments…
Leave a comment
Moderation charter. Every comment is reviewed before publication. We refuse hate speech, insulting or discriminatory language, advertising, spam and promotional links, off-topic posts and other people’s personal data.