langchain-ai/rfq-quote
Process an incoming request for quote (RFQ) from a customer: read the email, look up the customer and catalogue prices, compute a quote, have it reviewed, draft the reply, and log it. Use whenever a customer asks for a price, a quote, or to license/buy a batch of tracks.
npx skills add https://github.com/langchain-ai/lca-deepagents --skill rfq-quote
Follow these steps in order. Keep a todo list so Jane can see progress.
is asking, their company/email, and exactly what they want (which
genres/tracks, how many of each).
fallback).
add_customer. The system pauses automatically for Jane to approve — the
analyst should just make the call, not ask in prose. Once approved, continue.
UnitPrice for that genre (tracks are normally $0.99; verify, don't assume).
any line discounts, and the total. Never hand-add money.
State the discount explicitly in the quote.
before drafting.
(description, qty, unit price, line total), show any discount and the grand
total, and offer next steps.
subject and the full body. The system pauses automatically for Jane to
approve or edit the wording before it's saved — don't ask for permission in a
message first. Drafts are never auto-sent.
/outputs/quotes_ledger.md recording: date, customer,items summary, total, and the draft id. Create the file with a header row if
it doesn't exist yet.
Tell Jane the draft is in her drafts folder and summarize the quote total.
Take langchain-ai/rfq-quote from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.