Menu

Individual skill

lead-to-payment

0upvotes

Use when a new lead arrives (email, Telegram message, or website form) and needs to move through the full pipeline: qualify the lead, generate an estimate, get owner approval, create a payment link, draft a customer email for owner review, and track payment. This is the master flow that orchestrates estimator-engine, crm-lite, stripe-payments, himalaya (IMAP/SMTP), and quickbooks-online. Owner stays in the loop and approves before anything is sent or charged.

skills/lead-to-payment/SKILL.md

Read pinned source

Source commit 70a22739efb5650a27fedba4082ba48b1d53e9fd

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Network or broad shell
Last checked
Nov 11, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
127
Repository last updated
Sep 11, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Lead-to-Payment — Master Sales Flow

## Overview
This is the end-to-end pipeline for a service business: a lead comes in, the agent
turns it into a priced estimate, the owner approves it over Telegram, and the agent
creates a payment link or invoice and tracks it to paid. The owner is never bypassed —
the agent **drafts and proposes, the human approves**, then the agent executes. This
mirrors how a small business owner actually wants to work: they stay in control,
the agent removes the 30–60 min of manual work per estimate.

## Environment assumptions
- Model: `zai-org/GLM-5.2` via Together AI, **direct** (no proxy).
- Gateway: Telegram, running as a systemd service. Tool calling works in the gateway.
- Secrets live in `~/.hermes/.env`.
Back to top