agentleFS
newline53newline53/newline-mcp-server/skills/customer-overview/SKILL.md

customer-overview

Skill2 starsChanged 7 months agoApache-2.0View on GitHub

Builds a complete snapshot of a Newline customer, including their profile, KYC status, synthetic accounts and balances, recent transactions, and recent activity. Use when asked to look up, summarise, or report on a customer.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If you have the customer UID:

    line 12
  2. Distinctive:

    If you need to search:

    line 18
  3. Distinctive:

    Look for products associated with this customer to understand their enrolled services and product eligibility.

    line 80

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Customer Overview

Assembles a full picture of a customer from multiple Newline API resources.

Step 1 — Find and Retrieve the Customer

If you have the customer UID:

get-customer  uid=<customer_uid>

If you need to search:

list-customers  (filter by first_name, last_name, email, or external_uid)

Record from the customer response:

  • uid, external_uid
  • details — name, phone, business name
  • email
  • status — active, locked, archived
  • kyc_status and kyc_status_reasons
  • lock_reason / locked_at — if applicable
  • total_balance
  • pool_uids — pools the customer belongs to
  • customer_type — individual vs. business

Step 2 — Retrieve Synthetic Accounts

get-synthetic-accounts

Filter visually or by pool_uid to find accounts belonging to this customer's pools.

For each account note:

  • name, uid, status
  • synthetic_account_category
  • net_usd_balance, net_usd_pending_balance, net_usd_available_balance
  • routing_number, account_number_last_four
  • Payment rail details (ach, wire, or instant_payment block)

Step 3 — Retrieve Recent Transactions

list-transactions  customer_uid=[<customer_uid>]  sort=created_at_desc  limit=10

For each transaction note:

  • transaction_type, status, amount, currency
  • description
  • transfer_uid — link to originating transfer if applicable
  • created_at

Step 4 — Retrieve Recent Customer Activities

list-customer-activities

Filter for entries where customer_uid matches. These capture login events, KYC updates, setting changes, and other audit trail entries.

Note any recent activity_type values that suggest issues (failed logins, KYC status changes, locked events).

Step 5 — Retrieve Customer Products (Optional)

list-customer-products

Look for products associated with this customer to understand their enrolled services and product eligibility.

Step 6 — Summarise

Present a structured summary covering:

  1. Identity — name, email, type, status, KYC status
  2. Balances — total balance and per-account breakdown
  3. Accounts — list of synthetic accounts with status and category
  4. Recent Transactions — last 10 with amounts and status
  5. Recent Activity — notable activity log entries
  6. Flags — any locked status, KYC failures, or pending issues

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.