payment-operations
Skill2 starsChanged 7 months agoApache-2.0View on GitHub
Broad post-payment operations workflow for the Newline MCP server. Use when you need to investigate transfer failures, inspect transaction lifecycles, review returns, reconcile related records, or explain what happened after a payment was initiated. Prefer this skill for operational support across Claude Code, Codex, Pi, and other Agent Skills compatible harnesses.
In this repository9 other files it gives its agents.
- account-reconciliationSkill
- create-transferSkill
- customer-overviewSkill
- investigate-transferSkill
- making-paymentsSkill
- managing-users-and-accountsSkill
- new-account-setupSkill
- return-resolutionSkill
- transaction-reportingSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. About 0 are common, 12 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈12
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 9
Use this when the user is asking what happened after a payment was created.
- Distinctive: line 13
Do not assume a newly created transfer should already be settled.
- Distinctive: line 15
Use returns and transaction events to explain failures before suggesting retries.
- Distinctive: line 16
If remediation would require creating another transfer, get user confirmation first.
- Distinctive: line 40
Use list endpoints to find the right record:
- Distinctive: line 61
If there is no transfer, continue from the transaction or return path instead.
- Distinctive: line 81
If you need broader context:
- Distinctive: line 99
If needed, inspect a specific event:
- Distinctive: line 111
Look for returns tied to the original transaction.
- Distinctive: line 130
Use this to determine whether the transfer is part of a wider batch and whether other sibling transfers share the same issue.
- Distinctive: line 135
If the user asks whether funds moved or balances changed:
- Very specific: line 143
Use transaction_uid and balance_after to connect the payment to account-level impact.
- Distinctive: line 156
wait and re-check later if still pending
≈ “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.
Files
Payment Operations
A general operations skill for transfer follow-up, exceptions, and issue resolution. Use this when the user is asking what happened after a payment was created.
Guardrails
- Do not assume a newly created transfer should already be settled.
- Investigate by UID whenever possible: transfer UID, transaction UID, return UID.
- Use returns and transaction events to explain failures before suggesting retries.
- If remediation would require creating another transfer, get user confirmation first.
Step 1 — Start from the Best Identifier Available
If you have a transfer UID
get-newline-transfer uid=<transfer_uid>If you have a transaction UID
get-transaction uid=<transaction_uid>If you have a return UID
get-return uid=<return_uid>If you only have rough context
Use list endpoints to find the right record:
list-newline-transfers
list-transactions
list-returns
list-combined-transfersStep 2 — Inspect the Transfer Record
From the transfer, capture:
uid,status,created_atsource_synthetic_account_uiddestination_synthetic_account_uidinitiating_customer_uiddestination_customer_uidusd_transfer_amounttransaction_uids- which rail block is populated:
wire,ach, orinstant_payment
If there is no transfer, continue from the transaction or return path instead.
Step 3 — Inspect Related Transactions
For each related UID:
get-transaction uid=<transaction_uid>Record:
statustransaction_typeamount,currencysynthetic_account_uidcustodial_account_uidtransfer_uidbalance_after- timestamps and description
If you need broader context:
list-transactions transfer_uid=[<transfer_uid>]Step 4 — Inspect Transaction Events
list-transaction-eventsFilter for events tied to the transaction UID(s). Focus on:
- settlement progress
- failure states
- return-related events
- timing gaps between queued, pending, and settled states
If needed, inspect a specific event:
get-transaction-event uid=<transaction_event_uid>Step 5 — Check for Returns
list-returnsLook for returns tied to the original transaction. If one exists, capture:
uidoriginal_transaction_uidreturn_reasonamount,currencystatusprocessed_at
Then branch into the more focused return-resolution skill if the user needs next steps.
Step 6 — Check Grouped or Batch Context
Some issues are easier to understand via grouped transfers:
list-combined-transfers
get-combined-transfer uid=<combined_transfer_uid>Use this to determine whether the transfer is part of a wider batch and whether other sibling transfers share the same issue.
Step 7 — Check Balance Impact When Needed
If the user asks whether funds moved or balances changed:
get-synthetic-account uid=<synthetic_account_uid>
list-synthetic-line-items
list-custodial-line-itemsUse transaction_uid and balance_after to connect the payment to account-level impact.
Step 8 — Summarise Clearly
Explain:
- what record you started from
- current transfer and transaction status
- whether the payment is still processing, settled, failed, or returned
- what events support that conclusion
- whether balances or line items show the funds movement
- the safest next action
Typical next actions:
- wait and re-check later if still pending
- correct destination details before retrying
- review return reason and update account info
- escalate when the API shows inconsistent states
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
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.

