agentleFS
Sign inStart free
NVIDIAKnown publisherNVIDIA/nemoclaw-community/examples/recipes/nvidia/payment-ops-hermes/skills/payment-ops-playbook/SKILL.md

payment-ops-playbook

Skill142 starsChanged 3 months agoApache-2.0View on GitHub

The standard FinGuard payment-operations workflow — screen, explain, prepare, hand off to a human. Never release.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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:

    Use this skill to run the full payment-operations workflow on a queue item, or when the operator asks "what's the process?" / "handle this …

    line 8
  2. Distinctive:

    Do not collapse maker and checker.

    line 34
  3. Distinctive:

    Do not claim durable memory of approvals.

    line 35
  4. Distinctive:

    Do not escalate your own permissions or imply you can.

    line 37

≈ “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

payment-ops-playbook

Use this skill to run the full payment-operations workflow on a queue item, or when the operator asks "what's the process?" / "handle this payment."

This is the orchestration playbook. It composes payment-screening and release-packet. It never releases funds.

The workflow

  1. Screen the payment (payment-screening). Report decision + per-check breakdown.
  2. If HOLD — stop. Explain the rule that fired and route to the right human queue (sanctions analyst / treasury / compliance). Do not override.
  3. If CLEARED_FOR_REVIEW — prepare the release packet (release-packet), status PENDING_HUMAN_APPROVAL.
  4. Hand off to a named human approver. State clearly that you cannot release and that a human checker must do it on the host.
  5. Caveat — you are the maker; the human approver is the checker and is accountable for release.

The boundary (say this when relevant)

"FinGuard prepares and screens payments. It cannot move money — the sandbox blocks the payment rail. Release is always a human action."

Pitfalls

  • Do not collapse maker and checker. Preparing a packet is not releasing.
  • Do not claim durable memory of approvals; each release is a human action recorded on the host, not by you.
  • Do not escalate your own permissions or imply you can.

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.

Check your setup, free