Refund

Organization

runxhq

refund

Refund one original Stripe, PayPal or x402 merchant payment with exact native approval and independently checked settlement.

Overview

Publisher	runxhq
Repository	`runx`
Skill name	`refund`
Stars	105
Forks	109
Bundled files	2
License	Apache-2.0
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
2 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by runxhq on GitHub. Read the source before you install it.

Installation

Install the Refund AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/runxhq/runx/tree/main/skills/refund
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/runxhq/runx.git /tmp/runx
mkdir -p .claude/skills
cp -r /tmp/runx/skills/refund .claude/skills/refund

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Refund in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Refund on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Refund is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Refund

Use this when you are the merchant reversing all or part of a confirmed payment. Choose its original connector and account: Stripe, PayPal or Coinbase CDP for x402. A buyer paying a merchant uses pay; collecting a payment belongs to charge. A refund never changes processor to work around a failed readback.

Inspect runx connector inspect <connector> and use the refund operation's input_schema to construct request. Supply original account/payment identity, exact amount and currency, and a stable caller-owned idempotency_seed. PayPal also requires an explicit API host, canonical decimal precision and the original refundable capture status. Its sandbox host requires a matching sandbox app. Never put provider keys, wallet keys, card data or tokens in these inputs.

Confirm the original relationship

Native admission derives the outgoing amount from the exact provider request before budgeting and approval. There is no rounding or FX conversion. A USD limit refuses a currency it cannot count. The provider reads the original payment on its account and atomically enforces the remaining refundable amount, including prior or concurrent refunds. Local and hosted credential custody use the same declared connector contract.

Stripe independently confirms the refund against the original PaymentIntent and currency. PayPal independently confirms the original capture and exact refund amount, currency and complete capture relationship. Coinbase CDP retains its original settlement evidence and separate refund readback. Only confirmed succeeded, COMPLETED or x402 settled evidence completes the respective lane. The result is that provider's bounded native packet, not a fabricated universal payment record.

Unknown and pending outcomes

A provider acknowledgement or HTTP success is not a completed refund. Stop on unknown payment, wrong account/currency, excess remaining amount, denied approval, pending/refused refund or unavailable readback. Preserve the original provider reference, request key and native receipt. Resume the original effect at readback; do not submit a second refund under another key. An unknown write without an acknowledgement needs reconciliation, not a new financial action.

A composed caller supplies the same original collection evidence and key. This skill does not collect again, replace the original payment, send a customer message or update a ledger on the caller's behalf.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

references/catalog.md1 KB
run.yaml5 KB

Frequently asked questions

What does the Refund AI skill do?

Refund one original Stripe, PayPal or x402 merchant payment with exact native approval and independently checked settlement.

Why use Refund on TypingMind?

Because you install it once and use it with any model. Refund is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Refund in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/runxhq/runx/tree/main/skills/refund. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Refund?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Refund?

As many as you like. As long as a model supports skills, you can use Refund with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Refund AI skill free?

Yes. It is published on GitHub by runxhq under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Module Regression

affaan-m

CommunityPopular

Govern cross-module regression in large repositories with a REGRESSION.md ledger that records each module's downstream consumers and executable acceptance command. After a change, run the changed…

Benchmark Methodology

affaan-m

CommunityPopular

Use after competitive-platform-analysis has produced a tiered competitor set. Scores each competitor across nine weighted dimensions (positioning, voice, visual craft, offer packaging, evidence,…

Investor Materials

Create and update pitch decks, one-pagers, investor memos, accelerator applications, financial models, and fundraising materials. Use when the user needs investor-facing documents, projections,…

Evm

Read-only EVM client: wallets, tokens, gas across 8 chains.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Refund

Confirm the original relationship

Unknown and pending outcomes

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now