check-link-wallet
Skill896 starsChanged 30 days agoMITView on GitHub
Reads the connected Link account, the cards and bank accounts saved in its wallet, its saved shipping addresses, and the status of existing spend requests. Use when the user asks which Link account is connected, what payment methods or addresses Link has saved, or whether a Link purchase has been approved yet.
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- packages/agent-identity/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- create-payment-credentialSkill
- financial-insightsSkill
- complete-link-purchaseSkill
- create-payment-credentialSkill
- financial-insightsSkill
- use-link-identitySkill
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
- Distinctive: line 8
Read-only inspection of the connected Link account through the Link MCP server.
- Distinctive: line 23
Call only the tool that answers the question.
- Distinctive: line 53
Never surface tokens, credentials, or internal identifiers as an aside.
≈ “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
Check a Link wallet
Read-only inspection of the connected Link account through the Link MCP server. Nothing here moves money or changes a spend request.
To actually buy something, use the complete-link-purchase skill instead.
Tools
| Question | Tool |
| Which account is connected? | get_userinfo |
| What cards and bank accounts are saved? | list_payment_methods |
| What shipping addresses are saved? | list_shipping_addresses |
| What purchases are pending or approved? | list_spend_requests |
| What is the status of one purchase? | get_spend_request |
Call only the tool that answers the question. Do not sweep all five to build a picture the user did not ask for.
Spend request status
list_spend_requests returns only active requests by default — those in
created, pending_approval, or approved. Pass includeHistory when the
user is asking about something that already finished or expired.
The statuses mean:
created— exists, but the user has not been asked to approve it yet.pending_approval— waiting on the user. They approve in the Link app.approved— ready to spend against.- Expired and terminal states are only visible with
includeHistory, and cannot be spent against. A user who still wants the purchase needs a fresh one, raised withrequest_virtual_card— but only if they ask for it. Do not offer to re-run a purchase off the back of a status question.
get_spend_request returns the status of a single request by id. Do not pass
the include parameter here. include: ["card"] and
include: ["shared_payment_token"] return live payment credentials, and they
belong only in the moment of paying, which is the other skill's job.
What to expose
- Summarize. Do not dump raw JSON or object ids unless the user asks.
- Payment methods: brand, type, and last four only. Never a full number.
- Shipping addresses: city and postcode by default. Give the full address only if the user asks for it.
- Never surface tokens, credentials, or internal identifiers as an aside.
When the account is not connected
An authorization error from any of these tools means the user has not connected Link in Cursor, or the connection has lapsed. Say so plainly and let them reconnect. Do not retry in a loop, and do not try another tool hoping for a different answer.
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.