skills/plaid-integration/SKILL.md
This skill should be used when the user asks to "integrate Plaid", "connect a bank account", "sync bank transactions", "add Plaid Link to my app", or "implement financial data access". Integrates the Plaid API for bank account connections and transaction syncing in TypeScript/Bun applications.
npx skillsauth add b-open-io/prompts plaid-integrationInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Integrate Plaid for connecting bank accounts and syncing transactions in TypeScript applications using Bun.
bun add plaid
import { Configuration, PlaidApi, PlaidEnvironments } from 'plaid';
const plaidClient = new PlaidApi(new Configuration({
basePath: PlaidEnvironments[process.env.PLAID_ENV || 'sandbox'],
baseOptions: {
headers: {
'PLAID-CLIENT-ID': process.env.PLAID_CLIENT_ID,
'PLAID-SECRET': process.env.PLAID_SECRET,
}
}
}));
Omit redirect_uri to use popup mode — required for local HTTP development:
const response = await plaidClient.linkTokenCreate({
user: { client_user_id: `user-${Date.now()}` },
client_name: 'My App',
products: ['transactions'],
country_codes: ['US'],
language: 'en',
// No redirect_uri = popup mode, works with HTTP localhost
});
const linkToken = response.data.link_token;
After the user completes Link, exchange the temporary public_token for a permanent access_token:
const response = await plaidClient.itemPublicTokenExchange({ public_token });
const { access_token, item_id } = response.data;
// Store access_token securely — never expose to clients
Plaid returns a maximum of 500 transactions per request. Always paginate:
let offset = 0;
const count = 500;
while (true) {
const response = await plaidClient.transactionsGet({
access_token,
start_date: '2023-01-01',
end_date: '2024-12-31',
options: { count, offset },
});
// Process response.data.transactions
offset += response.data.transactions.length;
if (offset >= response.data.total_transactions) break;
}
For ongoing incremental updates, prefer transactionsSync with a cursor — see references/api-reference.md.
Catch Plaid errors from error.response?.data:
try {
await plaidClient.transactionsGet({ ... });
} catch (error: any) {
const plaidError = error.response?.data;
if (!plaidError) throw error;
switch (plaidError.error_code) {
case 'ITEM_LOGIN_REQUIRED':
// Re-initialize Link in update mode
break;
case 'INVALID_ACCESS_TOKEN':
// Token revoked — delete item, prompt re-link
break;
case 'PRODUCT_NOT_READY':
// Data still processing — retry after delay
break;
default:
throw new Error(`Plaid error: ${plaidError.error_code} — ${plaidError.error_message}`);
}
}
Use Bun SQLite with items → accounts → transactions hierarchy. For the complete schema with indexes, prepared statements, and TypeScript types, see references/code-examples.md.
references/code-examples.md — Full working implementations: bank connection flow with Elysia server, transaction sync with pagination, complete Bun SQLite database module, CLI integrationreferences/api-reference.md — All API endpoints with request/response shapes, sandbox test credentials, webhook events, rate limitstools
This skill should be used when a Claude Code session needs to keep working after Anthropic usage runs out, or when the user asks to run the Claude Code harness on GPT-5.6 Sol. Trigger phrases include "my Anthropic usage ran out", "I'm out of Claude usage", "usage limit reached, what now", "keep working on another model", "run Claude Code on GPT-5.6 Sol", "use GPT-5.6 Sol as the model", "set up claudex", "claudex isn't working", "route the harness through CLIProxyAPI", or "bill against my ChatGPT/Codex subscription". It stands up a local proxy so the Claude Code CLI runs on OpenAI's Codex backend as an escape hatch, and diagnoses that setup when it drifts. macOS + Homebrew.
testing
This skill should be used when the user asks to "open Visual Wayfinder", "answer a Wayfinder ticket visually", "turn this decision into a configurator", "show Wayfinder choices as a dashboard", "prototype the Wayfinder questionnaire", or wants interactive choice cards, tradeoff controls, rankings, ranges, toggles, and consequence previews for one active Wayfinder decision. It wraps the Wayfinder skill and JSON Render; it never replaces the tracker or resolves more than the active decision.
development
This skill should be used when the user asks to "make a visual proposal", "write this up so I can share it", "present these options visually", "diagram the trade-offs", "turn this plan into something reviewable", or requests a shareable design pitch, architecture proposal, RFC, options comparison, or visual roadmap for work that has not been built. It produces one self-contained, theme-aware HTML page led by grounded diagrams. Use visual-review instead for completed code changes; do not use this skill for internal task tracking.
tools
This skill should be used when the user asks to "add plugin settings", "make a plugin configurable", "store per-project plugin configuration", "use settings.local.json", "create a plugin state file", "expose skill settings in Agent Master", or "add a skill interface". Distinguishes official Claude Code settings from project-owned configuration and documents bOpen Agent Master skill interface discovery.