SSO, RBAC & audit · Any model, your keys · No seat tax
Matching rules, tolerances, and escalation logic for reconciling Stripe activity and the bank feed against the tracked invoices each month.
kortix marketplace install kortix-starter:reconciliation-match-skillplaid connector only
carries the app-level API credentials (client_id / client_secret /
environment) — it does not by itself grant access to any bank account's
transactions. Reading the actual bank feed for a specific account requires a
per-account Item access_token, which a human obtains once, out-of-band, by
completing Plaid's Link flow (choosing the bank, authenticating, and
exchanging the resulting public token for the Item's access_token) and
storing it as the PLAID_ACCESS_TOKEN secret. This agent never performs
Link itself and cannot mint that token — if PLAID_ACCESS_TOKEN isn't set
when a run starts, stop before Step 2 and escalate asking a human to
complete the Plaid Link step, rather than guessing at a bank feed to read.{{reconciliation_sheet}} and read the last dated reconciliation
entry to find the period's start (the day after the last close).{{cadence}} fired, or the explicit period the human gives you).PLAID_ACCESS_TOKEN (provisioned in Step 0): deposits and
withdrawals, with amount, date, and any reference/memo the bank provides.{{reconciliation_sheet}}: the period covered,
counts (clean matches / tolerance matches / escalated), and a row per
escalated mismatch with both records (Stripe reference + bank reference or
"none found") attached so the person reviewing doesn't have to re-pull them.The role-to-grant policy, extra-scrutiny cases, the approval handshake, and how an applied grant gets logged.
Get a complete picture of any company or person before outreach. This skill always works with web search, and gets significantly better with enrichment and CRM data.
Daily runbook for budget pacing, CPA/ROAS drift, underperformer detection, and anomaly flags across Google Ads and Meta Ads, plus how to rank and word optimization recommendations.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
Extract-and-match runbook for incoming vendor invoices: line-item extraction, PO/prior-invoice matching, duplicate + overcharge detection, and the ledger + approval hand-off.
Search, dedupe against the seen-mentions ledger, classify sentiment and notability, and post a digest with suggested response drafts — the daily brand-monitor runbook.