Matching rules, tolerances, and escalation logic for reconciling Stripe activity and the bank feed against the tracked invoices each month.
beeuni marketplace install beeuni-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.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.
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.
Route code, repository, and data/SQL work to isolated Beeuni sessions instead of burning your main context on it. Use when asked to implement a feature, fix a bug, make failing tests pass, work a ticket/issue, refactor, navigate or change a codebase, ship a PR, review a pull request, or run SQL/warehouse analysis against a dataset — and when the user wants two agents or parallel reviewers/investigators on the same work. Covers the explore-vs-session routing call, deciding where the code lives (this project's repo vs cloning an external GitHub repo) or where the data lives, finding the repo with gh, spawning sessions in parallel, dual PR reviews, and reporting results back. Triggers: 'implement', 'fix the bug', 'make the tests pass', 'work this ticket', 'refactor this', 'open a PR', 'review this PR', 'run two agents on it', 'query the warehouse', 'analyze this dataset'.
Convert Word (.doc, .docx), PowerPoint (.ppt, .pptx), Excel (.xls, .xlsx), OpenDocument (.odt, .ods, .odp), RTF, EPUB, CSV, and PDF files to GitHub-Flavored Markdown. Use when a task needs the contents of an office document, spreadsheet, presentation, ebook, or PDF you cannot read directly.
Deep research agent skill. Use when the user needs thorough, scientific, truth-seeking research on any topic -- investigating claims, finding primary sources, synthesizing evidence, producing cited reports. Triggers on: 'research this', 'investigate', 'deep dive', 'find sources', 'what does the evidence say', 'literature review', 'fact check', 'analyze the research on', any request requiring multi-source investigation with citations.
Artifact-agnostic design guidance — works for CSS, PowerPoint, matplotlib, PDF, or any visual output. Also includes a curated catalog of named font/color themes for slides, docs, and reports (non-web assets).