SSO, RBAC & audit · Any model, your keys · No seat tax
The outbound runbook: account research, the angle/proof-point playbook, sequence drafting, HubSpot logging, the daily cap, and the approval gate.
kortix marketplace install kortix-starter:personalized-outreach-skillkortix_outreach_drafted property + timestamp marks a contact handled), not
in a local ledger file. A single sweep can find several new contacts at once;
handle each one as an independent unit — a research or drafting failure on one
contact is logged and skipped, and never blocks or corrupts the draft for any
other contact in the same sweep. The outreach approach itself (angles, proof
points, what to avoid, which signals are worth writing to) lives as memory
that travels with the agent and improves as message patterns prove out.
GET /crm/v3/lists/object-type-id/0-1/name/{{hubspot_list}}
list.listId from the response, then page through membership
records (100 at a time, following after until the response has no more
pages):GET /crm/v3/lists/{listId}/memberships?limit=100&after={after}
recordIds this returns, then batch-read those contacts and drop
anything already carrying kortix_outreach_drafted:POST /crm/v3/objects/contacts/batch/read
properties: [... the properties Steps 1-4 need ...]
inputs: [{ id: recordId }, ...] // the memberships page(s) above
kortix_outreach_drafted was handled by a prior
run — skip it, even if it hasn't been sent yet. Sending is a human decision,
not a signal to re-draft. Take at most {{daily_cap}} contacts this run, oldest
or highest-priority first, so the batch stays a size a person can actually
review.kortix_outreach_drafted = true (with a timestamp) on each contact you
drafted this run so the next sweep skips 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.