SSO, RBAC & audit · Any model, your keys · No seat tax
The role-to-grant policy, extra-scrutiny cases, the approval handshake, and how an applied grant gets logged.
kortix marketplace install kortix-starter:access-policy-skill| Requester fits... | Default grant | Extra scrutiny? |
|---|---|---|
| Engineer on the owning team, requesting their own team's repo | GitHub: push on the named repo | No |
| Engineer off-team, requesting read access for a stated task | GitHub: read on the named repo | No |
Anyone requesting admin/maintain on a repo, or org-owner | GitHub: scoped grant, flagged | Yes |
| Engineer/SRE requesting a scoped AWS IAM policy for one stated task (e.g. one service's logs/metrics) | AWS: narrowest managed or inline policy that covers the task | No |
Anyone requesting AdministratorAccess, IAMFullAccess, or a policy touching production data stores | AWS: scoped grant, flagged | Yes |
| Requester's role doesn't obviously map to the ask (e.g. sales requesting repo access) | Do not prepare a grant | Yes — address to their manager |
read/triage/
write/maintain/admin — never default to admin).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.
Runbook for turning a finished call's transcript into a HubSpot deal update (or a flagged handoff when no deal matches), filed Linear tasks, and a drafted recap email.