SSO, RBAC & audit · Any model, your keys · No seat tax
Per-platform scope, read/write boundaries, and the human-approval gate for the Slack control-pane agent.
kortix marketplace install kortix-starter:control-pane-ops-skill| Platform | Access | Typical read | Typical write |
|---|---|---|---|
| Database | Read-only via scoped DATABASE_URL | Account/plan lookups, counts, joins | Not possible with this credential — the role cannot run UPDATE/DELETE/ALTER or any schema-changing statement. Surface the exact change needed and hand it to a human to run directly, or route it through an approval-gated connector/tool that supports it |
| Stripe | Composio connector (brokered) | Plan, invoices, subscription status | Refund, plan change, cancellation — approval gate |
| Linear | Composio connector (brokered) | Search issues/projects | Invite a member, create a project or issue — safe to do directly |
| GitHub | gh CLI + GH_TOKEN against {{target_repo}} | View/diff a PR, read issues and checks | Review, comment, and open a PR freely — never merge |
| Sandbox | Built-in to the session | — | Spin up an ad hoc sandbox to reproduce a bug or run a one-off script — always disposable, always safe |
DATABASE_URL is a read-only role — it cannot execute a write no matter
what a human approves. If the task needs a database change, state the exact
statement in the thread and hand it to a human to run directly; do not
attempt it yourself and do not promise to apply it later.gh pr view, gh pr diff, gh pr checks, gh issue view to
review. When a fix is warranted: branch, commit, and
gh pr create --repo {{target_repo}}. Opening a PR is fine — merging is not.DATABASE_URL is a
read-only role, so there is nothing to execute even after approval — hand the
statement to a human instead (see Step 3).{{cadence}})gh auth status against {{target_repo}}, a trivial SELECT 1 against
the database) to confirm the scoped credential still authenticates. Post a
health-check alert to {{ops_channel}} naming anything that failed, so a human
can reconnect it before the next task arrives. Do nothing else on this run.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.