SSO, RBAC & audit · Any model, your keys · No seat tax
Our standard NDA positions on mutuality, confidentiality duration, governing law, non-solicit, remedies, residuals, and more, plus how to redline and flag.
kortix marketplace install kortix-starter:nda-playbook-skill# Search Gmail for NDAs under the watched label that look unprocessed.
gmail.threads.list(label={{nda_label}}, query="has:attachment")
# For each candidate thread, check for an existing draft reply on it and an
# existing file in {{nda_folder}} named after the counterparty. Either one
# means it's already been handled — skip it.
gmail.drafts.list(threadId=thread.id)
drive.files.list(folder={{nda_folder}}, query="name contains '<counterparty>'")
docs.documents.get) so you're reading the actual body — not the
Gmail preview pane or the first page.| Clause | Routine | Flag |
|---|---|---|
| Type | Mutual | One-way, when we're also disclosing our own confidential info |
| Confidentiality duration | 2–3 years post-disclosure | Perpetual, or silent on duration |
| Governing law / venue | Our home jurisdiction | Counterparty's jurisdiction or an unfamiliar third one |
| Non-solicit | None, or ≤ 12 months, employees only | > 12 months, or extends to customers/contractors |
| Remedies | Standard damages; injunctive relief available to both | One-sided injunctive relief (counterparty only) |
| Residuals clause | Present, standard carve-out for retained general knowledge | Missing, or broad enough to cover specifics, not just recollection |
| Return/destruction of info | Either party, on request or termination, ≤ 30 days | No obligation to return/destroy, or > 30 days |
| Assignment | Requires consent, except to an affiliate/successor | Freely assignable without consent |
| Indemnification | None (standard for an NDA) | Any indemnification obligation placed on us |
docs.documents.batchUpdate
with the request's writeControl/suggester identity set so the change lands as
a suggestion, not an applied edit) — never as a direct write to the document.
Keep the redline close to our standard position (e.g., propose the 2-year term,
not a negotiating opener). One redline per flagged clause; reference the
section number.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.