Kortix Starter

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.

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.

The release-notes runbook: finding the release range, filtering noise, grouping by area, writing the entry, and opening the PR.

Scoring rules for usage decline, support friction, billing/payment risk, and renewal proximity, plus how to write the ranked at-risk list.

Monthly reconciliation tolerances, missing-document checks, and anomaly rules for working the close checklist and ledger in Google Sheets.

Route code, repository, and data/SQL work to isolated Kortix 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'.

Fetch, normalize, diff against the last snapshot, filter cosmetic noise, and post a short summary — the daily competitor-watch runbook.

The daily compliance-drift runbook: reading the policy, checking bucket/tag/role state, cross-referencing the audit logs, and drafting proposed remediation.

Finds pages losing search traffic, rotates coverage via a ledger, and refreshes copy, stats, and internal links on an isolated branch.

Our standard positions on liability, indemnification, termination, and the rest, plus how to summarize, flag, and draft a redline.

Per-platform scope, read/write boundaries, and the human-approval gate for the Slack control-pane agent.

Baseline-building and anomaly-attribution rules for daily AWS Cost Explorer spend, plus the alert format and ledger.

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.

The weekly dependency-upgrade runbook: upgrade tiers, the verification gate, breaking-change handling, the ledger, and guardrails.

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).

Maps landed code changes to affected docs pages and rewrites them to match, tracked via a commit-checkpoint ledger.

Use for structured review, fact-checking, annotation, and correction of documents such as PDF, DOCX, PPTX, and XLSX files.

Use for creating, editing, extracting, converting, and reviewing Word documents.

Free domain research and availability checking. No API keys or credentials required. Uses RDAP (1195+ TLDs) with whois CLI fallback for universal coverage. Checks if domains are available, searches keywords across TLDs, performs WHOIS/RDAP lookups, checks expiry dates, and finds nameservers. Use when the agent needs to: check if a domain is available, search for domains, find who owns a domain, check domain expiration, get nameservers, bulk check domains, or do any domain research. Triggers on: 'check domain', 'is domain available', 'search domains', 'domain availability', 'who owns this domain', 'whois', 'domain expiry', 'when does domain expire', 'nameservers for', 'domain research', 'find domains for', 'domain ideas', 'bulk domain check'.

Research first, then draft. This skill never sends generic outreach - it always researches the prospect first to personalize the message. Works standalone with web search, super...

Verification rules, the subject-data table map, the report format, and the SLA clock for turning a GDPR request into a compiled report ready for legal review.

The four-rung dunning ladder, minimum wait times between rungs, and the ledger format that carries each subscription's recovery state across hourly runs.

The shared-inbox runbook: categorize, look up the help doc, draft or file a ticket, and when to leave a thread label-only.

Groups new and spiking Sentry errors, dedupes against existing GitHub issues, and drafts an issue with the stack trace and impact for the top offenders.

The 15-minute runbook for detecting SLA breaches, VIP accounts, and high severity, routing the ticket, opening a linked Linear issue, and posting the alert.

Clustering rules, quote and title selection, and reconciliation against existing Linear issues for the feedback sweep.

Classifies every feature flag, removes what's safe (fully rolled out or long dead), and flags partial-rollout flags for a human.

Scores per-test flakiness from CI run history and quarantines the worst offenders via a skip-only PR.

Weights every open HubSpot deal by its own stage probability, rolls the total up by stage/rep/segment against quota, and flags deals slipping the quarter and other forecast risk.

The nightly dedupe, enrichment-fill, and stale-deal runbook, including the bulk-update approval gate.

The alert-triage runbook: pull the trace, correlate logs, find the suspect deploy, classify severity against known-noisy patterns, and decide when to page.

Reads the interview plan, checks panel availability, and drafts the candidate slot proposal and calendar invites — a coordinator confirms and sends everything.

The monthly metric-gathering, comparison, and formatting runbook, including plan targets and last month's update as the format reference.

Aging buckets, reminder tiers, and dunning cadence for chasing overdue invoices.

Clusters resolved tickets into topics, checks them against the KB repo and a ledger, and drafts undocumented recurring questions as a PR.

Runbook for researching a new lead, drafting a follow-up to the sales playbook, proposing a call slot, and gating every send behind human approval.

Territory map, segment specialists, stateless round-robin pool, intent scoring, HubSpot writes, and escalation rules for routing a new inbound lead to the right rep.

Legal document drafting -- contracts, memos, briefs, complaints, demand letters, opinions, discovery, settlements, ToS, privacy policies. Full pipeline: document structure, per-section writing, Bluebook citation, case law lookup (CourtListener API), regulation lookup (eCFR API), DOCX output, and TDD-style verification (defined terms, cross-references, placeholders, boilerplate, citation format). Triggers on: 'draft a contract', 'write a legal memo', 'create an NDA', 'write a brief', 'legal document about', 'draft a complaint', 'terms of service', 'privacy policy', 'demand letter', 'settlement agreement', 'legal opinion', 'discovery requests', any request to produce a legal or law-related document.

The per-meeting runbook for the notes format, action-item phrasing, ownership routing from memory, and when to flag instead of guess.

Our standard NDA positions on mutuality, confidentiality duration, governing law, non-solicit, remedies, residuals, and more, plus how to redline and flag.

Weekly workflow to cluster survey responses into themes, isolate detractor drivers, and track the score trend.

The runbook for working an employee departure across every connected system in the right order, with reversible vs. irreversible steps marked.

New-hire onboarding runbook across Google Workspace, Slack, and Linear, with an approval gate for account creation and group membership.

Runbook for tracking activation milestones and product events, detecting stalls and overdue accounts, drafting the nudge, and alerting the owning CSM.

The sourcing profile, the Greenhouse dedupe check, the personalized-outreach drafting approach, and the daily cap for outbound candidate sourcing.

Use for creating, editing, extracting, OCRing, filling, and converting PDF documents.

Find people and companies — track down a specific person, assemble a shortlist who match a profile (title + industry + geography + skill), or look up a company/account. Use to locate a named individual, build a sourcing/recruiting/outreach list, resolve a company's org chart or firmographics, or answer 'who is the X at Y' / 'find people who Z' / 'look up this company'. Backed by the people_search tool (LinkedIn profile search → structured profiles) for the default web path, and by a connected people-data connector (Apollo, People Data Labs, Clearbit, Clay, RocketReach, Hunter, Lusha, ZoomInfo) for verified, richer records and company-level data when one is available.

The outbound runbook: account research, the angle/proof-point playbook, sequence drafting, HubSpot logging, the daily cap, and the approval gate.

The header, link, and attachment checks used to classify a reported email's risk and recommend an action.

Hourly warehouse freshness, row-count, schema-drift, and failed-load checks that alert Slack and draft a GitHub issue with the likely cause.

Staleness, missing-field, stage-stall, and overdue-task rules, plus how to nudge the owning rep and escalate the day's worst offenders.

Classifies inbound HR questions as answerable from documented policy or as needing HR's judgment, drafts a grounded Gmail reply for the former, and escalates the latter to Slack.

Correlates the incident channel timeline against GitHub deploys and Datadog log spikes and drafts a structured postmortem PR.

The per-PR runbook: run the suite, deploy to the test environment, exercise the change through the edge, and post the result.

Classifies open PRs as overdue for review, stale, or carrying unaddressed requested changes, and writes the nudge for whoever owns the next move.

Create, manage, validate, preview, and export slide decks and presentations. Build 1920x1080 HTML slide decks (the default, higher-quality path) and export to PDF or PPTX — or produce/edit a fully native, editable PowerPoint (.pptx) file directly when the user needs a plain PowerPoint deliverable. Load this skill when you need to build a slide deck, presentation, or PowerPoint file, or export/edit/validate one.

Runbook for finding accounts due a QBR, pulling usage, health, support, and expansion signals, and assembling the draft deck and briefing doc.

Parses an inbound security questionnaire, matches each question to our vetted answers, drafts the response in the vendor's format, and flags anything without a confident match.

Matching rules, tolerances, and escalation logic for reconciling Stripe activity and the bank feed against the tracked invoices each month.

Renewal-workflow runbook: find renewals 90/60/30 days out, assemble the value/usage/expansion packet, draft outreach, and flag at-risk renewals.

Rubric-based scoring with quoted evidence, the structured screen format, and the strong-match interview-slot proposal.

Parses an RFP, matches questions to the vetted answer library, and drafts the response in Google Docs.

Find and read information on the open web — fan-out web/news/finance search plus full-page fetching and source extraction. Use to answer current questions, gather and cite sources, verify a claim, or pull text from specific URLs. Triggers: 'search the web', 'look this up', 'find sources on', 'what's the latest on', 'fetch this page', 'is it true that…', 'compare X vs Y'.

Collects shortcut requests since the last order, consolidates duplicates and standing staples, builds the cart, and gates checkout on an explicit Slack approval.

Reads the Notion content calendar, drafts platform-appropriate posts for upcoming items, and posts the batch with scheduled dates to the Slack approval channel.

Weekly SaaS-spend reconciliation runbook: match recurring charges to the register, detect duplicates/unused seats/price hikes/shadow IT, and rank recommended actions.

Validates the required vendor documents against a fixed checklist, records the result, and drafts a follow-up for anything missing or invalid.

Publish a website or web app from the sandbox to a public URL, and deploy to cloud providers — get a live link to share, ship a static site or SPA, put a built site online, or deploy a framework app / container. Use when the user says 'publish this', 'deploy it', 'put it online', 'give me a live URL', 'host this', 'share a preview link', or wants to make a site/app they (or you) just built reachable on the web. Covers the zero-account instant path (Cloudflare) and permanent hosting (Vercel, incl. any Dockerfile). Also owns the publish GUARDRAILS: never publish unprompted, how to honestly take a site down, the runtime-dependency and data-persistence checks, and the mandatory pre-publish security review. Points at kortix-marketplace for other providers and deeper provider-specific skills.

Use for fullstack web apps built with the bundled Express, Vite, React, Tailwind, and Drizzle template.

Use for distinctive production-grade websites, landing pages, and interactive web experiences with strong design and QA discipline.

The weekly shipping-brief runbook: window, PR-count sources, the leaderboard + streak format, the standup thread, the ledger, and Slack posting mechanics.

The weekly reporting runbook: metric definitions, the queries, the comparison window, notable-move criteria, and the report layout.

Breaks down closed deals by segment, competitor, price, and stage of death, clusters close reasons into themes, and posts themes plus recommendations to Slack.

Use for spreadsheet creation, analysis, financial models, and polished workbook outputs.