import-contacts

Quick book-of-business snapshot for a HubSpot Solutions Partner — total clients, total MRR, which clients need attention (churn signals, declining usage, near-term renewals, renewal dates to verify, managed relationships about to lapse) and which carry an ML-detected revenue signal. The fast entry point: it gives the overview, then points you to the specialised partner skills for the deep work. Read-only: never creates or edits records or deals, and never contacts anyone. ALWAYS use this skill for any portfolio-level request — "how's my book of business", "show me my clients", "client overview", "portfolio summary", "book of business", "client snapshot", "which clients need attention", "how's my portfolio doing", "partner overview", "review my clients" — and for "tell me about [client]". This skill is a lightweight pulse only — it hands off to the other skills for detail.

Read-only expansion reporting for a HubSpot Solutions Partner: surface which of the partner's clients are worth an upsell or cross-sell — including clients maxed out on seats, credits, or contacts, sitting on unactivated tools, or simply thriving with room to grow — ranked by value, plus (on request) the reasoning for a fit and suggested outreach copy. Use for viewing, prioritizing, or drilling into a partner's expansion, upsell, or cross-sell opportunities — e.g. "which clients can I sell more to", "who's maxed out on seats", "best Sales Hub opportunities", or "which clients should I approach about AI agents, and why". Do not use for creating or editing deals, updating records, or sending outreach or contacting customers — it drafts copy but only reads and reports. The deep-dive companion to book-pulse.

Read-only renewal reporting for a HubSpot Solutions Partner: surface which of the partner's clients have HubSpot subscription renewals coming up, ranked by urgency, with per-Hub renewal dates and the Contract Manager to coordinate with. Also flags renewal dates in the past that need verifying. Use for viewing, prioritizing, or drilling into upcoming or per-Hub client renewals — e.g. "walk me through my upcoming renewals", "who's renewing in the next 90 days", or "renewal dates for [client]". Do not use for creating or editing renewal deals, updating records, or contacting Contract Managers or customers — those are write workflows, and this skill only reads and reports. The deep-dive renewals companion to book-pulse.

Prepares a focused brief before a sales call or meeting. Pulls CRM history, open deals, recent notes, email threads, and company news. Falls back to calendar and email if the contact isn't in HubSpot yet. ALWAYS use this skill before a call or meeting — "prep me for my call with X", "I have a meeting with [company]", "brief me on [name]", "what do I know about X before my call", "research X", "who am I meeting with today", "prepping for X", or just a name paired with "call" or "meeting". Trigger proactively when the user seems about to get on a call and hasn't run prep.

Pulls a full view of a contact from HubSpot — deal status, lifecycle stage, last interaction, notes, tasks, and associated company. Returns a clean summary in chat. ALWAYS use this skill when the user asks about a specific person by name — "pull up X", "show me X's record", "what's happening with X", "check X", "who is X", "tell me about X", "what's X's status", "when did we last contact X", "look up X". Also trigger when the user pastes a contact email address wanting context on that person.

Generates a prioritised daily brief from HubSpot data plus any connected apps (calendar, email, Slack, meeting notes). Shows today's meetings, surfaces GTM tasks with effort-aware scheduling, deduplicates suggestions against existing HubSpot tasks, and outputs as readable markdown. ALWAYS use this skill when the user wants their day laid out — "good morning", "daily brief", "morning brief", "what do I need to do today", "what's on my plate", "what should I focus on", "catch me up", "today's priorities", "what's urgent", "what's due today", "show me my day", or any morning planning request. Trigger proactively when a user opens Claude first thing with no specific ask.

Drafts a personalised follow-up or outreach email for a named contact, grounded in HubSpot deal context, recent notes, and email history. Opens HubSpot with the email pre-populated so the rep can review and send with full tracking. If deal-related, updates the next step or deal stage as applicable. ALWAYS use this skill when the user wants to write or send outbound communication to a specific contact — "follow up with X", "draft an email to X", "send something to X", "check in with X", "reach out to X", "ping X", "touch base with X", "I need to reply to X", "draft a follow-up for [deal]", "write to X". Trigger on any request to compose outbound communication tied to a contact or deal.

Main HubSpot assistant and entry point for all CRM tasks. Handles direct lookups, stats, quick field updates, and how-to questions — and routes to specialized skills (call-prep, daily-brief, follow-up, log-call, pipeline-pulse, import-contacts) when a specific workflow is needed. ALWAYS use this skill as the primary entry point for any HubSpot-related request — "show me [contact]", "open deals", "pipeline value", "create a task", "update [deal]", "how many contacts", "what can you do", or anything touching contacts, companies, deals, or tasks. Even when another skill might match, use this one — it routes appropriately. Trigger on "/hubspot", "hey HubSpot", or any CRM question without a more specific skill clearly in scope.

About 450 ready-made HyperFrames blocks and components installed as editable source - transitions, overlays, titles, kinetic type, captions, charts, map overlays, 3D, camera moves. Use it before hand-building any named visual (CRT scanlines, glitch, film grain, a chart); also for hyperframes add and catalog.

Postgres best practices maintained by Supabase, for Postgres running anywhere. Load this skill BEFORE writing or changing anything that lives in a Postgres database: creating or altering tables and columns (including choosing column types), schema design, migrations and declarative schema files, RLS policies and the tests that verify them, indexes, triggers, database functions, queues and scheduled jobs (pg_cron, pgmq), vector/semantic search (pgvector), and restoring dumps (pg_restore) or importing data. Also load it when diagnosing slow queries, high CPU, timeouts, EXPLAIN plans, connection exhaustion, locking, bloat, or rows visible to the wrong user or tenant. This is not just a performance guide — schema, migration, security, and SQL authoring tasks need these rules too, even for a one-column change or a single query.

Deprecated compatibility name for prisma-orm-setup. Use only when a user or existing integration explicitly invokes prisma-database-setup; otherwise select prisma-orm-setup.

Deprecated compatibility name for prisma-postgres-setup. Use only when a user or existing integration explicitly invokes prisma-postgres; otherwise select prisma-postgres-setup.

Obtain or reuse a Prisma Postgres database and connect an application. Use when the user needs a database and has none configured ("I need a database", "add a Postgres database", "set up a database for this app"), runs or mentions `create-db` or `npx create-db`, or asks to set up or connect Prisma Postgres, including in v0 and the Vercel Marketplace. Hands Prisma ORM configuration to prisma-orm-setup; reuses an existing connection first and honors an explicit provider, driver, alternative ORM, or database-only choice.

Required reference for Prisma ORM 7 SQL driver adapter work. Use when implementing or modifying adapters, adding database drivers, or touching SqlDriverAdapter, Transaction, savepoint, result mapping, or DriverAdapterError behavior. Covers current transaction lifecycle, optional savepoint hooks, original database-error preservation, and verification.

Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, SvelteKit, Astro, Remix; auth issues (login, logout, sessions, JWT, cookies, getSession, getUser, getClaims, RLS); Supabase CLI or MCP server; schema changes, migrations, declarative schemas, security audits, Postgres extensions (pg_graphql, pg_cron, pg_vector); debugging and troubleshooting errors or unexpected behavior on Supabase projects (HTTP errors, Postgres errors, RLS surprises, permission denied, schema cache issues, timeouts, Edge Function crashes, Realtime drops, Storage failures) and reading or querying logs (Logs Explorer, ClickHouse).

Guides and best practices for working with Lakebase Postgres on Neon: connections, pooled vs direct, schema migrations, branching (including schema-only, reset-from-parent, and branch-per-PR workflows), autoscaling, scale-to-zero, instant restore, read replicas, IP allow lists, logical replication, egress optimization, and Lakebase Search. Use when the work is an existing DATABASE_URL, SQL, schema, inspect, or search. New backends, Auth, files, Functions, and LLM calls go to the parent `neon` skill. Live queries, reactive UIs, and realtime data go to `neon-realtime`. Also use for "@neondatabase/serverless", "@neon/neon-js", "neon inspect db", "neon postgres computes", "Neon branch", "schema-only branch", "reset branch", "branch per PR", high database bills, network transfer or egress, SELECT * optimization, query overfetching, "semantic search", "vector search", "full-text search", "BM25", or "hybrid search".