deepline-gtm-agent

Build a Total Addressable Market list by sourcing accounts and contacts from providers like Crustdata, Dropleads, and PDL.

Convert a Clay table configuration into local Deepline scripts. Handles extraction (MCP or script), documentation, action mapping, script generation, and parity validation against Clay ground truth.

Use this skill when answering business analytics, RevOps, GTM metric, pipeline, revenue, funnel, customer, or warehouse questions with Deepline. Triggers on phrases like 'query Snowflake', 'analyze pipeline', 'total ACV', 'break down by quarter', 'use the semantic layer', 'run a semantic query', or any use of snowflake_get_semantic_layer / snowflake_run_semantic_query. Skip prospecting, enrichment, contact finding, outbound, or personalization workflows; use deepline-gtm for those.

Send feedback or bug reports to the Deepline team, including session transcript and environment info. Use when the user asks to report a bug, send product feedback, or share the current Claude/Cowork session with Deepline support.

Use for outbound prospecting, enrichment, qualification, CSV processing, lead/account/contact research, waterfall enrichment, email or LinkedIn lookup, personalization, scoring, and campaigns. Route CSV-heavy and provider-driven requests here; use linked sub-docs and playbooks to execute. Providers: adyntel, ai_ark, allegrow, apify, attio, aviato, bettercontact, bloomberry, builtwith, cloudflare, contactout, crustdata, crustdata-v2, customer_db, dataforseo, datagma, deepline_native, deeplineagent, discolike, dropleads, emailbison, enformion, exa, findymail, firecrawl, forager, fullenrich, generic_http, google_ads_audiences, heyreach, hubspot, hunter, icypeas, instantly, ipqs, leadmagic, lemlist, limadata, linkedin_ads_audiences, linkedin_scraper, lusha, meta_audiences, openmart, opensosdata, openwebninja, parallel, peopledatalabs, predictleads, prospeo, rocketreach, salesforce, scrapecreators, serper, slack, smartlead, snowflake, tamradar, theirstack, trestle, upcell, wiza, wizleads, zerobounce.

Send Deepline SDK/V2 CLI feedback or bug reports, including environment info and the current Claude/Cowork session transcript. Use when the user asks to report a Deepline bug, share a failing run, or send feedback from a V2 SDK workflow.

Run a quick Deepline demo recipe on the V2 CLI using prebuilt plays.

Use for Deepline Plays/CLI V2 work: get started, find/describe/run prebuilts, process CSVs, bootstrap/wrap/fork plays, author durable V2 workflows, find companies or contacts, size TAM, inspect/export runs, explain billing, and repair failures. Triggers on deepline CLI work, plays, prebuilts, CSV enrichment, prospecting, TAM, provider routing, play authoring, staleAfterSeconds, datasets, runs, exports, billing, and eval-style GTM tasks.

Run a quick Deepline demo recipe to show the user how Deepline works.

Use when finding real role-holders at known company domains from an ICP, especially prompts like 'find all job titles at these companies', 'find qualified titles', 'find RevOps or marketing-ops buyers', or when exact title discovery should precede paid people search.

Resolve LinkedIn profile URLs from name + company with strict identity validation to avoid false positives.

Discover niche first-party signals that differentiate Closed Won vs Closed Lost accounts for ICP analysis. Use when the user provides won/lost customer domain lists and wants differential signals (website content, job listings, tech stack, maturity markers) to build account scoring models and prospecting criteria. Triggers: ICP analysis, niche signals, won vs lost analysis, differential signals, signal discovery, ICP signal report, account scoring signals, lead scoring, first-party signals, buyer signals. Before reading this file, first read deepline-gtm to understand the Deepline CLI tool and how to use it. Then read this file for guidance on the task.

Find companies backed by a specific investor or accelerator, then find contacts and build personalized outbound.

Create a cloud Deepline workflow that runs on a recurring cron schedule or via webhook, inspect it, and validate trigger behavior end to end.

Use for account research briefs, ICP fit checks, account signals, buyer hypotheses, and first-message angle maps. Uses Deepline-native execution for data access.

Use for Deepline GTM AgentMail workflows: inbox triage, inbound context capture, reply drafting, thread summaries, and safe email identity management. Draft-only by default.

Use for HubSpot/CRM hygiene proposals, duplicate checks, missing-field audits, stale deal review, and proposed CRM updates. Proposal-only unless approved.

Primary Deepline GTM operator for Jai. Use for routing, context selection, Deepline Session UI plans, tool selection, subagent orchestration, final review, and operator-facing summaries.

Specialist marketing subagent for Deepline campaign briefs, launch angles, channel plans, content calendars, SEO/GEO outlines, and GTM content workflows.

Specialist marketing subagent for Deepline content drafts: LinkedIn, newsletter, social, transcript-to-draft, short scripts, and founder POV. Review-only by default.

Specialist marketing review subagent for Deepline claims, exclusions, voice, source status, and external-use safety before content or campaigns are published.

Use before publishing Deepline claims, proof points, stats, customer references, or competitive statements. Blocks unsupported claims and excluded names.

Use as a bounded subagent for Deepline sales workflows: post-call follow-up drafts, account research briefs, CRM hygiene proposals, meeting prep, objection extraction, and outbound angle maps. Draft-only by default.

Use to design Deepline GTM workflow specs: triggers, inputs, steps, waterfalls, output contracts, validation, pilots, and rollout criteria.