creatop-gtm/apollo-operator

Run outbound against a named set of target accounts, or build a Dream 100 when there is no list: resolve accounts for free, map 2 to 3 people per account by default (or everyone, free or enriched), one sequence per persona, and stop the whole account on a positive reply. Use for high-value accounts, client target lists, or any time the operator wants to work specific companies.

Audit an existing Apollo account with reads only: mailboxes and daily limits, domain authentication, live sequences that are not actually sending, Bounce Guard, performance history, lists, contacts, credits, Context Center, and website tracking. Graded findings, no changes. Use before running outbound on an inherited or client account, or when a campaign is not sending.

Protect the sending asset on Apollo: mailbox health, warmup, volume limits, bounce and incident response, sending schedule. Use before launching and whenever deliverability looks off.

The last mile: enroll a graded list into a built (inactive) sequence, get a human to approve activation, and pull contacts on complaint or bad fit. Use to take an Apollo sequence live safely.

Turn a business and its ICP into a real Apollo search, a shared profile.yaml, and one to three custom scoring signals, validated on a sample. Use to define who to target on Apollo before building a list.

Build a clean, enriched, graded lead list on Apollo: paginated search, dedupe, credit-aware enrichment, scoring signals, email verification, then grade. Use to build the full prospect list after the ICP is set.

Optional layer on top of email: add LinkedIn, call, and manual steps to an Apollo sequence and work the task queue they create. Apollo automates email only; the rest are human tasks. Use to run multichannel outbound on Apollo.

The four ways to run Apollo headless and how to choose: MCP (typed tools, results always through context), the apollo CLI binary (disk output, common filters), REST authenticated with the CLI's own OAuth token (full MCP filter surface WITH disk output, no API key), and REST with an API key. Includes measured context costs, credit costs per lane, verified command recipes, and the kill switch for stopping a live sequence. Use to decide which lane a task should run on.

Write a 3-step, 2-variation cold email sequence matched to the persona (ATL or BTL) and build it in Apollo as an inactive draft. Use to write and create outbound sequences on Apollo.

Find the reason to reach out now. Offer-fit signal discovery, not a universal heat score. Use to identify and act on buying signals for a specific offer on Apollo.

Build one readable brief.md capturing the business: identity, offer, who buys and why, objections, proof, and voice. The narrative context layer every other skill reads. Use before ICP work, when copy comes out generic, or when the business changes.

Report a campaign's real results from Apollo's own analytics: per sequence, step, variant, and mailbox, plus meetings booked and opportunities, read-only. Use weekly, at the end of an experiment, or before deciding to scale, change, or stop a campaign.

Design single-variable outbound experiments (list-only, copy-only, combined) so you learn what actually works. Use to improve a campaign deliberately.

Check a lead list before it goes into a sequence. Gives a deliverability readout (firm) and a targeting readout (advisory). Surfaces issues, never blocks. Use before enrolling any list.

Operator context for running B2B outbound on Apollo.io through the Apollo MCP. Load this first. Provides the Apollo tool map, universal deliverability and copy rules, the shared profile.yaml object, and routing to every other Apollo Operator skill. Use for any outbound task on Apollo: targeting, list building, sequences, deliverability, sending, or iteration.

Classify replies and compute positive reply rate, the metric that predicts revenue. Use to tell whether a campaign is actually working, not just getting replies.

Go back to leads who finished a sequence and never replied. Covers when it is safe to re-approach (60-90 days), the permanent exclusions, re-verification, and bringing a genuinely new angle rather than another follow-up. Use for quarterly re-engagement passes or when a finished list looks dead.

Build the sending stack from zero before you send: dedicated domains separate from your primary, mailboxes, SPF/DKIM/DMARC/MX, redirect, and warmup. Includes the volume math (mailboxes and domains per daily send target). Use for first-time setup or when scaling adds mailboxes.

Review a drafted cold email sequence for spam and deliverability risks (firm) and copy craft (suggestions). Advisory, never blocks. Use before building or activating a sequence.

The weekly operating cadence for running outbound continuously: Monday deliverability, Wednesday reply sweep, Friday retrospective, plus biweekly, monthly, and quarterly reviews. Use to run outbound as an ongoing system.