Open, production-grade GTM skills for AI agents.
This repository also configures its own agents. See what gtm-skills tells them →
Skill Claude CodeCodex
Use this skill in the gap between a discovery call and the demo that follows — when you have discovery notes and need to turn them into a demo that proves value instead of dumping features. Run it when a rep is about to "walk through the product," when discovery surfaced several pains and you need to decide what to…
Skill Claude CodeCodex
Use this skill on a live deal when you need to stop relying on one contact and build a coalition across the buying committee. Run it when a deal is single-threaded (everything runs through one champion), when you can't name who actually decides, when a champion goes quiet and the deal goes dark with them, when you're…
Skill Claude CodeCodex
Use this skill when a deal is live and you need to align the buyer on a shared path to value — when a champion asks "so what are the next steps," when you're heading into scoping, POC, security review, or procurement, when a deal has slipped once or stalled with no mutual timeline, when you just can't tell who on the…
Skill Claude CodeCodex
Use this skill when a live deal needs a business case the buyer will actually believe — heading into procurement, finance review, or exec sign-off, when a champion needs an internal case to justify the spend, when a single "dream ROI" number is triggering skepticism, or when you want to pre-handle the…
Skill Claude Code
Map every decision-maker, influencer, and blocker at a target account. Takes a company name or domain plus a deal stage or research context. Returns verified contacts classified by buying role, coverage gaps by function, departure flags, and ranked next actions — all shaped by where you are in the deal. Requires a…
Skill Claude Code
Turn any trigger event into a full cold outreach sequence. Takes a signal, a contact identifier, and product context. Verifies the contact via Lusha, confirms account signals, and writes a multi-step sequence grounded in the specific trigger — not a generic template. Up to 5 steps with subject lines, body copy, and…
Skill Claude Code
Run a weekly signal sweep across every account in your territory. Takes an account list and returns a ranked brief — promotions, job changes, funding rounds, hiring surges, and intent spikes, sorted by signal strength. Designed to run every Monday morning before a pipeline review. Requires a Lusha connection.
Skill Claude CodeCodex
Use this skill when any GTM copy needs to stop reading like AI before it ships - a LinkedIn post, a cold email, a newsletter, a landing page, a case study, an exec's thought-leadership draft. Produces the same copy with the machine tells stripped out, back to a clean baseline. Reach for it when someone says "this…
Skill Claude CodeCodex
Use this skill when a GTM operator is losing time hopping between tools to see their own work - the task board in one tab, the outreach queue in another, research in a third, the content calendar in a fourth. Produces one personal operating surface that aggregates those lanes, plus a single daily "what needs me now"…
Skill Claude CodeCodex
Use this skill when GTM copy is clean but reads flat, generic, or "technically fine but nobody's home" - a LinkedIn post, a cold email, a newsletter, an exec's thought-leadership draft, a landing page. Produces the same copy with one or two deliberate human moves added, so it reads as one specific person instead of a…
Skill Claude CodeCodex
Use this skill when ghostwriting LinkedIn posts for a founder or executive - the ask is "what should our CEO post", "draft the next posts for [exec]", "write this in [exec]'s voice", "an industry-news take", "a repost", or "exec thought leadership". Produces three ranked, typed post options per executive in that…
Skill Claude CodeCodex
Use this skill when doing media and PR outreach - first contact with a reporter, a news pitch, a contributed-byline pitch, or a fast reactive pitch on breaking news. Produces a short, anchored pitch that leads with the reporter's beat and closes on a concrete give-plus-ask, plus a follow-up plan. Reach for it when the…
Skill Claude CodeCodex
Use this skill when an inbound RFP, RFI, or brief lands and a proposal has to go back by a deadline - "an RFP just came in", "should we bid on this", "build the response", "the proposal is due Friday", "set up the RFP", "where are we on the [brand] RFP", "what's the status of our RFPs", "which RFP is about to slip".…
Skill Claude CodeCodex
Use this skill when a marketing design asset needs a senior review before it ships - a sales deck, a one-pager, a LinkedIn graphic or carousel, a case study, a landing section, a proposal slide. Produces a prioritized design read: what works, the ranked fixes with the commercial reason for each, brand and…
Skill Claude CodeCodex
Use this skill immediately after acquiring a product or brand, before combining websites, customer data, pipelines, messaging, analytics, or campaigns. Produces a staged GTM integration plan that preserves active demand and customer access while defining what to retain, endorse, consolidate, or retire.
Skill Claude CodeCodex
Use this skill after a B2B webinar has registrations or engagement data but before treating every registrant as a sales lead. Produces reconciled lifecycle states, fit and intent scores, a prioritised sales-review queue, segment-specific follow-up, and a measurable handoff from webinar registration to qualified…
Skill Claude CodeCodex
Use this skill when an AI-visibility number needs to be trusted, defended, or compared over time — "is this score real," "the engine said something different an hour later," "did our AI visibility actually move this week." Re-asks every question multiple times per engine, majority-votes presence, and keeps the…
Skill Claude CodeCodex
Use this skill when the sources behind AI answers are known and the brand needs to get into them — "AI keeps citing these directories and the brand is not there," "turn the citation analysis into an outreach plan," "get named where the engines already read." Converts cited-source gaps into a ranked get-listed plan…
Skill Claude CodeCodex
Use this skill when a business serves specific towns or suburbs and needs to know where AI recommends it — "do we show up in this suburb," "named in one city and invisible in the next," "which service areas are the gap." Measures AI answers town by town, records map-pack and written-answer presence separately, and…
Skill Claude CodeCodex
Checks whether a Swan workspace is structurally healthy. Use for configuration audits that surface missing knowledge, disconnected integrations, exhausted senders, broken triggers, sparse CRM data, and credit or subscription issues.
Skill Claude CodeCodex
Creates or updates a competitor battlecard. Use when the user needs positioning, strengths, weaknesses, objections, win conditions, and practical talk tracks saved into competitive knowledge.
Skill Claude CodeCodex
Creates a one-page executive account brief. Use before sponsor syncs, deal reviews, QBRs, or board updates where the user needs account context, opportunity state, risks, and asks.
Skill Claude CodeCodex
Builds prospect lists of companies, contacts, or both. Use when the user asks for target accounts, ICP-fit prospects, decision-makers, enrichment, or a list ready for CRM, Swan, or sequence activation.
Skill Claude CodeCodex
Triages pending Swan work for a user. Use to prioritize review items, sequence approvals, alerts, and suggestions into act-now, bulk-approve, acknowledge, or investigate buckets.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: