Systems Lab

Skill library

victor-shulga/gtm-skills

Publisher description: 10 Claude Skills for B2B agency go-to-market — outbound, scoring, offers, proposals, reply handling. By Victor Shulga (Fractional CRO).

Catalogue scope: 6 entries at separate source paths.

MIT

Repository health

GitHub’s own figures, read from its REST API. Commit and contributor totals come from the paging header rather than an estimate.

Repository metadata checked 2026-10-06 · skill files extracted 2026-10-06 · published 2026-09-05

Extraction and automated analysis describe the files at the recorded revision. They are not an editorial review or a test of the skills in use.

Stars
0
Commits
16
Last 90 days
16

commits

Contributors
2
Last push
2026-09-24
First commit
2026-07-15

repo created

6 skill entries

  • agency-signal-sourcer

    Operational buying-signal engine for B2B service agencies (BIM/MEP, custom dev, GIS, AI/SaaS engineering outsourcing). Answers the OPERATIONAL half of signal-based outbound: how to DETECT a signal (which tool, Clay credit cost), WHEN it expires (freshness and decay windows), how to SCORE and prioritise accounts (recency multipliers, multi-signal stacking, heat tiers with SLAs) and WHAT to do once it fires (signal-to-action plays). Use for: detecting buying signals, which tool finds which signal, Clay cost per signal, signal freshness / decay / timing, signal scoring, heat-tier SLAs, signal-to-action plays, visitor-tracking and intent tooling (RB2B, Trigify, Common Room, Bombora, Koala, Warmly, 6sense, with EU/GDPR and agency-budget caveats), or "how do we operationalise signal X". Pairs with the STRATEGY layer (which signal x ICP x offer to test). Do NOT use it to invent the signal list (hypo-generator's signals-catalog) or to write outreach copy (sequence-writer).

    Self-containedInstructions only973 words
  • anticopywriting-ai

    Знаходить і прибирає ознаки ШІ-генерації з тексту українською або англійською мовою. Робить текст природним, людяним, з власним голосом замість шаблонного «копірайтингу від ChatGPT». Виявляє і виправляє: роздування значущості, канцелярит, ШІ-кліше, шаблонні звороти, надлишкове форматування, підлабузницький тон, водянисті формулювання, відсутність голосу. Якщо текст пишеться для Viktor Shulha — підтягує його стиль із about-viktor. Використовуй цей скіл, коли користувач каже: «прибери ШІ», «зроби людяним», «гуманізуй», «humanize», «deslop», «remove AI signs», «це звучить як ChatGPT», «перепиши, щоб не пахло ШІ», «перевір на ШІ», «зроби природніше», «звучить як копірайтер», «занадто гладко», «забери воду», «anti-copywriting», «check for AI», «make it sound human», «rewrite without AI tone», «занадто шаблонно», «зроби живим». Також тригер — коли користувач показує текст і скаржиться на «гладкість», «штучність», «безликість» або просить «прибрати канцелярит».

    Reaches the webDeclared tools2,185 words
  • hypo-generator

    Use when Viktor wants to generate outreach hypotheses for an IT agency client from a website URL or text brief. Performs Phase 1 (extract services / ICP / use cases / case studies from the client's site) + Phase 2 (build a 10-hypothesis matrix of 2-3 ICP × 2-3 signals × 2-3 offers, each scored with Viktor's 5-factor weighted framework). Trigger when the user says: "генеруй гіпотези для клієнта", "побудуй матрицю гіпотез", "оціни цей агентський сайт", "що тестувати для [клієнт]", "hypothesis generation for agency", "матриця гіпотез по URL", or provides a client URL and asks what campaigns to run. NOT for one-off campaign idea generation when ICP/signals are already known — use hypothesis-builder for that.

    Reaches the webActs undeclared1,915 words
  • hypothesis-scoring

    Scores and ranks outbound hypotheses BEFORE launch and turns them into a launch queue — the pre-launch evaluation method from Victor Shulga's guide on testing cold-outreach hypotheses: stop-filter gate, canonical hypothesis format with the number N, channel capacity check, 6-factor weighted score on the 0/1/3/5 scale, priority queue where the top three go into work, and a journal skeleton for the facts. Trigger when the user says "оціни гіпотези", "оцінка гіпотез", "пріоритизуй гіпотези", "яку гіпотезу запускати першою", "черга запуску", "відбери 3 гіпотези", "score these hypotheses", "prioritize hypotheses", "which hypothesis do we run first", or hands a list of campaign ideas / a hypothesis matrix and asks what goes into work. Also use to re-score a hypothesis matrix before launch, or to audit a hypothesis list a team wrote itself. NOT for generating hypotheses from scratch (use hypo-generator), NOT for reading results after a test has already run.

    Self-containedActs undeclared1,843 words
  • offer-factory

    Use when Viktor wants to invent offers FAST for an IT-agency client and test them with outbound. From a client website URL, generates 5–10 testable offer-bets (ICP × pain × mechanism), scores them, and expands the winners into outbound-ready cards with built-in test design. Trigger when the user says "придумай офери для клієнта", "що продавати цій агенції", "офери під аутбаунд", "build offers from this URL", "offer factory", "розроби офер для [клієнт]", or pastes an agency URL and asks what to sell/test. NOT for choosing WHO+WHICH-SIGNAL to target (use hypothesis-builder / hypo-generator for that) — this skill is about the OFFER itself.

    Self-containedActs undeclared1,101 words
  • prospect-profiler

    Turns a SCORED account list into one tactical pre-touch dossier per account: a compact "60-second card" an SDR reads right before writing the first touch. Batch by design: reads the output of lead- scoring / agency-signal-sourcer (or any list with company + signal + role data) and emits one action card per account (summary, talking points, comm style, grounded pain, recommended approach, data- quality flag). Adapted for B2B service agencies (BIM/MEP, GIS, custom dev, AI/SaaS engineering outsourcing), NOT US-SaaS. Use when asked: "зроби картки по лідах", "профайли проспектів", "pre- touch brief", "дос'є на акаунти", "prep cards before outreach", "build prospect profiles", or when handed a scored list before copy is written. Sits between the list stage and the copy stage. NOT for deep one-company intelligence (account-dossier), NOT for persona archetypes (persona-builder), NOT for writing the sequence (sequence-writer).

    Self-containedInstructions only1,099 words

Ask about victor-shulga/gtm-skills

Opens your assistant with this page's verified links already in the prompt.

Is this safe to install?ClaudeChatGPT
Adapt it to my stackClaudeChatGPT
What else do I need for it to workClaudeChatGPT
Rather ask a human? Talk to Cheetah

Need help setting it up?

This page tells you what victor-shulga/gtm-skills does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.

Book a call →

The directory stays free. There is nothing gated behind this.