extruct-ai/gtm-skills

extruct-ai-Profil

Letzte erfasste Quellaktivität: 28. September 2026 um 15:41

SkillsMP-Katalog aktualisiert: 17. Oktober 2026 um 00:09

gesammelte Skills: 21

GitHub-Stars: 109
GitHub-Forks: 24

README des Repositorys

README-Quelldatei: README.md

README-Quelldatei lesen

Vollständige README anzeigen

![Extruct](docs/images/cover.png) # GTM Skills by Extruct Run outbound campaigns end-to-end with [Extruct](https://www.extruct.ai) and [Claude Code](https://docs.anthropic.com/en/docs/claude-code/skills). Research, list building, enrichment, segmentation, email generation, and sending. Use one [skill](https://docs.anthropic.com/en/docs/claude-code/skills) or combine several. Each works independently. For updates, follow [Danny Chepenko on LinkedIn](https://br.linkedin.com/in/danielchepenko). ## Getting Started ### 1. Install skills Via [skills.sh](https://skills.sh) CLI ([repo](https://github.com/vercel-labs/skills)): ``` npx skills add extruct-ai/gtm-skills ``` Or via [Claude Code](https://docs.anthropic.com/en/docs/claude-code/skills) plugin manager: ``` /plugin marketplace add extruct-ai/gtm-skills /plugin install gtm-skills ``` Skills are stored in `~/.claude/skills/`. Install once, use everywhere across all your projects. **Updating:** re-run `npx skills add extruct-ai/gtm-skills` to pull the latest version, or `npx skills update` to update all installed skills at once. For the plugin manager, run `/plugin marketplace update` to refresh and get the latest versions. ### 2. Get your Extruct API token Sign up at [extruct.ai](https://www.extruct.ai) (free plan with 25 monthly credits) and grab your API token from the dashboard. The token is needed for company search, table creation, enrichment, and people search. Skills that don't call the Extruct API (context-building, hypothesis-building, email-prompt-building, email-generation) work without it. Set the token in your terminal: ``` export EXTRUCT_API_TOKEN=<your-token> ``` If you skip this step, skills will ask for the token in chat when they need it. ### 3. Run your first workflow Describe what you need in Claude Code: **Start from your website:** ``` I'm building www.example.com. Read my website, figure out my ICP, and draft a plan for an outbound campaign. ``` **Start from a win case:** ``` I'm building www.example.com. One of my customers is www.customer.com, they use us to score suppliers. Find similar companies and plan a campaign. ``` **Start from a list of won deals:** ``` I'm building www.example.com. Here's a list of my won deals [attach CSV]. Analyze them and find similar companies to target. ``` Each prompt triggers plan mode. Claude will research, ask clarifying questions, and propose a step-by-step campaign plan before executing. ## Skills Use one, combine a few, or run them all. No required sequence, each skill works independently. | Skill | Description | |-------|-------------| | **context-building** | Build/maintain global context file (ICP, voice, proof points, DNC) | | **hypothesis-building** | Generate pain hypotheses from context file + user knowledge (no API) | | **list-building** | Find companies via Search, Discovery, or Lookalike | | **market-research** | Research vertical pain points via deep research APIs | | **enrichment-design** | Design enrichment columns (segmentation + personalization) | | **list-enrichment** | Add research columns to Extruct tables | | **table-creation** | Create Extruct table, upload rows, add columns | | **list-segmentation** | Tier companies by hypothesis fit + data richness | | **account-research** | Deep-dive one target account: resolve its entity tree, map buyers, mine signals | | **people-search** | Find LinkedIn profiles via Extruct | | **email-search** | Get verified emails + phones via contact enrichment providers | | **email-prompt-building** | Build self-contained prompt template for a campaign. **Edit this skill to change email structure** (paragraph count, word limits, format). | | **email-generation** | Generate emails from prompt + CSV (tier-aware) | | **atomic-message** | Draft ONE message (cold email, LinkedIn, or follow-up) from signal + persona + channel — runtime generator with self-check lint. Single message, not a sequence. | | **email-verification** | Validate emails via verification provider before sending | | **email-response-simulation** | Simulate prospect reading your email (Tier 1 review) | | **campaign-sending** | Upload leads for sequencing and sending | | **inbox-reply** | Manage and reply to lead responses in the email sequencing inbox | | **competitor-monitoring** | Track competitors with enrichment-powered monitoring tables | | **post-engagers** | Extract engagers from any LinkedIn post and load into Extruct | | **extruct-api** | Bundled Extruct API reference — used by other skills for all API operations | ## About Extruct [Extruct](https://www.extruct.ai): API-first company search and lookalikes engine. **Core capabilities:** - **Instant Search**: semantic company search (free, unlimited) - **Lookalike Search**: find companies similar to your best accounts (free, unlimited) - **Deep Search**: AI-powered discovery with criteria scoring (1 credit/match) - **AI Tables**: research any data point per company with AI agents (1 credit/cell) - **People Finder**: find decision makers with LinkedIn profiles (2 credits/cell) **Pricing:** Free with 25 monthly credits. Starter at $49/mo for 500 credits. See [extruct.ai/pricing](https://www.extruct.ai/pricing). Built by [Danny Chepenko](https://www.linkedin.com/in/danielchepenko/) and [Dima Persiyanov](https://www.linkedin.com/in/persiyanov/) --- ## Reference ### Campaign Artifacts Skills automatically create a `claude-code-gtm/` directory with all intermediate files: ``` claude-code-gtm/ ├── context/ │ ├── {company}_context.md ← ICP, voice, proof points │ └── {vertical-slug}/ ← per-vertical research + hypotheses ├── prompts/ │ └── {vertical-slug}/ ← email prompt templates └── csv/ ├── input/{campaign-slug}/ ← segmented lists, people, contacts └── output/{campaign-slug}/ ← generated emails ``` ### Environment Variables | Variable | Service | Used by | |----------|---------|---------| | `EXTRUCT_API_TOKEN` | [Extruct API](https://www.extruct.ai/docs) | list-building, list-enrichment, table-creation, people-search, list-segmentation, email-search | Other providers' credentials (email enrichment, sequencing, deep research) are requested in chat when the corresponding skill runs.

README des Repositorys wird geladen…

Skills in diesem Repository

Marktforschungsanalysten und Marketingspezialisten Dienstleistungsvertriebsmitarbeiter (außer Werbung, Versicherung, Finanzdienstleistungen und Reisen)Softwareentwickler

3 Berufskategorien · 100% klassifiziert

Skill

Beruf

Beschreibung

Aktualisiert

email-search

Marktforschungsanalysten und Marketingspezialisten

Get verified emails and phones for contacts found by people-search. Takes LinkedIn profiles from the Extruct people table and enriches them via contact enrichment providers like Prospeo or Fullenrich. Supports single-provider and waterfall modes. Outputs a…

Quellsprache: Englisch

2026-09-28

account-research

Marktforschungsanalysten und Marketingspezialisten

Deep-research a single target account into a decision-ready dossier: the entity tree, the buying units and decision-makers, live signals (open/closed roles, leadership moves, news, tech stack), and the entry angle. Powered by Extruct Deep Research — ONE cited…

Quellsprache: Englisch

2026-07-01

atomic-message

Dienstleistungsvertriebsmitarbeiter (außer Werbung, Versicherung, Finanzdienstleistungen und Reisen)

Draft ONE cold-outreach message from a signal + persona + channel: a single cold email, a LinkedIn note, or a follow-up. Generates one primary draft plus 1-2 variants, then runs a self-check lint. Reads voice, sender identity, positioning, proof, and banned…

Quellsprache: Englisch

2026-06-16

email-verification

Dienstleistungsvertriebsmitarbeiter (außer Werbung, Versicherung, Finanzdienstleistungen und Reisen)

Validate email addresses before campaign sending. Takes a contact CSV, validates each email via a verification provider, removes invalid/do_not_mail/abuse/catch-all/unknown addresses, and optionally cleans them from sequencer campaigns. Outputs a verified CSV…

Quellsprache: Englisch

2026-05-21

email-generation

Dienstleistungsvertriebsmitarbeiter (außer Werbung, Versicherung, Finanzdienstleistungen und Reisen)

Render a cold-outreach email sequence from a fixed template set and a contact CSV whose input fields are already filled. Deterministic — variant routing + placeholder substitution, no per-row LLM call. The render contract (newline model, per-target escaping,…

Quellsprache: Englisch

2026-05-20

email-prompt-building

Marktforschungsanalysten und Marketingspezialisten

Design a cold-outreach email sequence as a FIXED TEMPLATE SET — real, human-approved copy with {{input_field}} placeholders and variant-routing rules. Reads the company context file and campaign research, explores angles, and commits to copy at design time.…

Quellsprache: Englisch

2026-05-20

campaign-sending

Marktforschungsanalysten und Marketingspezialisten

Upload finalized emails for sequencing and sending. Maps fields to lead schema, creates or finds campaigns, uploads leads with dedup, and provides a pre-send verification checklist. Triggers on: "upload to instantly", "run instantly", "send emails",…

Quellsprache: Englisch

2026-05-20

post-engagers

Marktforschungsanalysten und Marketingspezialisten

Extract people who engage (comment, react, repost) on a LinkedIn post, enrich their profile / email / company data, and land them in a local SQLite CRM (content.db → crm.db) as the source of truth. Extruct people-table upload is optional. Triggers on: "post…

Quellsprache: Englisch

2026-05-20

inbox-reply

Marktforschungsanalysten und Marketingspezialisten

Manage and reply to lead responses in Instantly unibox. Fetches unread conversations, classifies reply intent, drafts contextual responses, and sends replies via Instantly API. Fits after campaign-sending in the GTM pipeline. Triggers on: "reply to leads",…

Quellsprache: Englisch

2026-03-27

email-response-simulation

Marktforschungsanalysten und Marketingspezialisten

Deep persona simulation and skeptical buyer review for cold emails. Builds a full prospect "world" from LinkedIn + company data, defines their professional reality (KPIs, pain points, inbox behavior), then runs a skeptical buyer roast — emotional reaction…

Quellsprache: Englisch

2026-03-20

competitor-monitoring

Marktforschungsanalysten und Marketingspezialisten

Set up and run competitive intelligence monitoring. Discover competitors via user input, lookalike search, web research, or G2/review sites, then create an Extruct company table with research columns for blog, social media, news, key people, and business…

Quellsprache: Englisch

2026-03-19

extruct-api

Softwareentwickler

Run explicit Extruct API tasks through the bundled Extruct CLI. Covers Deep Search, semantic search, lookalike search, company and people tables, column operations, enrichment, and contact finding.

Quellsprache: Englisch

2026-03-19

list-building

Marktforschungsanalysten und Marketingspezialisten

Build targeted company lists for outbound campaigns using Extruct. Use when the user wants to: (1) find companies matching an ICP, (2) build a prospect or outbound list, (3) search for companies by description, (4) discover companies in a market segment, (5)…

Quellsprache: Englisch

2026-03-19

list-enrichment

Marktforschungsanalysten und Marketingspezialisten

Add research-powered enrichment columns to Extruct company tables. Use when the user wants to add enrichment columns (e.g. funding, verticals, tech stack) to an existing Extruct table, run column configs from enrichment-design, or monitor enrichment progress.…

Quellsprache: Englisch

2026-03-19

list-segmentation

Marktforschungsanalysten und Marketingspezialisten

Take an enriched Extruct table and a hypothesis set, then segment companies by hypothesis fit and assign tiers based on data richness and signal strength. Outputs a tiered, segmented list ready for email generation. Triggers on: "segment", "tier", "segment…

Quellsprache: Englisch

2026-03-19

people-search

Marktforschungsanalysten und Marketingspezialisten

Find LinkedIn profiles of decision makers at target companies using Extruct's company_people_finder. Takes a company table, adds a people finder column, and produces a linked child people table with names, roles, and LinkedIn URLs. No external API credits —…

Quellsprache: Englisch

2026-03-19

table-creation

Marktforschungsanalysten und Marketingspezialisten

Create an Extruct company table from user-provided data, upload rows, and optionally add enrichment columns. Handles the full flow: parse input (CSV, pasted list, or structured data), create or reuse a table, upload domains in batches, add agent columns, and…

Quellsprache: Englisch

2026-03-19

context-building

Marktforschungsanalysten und Marketingspezialisten

Build and maintain a global company context file that all other GTM skills read from. Captures product info, voice rules, ICP, win cases, proof library, campaign history, hypotheses, and DNC lists. Supports four modes: create (new context), update (append to…

Quellsprache: Englisch

2026-03-04

market-research

Marktforschungsanalysten und Marketingspezialisten

Research a target vertical's pain points using deep research APIs and distill findings into a numbered hypothesis set. Pure industry education tool — decoupled from email generation. Use when the user wants to understand a market before outreach, form…

Quellsprache: Englisch

2026-03-03

enrichment-design

Marktforschungsanalysten und Marketingspezialisten

Design enrichment columns that bridge research hypotheses to list enrichment. Two modes: segmentation (columns that score hypothesis fit per company) and personalization (columns for company-specific hooks). Interactive column design with the user. Outputs…

Quellsprache: Englisch

2026-03-03

hypothesis-building

Marktforschungsanalysten und Marketingspezialisten

Generate testable pain hypotheses from the company context file (ICP, win cases, product knowledge) and user input. Fast, no API keys needed — pure reasoning. Outputs a hypothesis set with search angles that directly guide list-building queries. Sits between…

Quellsprache: Englisch

2026-03-03

Es werden 21 von 21 gesammelten Skills angezeigt.

Mit einem KI-Assistenten installieren

Diesen Prompt kopieren und in den verwendeten KI-Assistenten einfügen.

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/extruct-ai/gtm-skills.