getbeton/openclaw-gtm-skills

18 skills

• gtm-campaign-prep

  End-to-end campaign preparation — from hypothesis to send-ready CSV. Apollo enrichment, contact reveal, vertical mapping, email generation, LinkedIn sequences. Runs locally from Claude Code. Triggers on "prep campaign", "generate emails", "build campaign", "outreach prep", "campaign for", "run campaign on".

  Self-containedInstructions only678 words
• gtm-contacts
  Needs a keyActs undeclared905 words
• gtm-deck
  Self-containedInstructions only435 words
• gtm-intake
  Reaches the webInstructions only331 words
• gtm-linkedin

  Optional LinkedIn enrichment skill — finds LinkedIn company pages, extracts employee count, and filters by headcount. Runs after gtm-prefilter, before gtm-research.

  Reaches the webActs undeclared324 words
• gtm-outreach
  Self-containedInstructions only706 words
• gtm-prefilter

  Fast homepage reachability check for 50k domains — no Firecrawl, no proxy, no LinkedIn. Marks domains as prefiltered or skip.

  Self-containedActs undeclared254 words
• gtm-research
  Self-containedInstructions only750 words
• gtm-sales-org
  Reaches the webInstructions only595 words
• gtm-segment
  Self-containedInstructions only700 words
• gtm-send
  Self-containedActs undeclared1,101 words
• gtm-signals
  Reaches the webInstructions only654 words
• context-building

  Build and maintain the Beton GTM context file — the single source of truth for all outbound campaigns. Captures product info, voice rules, ICP, win cases, proof library, campaign history, hypotheses, and DNC list. All other GTM skills read from this file. Supports four modes: create (new context), update (add sections), call-recording (extract signals from transcripts), feedback-loop (import campaign results). Triggers on: "build context", "update context", "company context", "ICP", "win cases", "proof points", "DNC list", "campaign history", "call recording", "feedback loop", "outbound context".

  Self-containedInstructions only522 words
• email-generation

  Generate cold outreach emails from a contact CSV and a self-contained prompt template built by email-prompt-building. Campaign-agnostic — no hardcoded product or voice. The prompt template contains all voice rules, research data, value prop, proof points, and personalization rules. This skill just runs it per row. Triggers on: "generate emails", "email generation", "run emails", "create emails", "write emails for campaign", "generate outreach".

  Reaches the webActs undeclared1,929 words
• email-prompt-building

  Generate self-contained email prompt templates for cold outreach campaigns. Reads from the Beton context file (voice, value prop, proof points) and campaign research (hypotheses) to produce a prompt that the email-generation skill runs per-row against a contact CSV. One prompt per campaign. Triggers on: "cold email", "outreach prompt", "email campaign", "new vertical email", "draft email prompt", "email sequence", "write emails".

  Self-containedInstructions only819 words
• gtm-hypothesis-scorer

  Score and rank all GTM hypotheses in the Beton Supabase DB using a RICE-based framework (Reach × Impact × Confidence). Outputs a ranked terminal table and CSV ready for campaign planning. Use when: asked to score hypotheses, rank experiments, find the best outreach angle, prioritize GTM campaigns, see RICE scores, or decide which segment to target first. Triggers on: "score hypotheses", "rank experiments", "best outreach angle", "RICE score", "prioritize campaigns", "which segment to target", "top hypotheses by score".

  Needs a keyActs undeclared242 words
• hypothesis-building

  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 and segmentation. Sits between context-building and email-prompt-building in the Beton GTM pipeline. Triggers on: "build hypotheses", "hypothesis set", "pain hypotheses", "define hypotheses", "what pain points", "campaign angles", "search angles", "refine hypotheses", "what verticals to target", "run on scored companies", "generate hypotheses from data".

  Self-containedInstructions only1,907 words
• list-segmentation

  Take a classified companies CSV (from Supabase) and a hypothesis set, then segment companies by hypothesis fit and assign tiers (1/2/3) based on data richness and signal strength. Outputs a tiered, segmented CSV ready for email-generation. Beton-specific: reads from Supabase export, not Extruct. Triggers on: "segment companies", "tier companies", "prioritize list", "segment and tier", "tiering", "which companies first", "who to email first".

  Self-containedInstructions only492 words