skillZs
★ LIVE SKILL TAGS ★
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
※ REAL INSTALL DATA ※
← back to all skills
victor-shulga/outbound-engine-skills61 installs

icp-validation

Use when asked to validate a company against ICP criteria, score fit, or check if a company is worth targeting

How do I install this agent skill?

npx skills add https://github.com/victor-shulga/outbound-engine-skills --skill icp-validation
view source ↗

Is this agent skill safe to install?

  • Gen Agent Trust Hubpass

    The skill is designed for company validation and ICP scoring. It poses a low risk of indirect prompt injection because it fetches and processes content from untrusted external websites and LinkedIn profiles.

  • Socketpass

    No alerts

  • Snykwarn

    Risk: MEDIUM · 1 issue

What does this agent skill do?

ICP Validation

Validate a company against defined ICP criteria and return a scored fit verdict.

Required tools

Install these before running the skill. It still runs without the ones marked Required, but the result gets noticeably worse: size and role fit are scored from the website alone, so headcount, open roles and the presence of the target persona are guesses.

ToolUsed forRequired?Without it
Firecrawl (MCP)pulling the company website: product type, industry, team size hints, tech signalsRequiredyou paste the site text; signals on deeper pages are missed
AI Ark, Icypeas or MoltSets (MCP)headcount, leadership and whether the target persona exists at the companyRequiredsize and role fit fall back to public signals only and are flagged
ApifyLinkedIn company page: recent hires, open roles, recent posts for the signal scoreRecommendedsignal fit relies on the website and search only
CRM (Twenty, HubSpot)checking whether the company is already a client, partner or vendorRecommendedthe «already ours» skip reason cannot be checked

Alternatives: Exa (MCP) can stand in for Firecrawl.

Inputs to provide:

  • Company name or website URL
  • ICP definition (provide inline or reference your ICP file)

Process

  1. Pull the company's website and scan for: team size indicators, tech stack signals, product type, industry, and growth stage
  2. Check LinkedIn via MCP for: headcount, recent hires, open roles, and leadership profile
  3. Score fit against each ICP dimension (1-3 per dimension):
    • Segment fit: does the company match the target segment?
    • Size fit: does headcount/revenue match the ICP range?
    • Signal fit: is there an active reason they'd respond now?
    • Role fit: is the target persona present and reachable?
  4. Return a one-line verdict + reasoning

Terms and plain-language output

<!-- glossary:start terms=fit-score,buying-signal,disqualifier-rings,account-tier,sequence -->

Rules for every document a client or their team will read (review, roast, canvas, offer cards, instruction):

  1. Open with «Словник цього документа»: only the terms that actually appear in it, at most 10, each as «термін: що це простими словами». Like the definitions section of a contract.
  2. No internal codes or letter scales in the text (A/B/C, D L T E, BLEND numbers without words, Own/Shared/Generic, Z1.4, GATE 2.5, T1–T6). Write the meaning instead: «є цифра з клієнтом», not «A».
  3. Use the plain form from the table below. English stays only for tool names and for copy that ships in English (promises, hooks, subject lines). If the document is in another language, translate the plain form, never the internal term.
  4. Do not score what cannot exist yet. A block that depends on work not done (signal catalog, case studies, a previous step) gets «пропущено: спершу потрібно <що саме>», not a score.
  5. Every section of a review opens with one concrete action («до наступного дзвінка: …»), then at most five lines of why. No paragraph that only restates the framework.
Internal term (this skill)Write for the readerWhat it means
ICP fit, services fit, prospect score, prospect profileоцінка відповідності профілюБали за те, чи компанія з вашої ніші і чи їй бракує саме вашої послуги; рахуємо ще до першого контакту.
buying signalознака готовності купуватифакт про компанію, після якого розмова про вашу послугу доречна саме зараз.
negative ICP, anti-ICP, rings 1–4фільтри відсівуЧотири перевірки по черзі: модель бізнесу, конкурент, розмір і країна, вже наш клієнт чи партнер; кожна відсіяна компанія має причину.
Tier 1 / Tier 2 / Tier 3, tierтір: група компаній за розміром і чекомусередині однієї ніші ділимо компанії за розміром і можливим чеком; від тіру залежить офер і скільки уваги даємо
sequences and templatesланцюжки листів і шаблонисерія з кількох листів чи повідомлень одному проспекту з паузами між ними.
<!-- glossary:end -->

Output format

Company: [Name]
Fit score: [X/12]
Verdict: [Strong fit / Marginal fit / Not a fit]

Segment: [score] — [one line reason]
Size: [score] — [one line reason]
Signal: [score] — [one line reason]
Role: [score] — [one line reason]
Why a buyer, not a competitor: [one line — what they sell and to whom, and why that makes them a buyer of your offer]

Recommended action: [write first, personal sequence / write later, standard sequence / skip] (in words, no tier numbers)
Skip reason: [business model does not buy this / competitor / size or country outside the range / already a client, partner or vendor] (in words, no ring numbers) — [one line]

Notes

  • If ICP isn't defined, ask for it before proceeding
  • If LinkedIn data is unavailable via MCP, flag it and use public signals only
  • "Marginal fit" means worth a Tier 2 sequence, not skip

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/victor-shulga/outbound-engine-skills/icp-validation">View icp-validation on skillZs</a>