SkillMachine
All skills

Lead Dossier — Multi-Source Account Research & Enrichment Pipeline

Report

From domain to verified lead dossier: research → enrich → dedupe → upload.

Live output preview

Input Format: Input FormatOutputWatch the Output: Watch the Output

A plan is required to view this content

Choose a plan to access input format, sample outputs, and live previews.

View Plans →

About the skill

What it does

Lead Dossier is a multi-source automation pipeline that turns scattered raw signal (a domain, or a target-persona definition) into a sales-ready, verified lead dossier. It bundles four workflows: (1) Account research — website title/description/body scraping + marketing-gap analysis, tech-stack detection via BuiltWith (CRM, marketing tools, enterprise signals), hiring signals and news/funding triggers, ending with a 3-5 sentence research brief. (2) Cascade enrichment — fills a prospect list with verified emails. (3) Full lead pipeline — source → verify → dedupe → upload, end to end. (4) Real-time enrichment — enriches inbound webhook/form/CRM-triggered leads.

When to use it

When you need a clean, verified lead list before an outbound campaign; when you want to brief an account deeply before a meeting; when enriching your CRM with technographic + intent signal; or when auto-enriching inbound form/voice-agent leads with context. Ideal for building ABM (account-based marketing) target lists while keeping bounce rates low.

Method / frameworks

The core logic is waterfall enrichment: an email passes through multiple providers in sequence; if a provider returns a verified result above the confidence threshold (typically 90%+), the cascade stops, otherwise it hands off to the next provider. In practice 3-4 providers is the optimum — the first handles most records, the second recovers 15-25%, the third another 8-12%. Verification uses SMTP ping + syntax checks; the target bounce rate is <3% (single-source is typically 8-15%). Lead scoring uses intent signals (hiring growth, funding, exec changes, technographic shifts); intent-prioritized accounts convert at ~21% vs ~8% for non-prioritized in published benchmarks. Safety rules are strict: never upload unverified leads, always dedupe, log everything, run idempotently, and sandbox+sanitize all inbound web content before processing.

How do I use this skill?

You don't "run" a skill — after installing it you just tell the agent your task (e.g. ask for the relevant job), and the skill kicks in by itself when its description matches.

Upload the lead-dossier.zip you downloaded as-is — no packaging needed, the format is already correct (folder at root).

  1. Open Settings → Customize → Skills
  2. Upload → select the lead-dossier.zip you downloaded
  3. Claude reads SKILL.md; the name + description appear. Ready ✅

Scripts run in Anthropic's code-execution environment (sandbox) — not on your machine.