Lead Dossier gives an agent four workflows for B2B prospecting: account research from a company domain, a cascade that fills in missing emails, a full lead pipeline that sources, verifies, deduplicates and uploads to a campaign tool, and a real-time enricher for inbound leads.
Each workflow runs a Python script that reads API keys from environment variables, caches or logs its results as JSON, and supports a dry run.
What You Get
- A structured JSON dossier per account with website analysis, tech stack, hiring and news prompts, and a short research brief
- A prospect list where each row is tagged with where its email came from, or marked LinkedIn-only or no-contact
- A lead pipeline that pulls people from a search API, verifies each email, removes duplicates and uploads the rest to a campaign
- An enriched lead card for each inbound form, call or CRM lead
- A JSON run log for every pipeline run
Common Use Cases
- Researching a target company before a cold outreach sequence
- Building a verified list of VPs of marketing in a given industry and size band and loading it into a campaign
- Enriching form submissions with CRM data and account research the moment they arrive
What Makes It Unique
The skill covers the whole path from a search filter to uploaded leads in one place, with explicit safety rules: never upload an unverified email, always deduplicate against the campaign tool and an exclusion file, log every run and support a dry run that stops before upload. Endpoints are set by environment variables, so the same scripts work with different providers.
Under The Hood
The agent runs Python scripts from the skill’s scripts folder through the shell. The account researcher fetches the target’s homepage over HTTP and calls the BuiltWith API for tech detection, and writes a cache file per domain. The lead pipeline calls a people search API, an email validation API and a campaign tool API, sends lead records to that campaign tool, and writes JSON run logs and intermediate files to disk. The enrichers query a CRM over its API and write result and log files. All of these need API keys read from environment variables or a config file the user creates. The skill tells the agent to scan inbound web content before processing.