Skip to content
SkillScript-led1,487 tokens in use

Lead Dossier

Researches accounts, finds missing emails and runs a source, verify, dedupe and upload pipeline for B2B leads, with Python scripts behind each step.

3,862 stars on the repository MIT Licenseericosiu/ai-marketing-skills · lead-dossier
npx skills add ericosiu/ai-marketing-skills -s lead-dossier
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Lead Dossier costs

28tokens idle
1,487tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Script-led

Script-ledMixedModel-led

Most of this skill is scripts, so it behaves much the same whichever model runs it.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: scripts/account-researcher.py, scripts/cascade-enricher.py, scripts/lead-enricher.py, scripts/lead-pipeline.py.

Touches

shelldetectednetworkdetectedwrites filesdetectedcredentialsdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter8/15
  • Structure22/25
  • Examples15/15
  • Output15/15
  • Size15/15
  • Resources8/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Fair
  • File that was not read−15

    a file the skill ships that was not read, so what it does is unknown

    .env.example
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 55
  • Reads credentials−15

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 120
  • Reaches the network−10

    does this on the machine, and the frontmatter does not say so

    scripts/account-researcher.py, line 16
  • Writes files−8

    does this on the machine, and the frontmatter does not say so

    scripts/account-researcher.py, line 261

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity88
  • Maintenance44
  • Community56
  • Maturity28
  • Momentum40

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.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers