Skip to content
SkillScript-led1,064 tokens in use

sales-pipeline

Python scripts that score RB2B-identified site visitors, suppress and route them to Instantly, revive dead HubSpot deals and tune your ICP.

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

Install command as written in the repository's README

Skill label

measured from its files

What installing sales-pipeline costs

30tokens idle
1,064tokens 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: deal_resurrector.py, icp_learning_analyzer.py, rb2b_instantly_router.py, rb2b_suppression_pipeline.py, rb2b_webhook_ingest.py, trigger_prospector.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 →
Good
  • Frontmatter8/15
  • Structure9/25
  • Examples15/15
  • Output5/15
  • Size15/15
  • Resources10/15

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 12
  • File that was not read−5

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

    data/campaigns.json.example
  • Reads credentials−15

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

    deal_resurrector.py, line 39
  • Writes files−8

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

    deal_resurrector.py, line 141
  • Reaches the network−10

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

    icp_learning_analyzer.py, line 94

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

Sales Pipeline automates the path from an identified website visitor to a cold email campaign. A webhook server receives RB2B visits and scores intent from the pages viewed, a five-layer suppression check screens each contact, and a router classifies the lead and enrolls it in an Instantly campaign.

Three more scripts cover deal intelligence: a deal resurrector that scores closed-lost HubSpot deals and drafts revival emails, a trigger prospector that watches web signals through Brave Search, and an ICP learning analyzer that studies approve and reject decisions.

What You Get

  • A webhook server that scores visitor intent by page, with scores you edit for your own URLs
  • A five-layer suppression pipeline you can run on a single email address
  • A router that classifies leads, picks a campaign from a JSON file and enrolls them in Instantly
  • A three-layer deal resurrector with time decay, contact expansion and champion tracking, with a dry-run mode
  • A trigger prospector that looks for new hires, funding and agency searches
  • An ICP analyzer that recommends filter changes from approve and reject history

Common Use Cases

  • Turning anonymous visitor identification into reviewed cold outreach
  • Checking an address against suppression layers before any email goes out
  • Reviving closed-lost deals with drafted emails in a review queue
  • Finding companies showing buying signals in the last week

What Makes It Unique

It joins visitor identification, suppression, routing and deal revival in one package, and each script has a clear customization point such as intent scores, agency keywords, loss reason bonuses and search queries. Deal drafts land in a review queue and the resurrector has a dry-run flag.

Under The Hood

The scripts run as Python commands. They read HubSpot, Instantly and Brave Search keys and a Postgres connection string from environment variables, then call those services over the network. The webhook and router scripts start a local HTTP server on a port you choose, and some scripts write queue and data files. A preamble at the start runs the repository’s version check and telemetry setup scripts, which log usage locally and make remote reporting opt-in.

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