Skip to content
SkillScript-led2,065 tokens in use

revenue-intelligence

Three Python tools that pull insight from sales call transcripts, tie content to closed revenue and build multi-source client reports.

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

Install command as written in the repository's README

Skill label

measured from its files

What installing revenue-intelligence costs

27tokens idle
2,065tokens in use
2,092tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. 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: client_report_generator.py, gong_insight_pipeline.py, revenue_attribution.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
  • Structure25/25
  • Examples15/15
  • Output10/15
  • Size15/15
  • Resources12/15

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 →
Good
  • Runs shell commands−5

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

    SKILL.md, line 12
  • Reaches the network−10

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

    SKILL.md, line 217
  • Reads credentials−15

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

    client_report_generator.py, line 35
  • Writes files−8

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

    client_report_generator.py, line 1001

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

Revenue Intelligence bundles a Gong insight pipeline, a revenue attribution mapper and a client report generator. The pipeline extracts objections, buying signals, competitor mentions and pricing talk from call transcripts. The mapper joins GA4 and HubSpot data to show which content drove deals. The report generator combines GA4, HubSpot, Ahrefs and Gong into one client deliverable.

The skill also sets a feedback loop: define a baseline window and a primary metric before a change, then read the result back before promoting it.

What You Get

  • Objections sorted into pricing, timing, competition, authority and need
  • Buying signals, competitor mentions and pricing discussions from each call
  • Content topic ideas from recurring objections and follow-up drafts for outbound sequences
  • Content ROI reports with revenue per piece, cost per acquisition by content type and funnel gaps
  • Client reports with traffic, pipeline, SEO and call quality sections
  • A readback template with baseline window, candidate window, metric winner, caveats and rollback rule

Common Use Cases

  • Weekly review of what prospects objected to on recent sales calls
  • Monthly proof of which blog posts, videos and podcasts led to closed deals
  • Producing a monthly client report from GA4, HubSpot, Ahrefs and Gong
  • Checking whether a change to outbound or content raised reply or meeting rates

What Makes It Unique

It links call transcripts, web analytics and CRM data in one skill, so an objection heard on a call can become a content topic and the resulting content can be traced to revenue. The feedback loop section requires a primary metric chosen before looking at results.

Under The Hood

The scripts run as Python commands and read credentials from environment variables for Gong, HubSpot, GA4 and optionally Ahrefs. They call those services over the network, read transcript files from disk and write report files to an output directory. 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. Dependencies are installed with pip.

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