Skip to content
SkillScript-led1,720 tokens in use

Outbound Engine

Audits an Instantly cold email setup, rewrites sequences until a ten-expert panel scores them 90, and bundles scripts for lead sourcing and competitor tracking.

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

Install command as written in the repository's README

Skill label

measured from its files

What installing Outbound Engine costs

25tokens idle
1,720tokens in use
5,634tokens, 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: scripts/cold-outbound-sender.py, scripts/competitive-monitor.py, scripts/cross-signal-detector.py, scripts/instantly-audit.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 →
Good
  • Frontmatter8/15
  • Structure19/25
  • Examples12/15
  • 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 →
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 11
  • Writes files−8

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

    scripts/cold-outbound-sender.py, line 64
  • Reads credentials−15

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

    scripts/cold-outbound-sender.py, line 158
  • Reaches the network−10

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

    scripts/competitive-monitor.py, line 24

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

Outbound Engine is a cold outbound optimizer. It asks whether the user has an Instantly account, audits campaigns, sending accounts and warmup scores through the Instantly API, collects the ideal customer profile and offer, and then scores draft email copy with a ten-expert panel until it reaches 90 out of 100.

The result is a strategy document with every scoring round, final copy in Instantly format, capacity math and stop and start lists. Nothing is pushed to Instantly without explicit approval.

What You Get

  • An infrastructure report on campaigns, sending accounts, warmup scores and which accounts are ready to send
  • A confirmed ideal customer profile with an anti-profile and a one-sentence offer
  • Every scoring round with a score per panelist, the top weaknesses and the revised copy
  • A strategy document with final email copy, an implementation plan, capacity math, weekly metric targets and STOP and START lists
  • Optional scripts for lead sourcing, competitor change reports and cross-source signal detection

Common Use Cases

  • Auditing an existing Instantly setup to find what to stop and what to start
  • Writing a first cold email sequence for a new offer and testing it against a panel
  • Estimating how many emails and replies a set of warmed accounts can produce each month

What Makes It Unique

The score target of 90 is a hard gate, and every round stays in the final document so the reasoning is visible. Accounts are flagged as not ready when warmup is under 80 or under 14 days, and capacity is worked out from ready accounts only. A human review gate sits before any write to Instantly.

Under The Hood

The skill holds instructions, four reference files and five Python scripts. At start it runs the repository’s version check and telemetry helper through the shell and says usage is logged locally with remote telemetry opt-in. The audit script calls the Instantly API with a key the user supplies. The lead pipeline calls people search, email validation and campaign APIs. The competitor monitor fetches competitor pricing and blog pages over HTTP and keeps snapshots on disk. The signal detector reads agent output files in a data folder. The sender script sends email by SMTP or by a command line mail tool using credentials from environment variables, and it keeps a send history file with a daily cap. The agent writes the strategy document, so it writes files or a document too.

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