Skip to content
SkillModel-led2,122 tokens in use

offers

Improves the offer itself: scores the value equation, audits six offer components, and designs guarantees, bonus stacks and real scarcity for services, courses, coaching and high-ticket B2B.

61,712 stars on the repository MIT Licensecoreyhaines31/marketingskills · skills/offers
npx skills add coreyhaines31/marketingskills --skill offers
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing offers costs

101tokens idle
2,122tokens in use
18,372tokens, 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 Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

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
  • Frontmatter12/15
  • Structure19/25
  • Examples12/15
  • Output10/15
  • Size15/15
  • Resources15/15

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 →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity100
  • Maintenance100
  • Community76
  • Maturity32
  • Momentum40

offers helps an agent work on the offer underneath the sales page. It scores four levers of the value equation, checks a six-part offer anatomy, and fixes one weak component per iteration, such as a missing guarantee, bonus or deadline.

Eight references cover the equation, anatomy, guarantee types, bonus stacking, scarcity, format playbooks by business type, SaaS offers and worked examples.

What You Get

  • A value equation score for the four levers and the one that binds
  • An audit of core deliverable, bonus stack, guarantee, scarcity or urgency, name and price structure
  • A guarantee chosen from eight types with when each works or backfires
  • Bonus and scarcity drafts based on real constraints such as capacity, cohorts and founding pricing
  • A lift projection that multiplies component gains and recommends a test

Common Use Cases

  • Working out why a course or coaching offer is not selling
  • Adding a guarantee to a service package
  • Replacing a discount with a stronger offer for a SaaS product
  • Creating a real deadline for a cohort or founding-member price
  • Naming and packaging a productized service

What Makes It Unique

It treats the offer as the thing to fix before the copy. It limits its own tactics: it rules out fake countdowns, inflated bonus values and discounting to acquire customers. It includes a banned vocabulary list for offer language and tells the agent to project only modest lifts per change.

Under The Hood

The SKILL.md and eight references are loaded as context, with each reference read only when its topic comes up. It ships no scripts and runs no commands. The agent reads the product marketing context file in your project when it exists. It reaches no services and writes no files. Output is a written diagnosis, drafted offer components and a suggested test.

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