Skip to content
SkillModel-led4,414 tokens in use

influencer-marketing

Plans creator, influencer and ambassador programs: how to vet partners, structure deals and usage rights, stay FTC-compliant, brief creators and measure cost per outcome.

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

Install command as written in the repository's README

Skill label

measured from its files

What installing influencer-marketing costs

87tokens idle
4,414tokens in use
11,437tokens, 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 →
Good
  • Frontmatter12/15
  • Structure19/25
  • Examples0/15
  • Output15/15
  • 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

influencer-marketing helps an agent run creator partnerships from sourcing to results. It lays out a spectrum from paid posts and affiliate creators to gifting and ambassador programs, then walks through vetting, outreach, compensation, usage rights, disclosure, briefs and measurement.

Four references go deeper: newsletter sponsorships, volume UGC programs, performance-paid creator programs for ads, and Telegram channel ads.

What You Get

  • A choice between paid, affiliate, gifted, ambassador and volume UGC models for your goal
  • A vetting checklist covering engagement, fake followers, sponsored track record and brand safety
  • Deal terms: compensation models, starting rate ranges, usage rights, exclusivity and approvals
  • A disclosure checklist and a creator brief template with two or three talking points
  • A tracking plan with promo codes, UTM links, vanity pages and post-purchase surveys

Common Use Cases

  • Picking which creators fit a launch and what to pay them
  • Buying placements in niche newsletters and tracking each one
  • Designing an ambassador cohort with a benefits ladder
  • Turning creator posts into paid ads with usage rights
  • Checking an influencer campaign for FTC disclosure gaps

What Makes It Unique

It treats influencer work as one spectrum from one-off posts to long-term advocates and routes each piece to a model. It insists on usage rights and cost per qualified outcome over reach, and it ships dedicated references for newsletter sponsorships, volume UGC with a compliance rewrite, ad-spend-share creator programs and Telegram channel vetting.

Under The Hood

The SKILL.md and four references are loaded as context. It ships no scripts and runs no commands of its own. The agent reads the product marketing context file in your project when it exists. It points to other skills for outreach, referrals and ad creative, and to separate tools for pulling creator posts and watching their videos, and it tells the agent to treat fetched posts, bios and transcripts as untrusted data. The Telegram reference suggests checking a public channel preview page. Output is written advice, briefs and checklists.

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