agentleFS
link7373link7373/agentic-sales-marketing/.claude/skills/grow-referrals/SKILL.md

grow-referrals

Skill1 starsChanged 3 months agoMITView on GitHub

Turn customers into the growth engine — reviews, testimonials, referral asks, repeat-purchase flows, and the customer experience that powers word of mouth. Run after the first sales land; then as a standing program.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Handle complaints as marketing: Every complaint gets a fast, generous resolution — recovered complainers talk.

    line 20

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/grow-referrals — The Cheapest Growth Is Earned

Inputs: customer records (from knowledge/pipeline.md / order history), knowledge/offer.md, knowledge/business-context.md. Agents: campaign-manager runs the flows; brand-strategist shapes the experience; copywriter writes the asks; tools-operator automates. Method: knowledge/methods/referral-and-retention.md; knowledge/methods/persuasion-principles.md (reciprocity & commitment, within ethics).

Steps

  1. Audit the experience first. Word of mouth is earned by the experience, not extracted by asks. Walk the customer's journey from purchase to outcome: where does it exceed the promise, where merely meet it, where fall short? Fix the short-falls before amplifying anything — asking for reviews of a flawed experience buys public criticism.
  2. Design the delight moment. One deliberate above-expectation touch (a personal note, an unexpected extra, proactive help) placed where it's most felt. Cost-controlled, genuine, systematic.
  3. Time the asks. Map when the customer feels the value (first result, successful delivery, repeat use) — asks land there, not at random. Review ask, then referral ask, spaced; never both at once.
  4. Make asking effortless. Direct link, 2-line suggested text they can edit, one-tap paths. Referrals: give the customer something of value to give their friend (a genuine perk), which beats paying bounties for authenticity — incentives, where used, are disclosed per compliance.
  5. Automate the flows. Post-purchase sequence via /launch-campaign mechanics: delivery confirmation → onboarding/first-value help → value check-in → review ask → referral ask → repeat/replenish offer where the product supports it. Add the standing customer-marketing flows: win-back for lapsed customers, expansion nudges where a bigger tier genuinely fits (B2B), replenishment reminders (B2C consumables). B2B: case-study ask and introduction requests handled personally through deal-closer. 5b. Route the proof. Every testimonial, review, and case-study quote captured (permission noted) goes to knowledge/research/social-proof.md — the proof library that /create-content, /build-funnel, /launch-campaign, and /close-deal pull from. Proof that sits unrouted is proof wasted.
  6. Handle complaints as marketing. Every complaint gets a fast, generous resolution — recovered complainers talk. Route recurring complaint themes to the operator as product feedback.
  7. Track the engine. Reviews earned, referral-attributed sales ("how did you hear about us?"), repeat rate. Reviews are real and unincentivized-or-disclosed, always.

Before you start

  1. Required inputs: at least one real customer (in knowledge/pipeline.md or order history) — before the first sale, this skill has nothing true to amplify.
  2. Scan knowledge/decision-log.md for tags content, channel — the delight moment and incentives must fit prior budget decisions.
  3. Gate check: flows that email customers fall under the outbound gate (templates approved once); public review responses fall under publishing; incentives are money decisions and disclosed per compliance.

If things go wrong

  • Experience audit finds real shortfalls → fix first, amplify second; report the shortfalls to the operator as product feedback, not marketing failure.
  • A customer refuses or ignores the ask → once, gracefully; never re-ask a no.
  • Negative review lands → fast, generous, public response (operator approves the template once); the recovery is the marketing.

Outputs

Running post-sale and customer-marketing flows; a proof library (knowledge/research/social-proof.md) that compounds. Close with the report per templates/skill-report.md.

Writeback

Flows to knowledge/campaigns/YYYY-MM-<slug>.md; metrics to knowledge/results-history.md; experience fixes (tag: other) to knowledge/decision-log.md; testimonials (with permission noted) to knowledge/research/social-proof.md.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.