referral-program

When the user wants to plan, implement, or optimize referral program strategy. Also use when the user mentions "referral program," "referral marketing," "user referral," "refer-a-friend," "word-of-mouth growth," "referral rewards," "referral tracking," "referral code," "referral incentives," or "viral loop." For referral landing copy, use landing-page-generator.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A lean, information-dense strategy guide that consistently provides specific benchmarks, tool names, and a defined output format rather than generic marketing advice. Its weaknesses are minor: some duplicated and inferable content, a few vague directives, and no explicit validation step in the design workflow.

Suggestions

Consolidate the 'Placement' guidance, which appears in both Best Practices and Implementation, into one section.

Replace soft directives like 'audit referrals regularly' with concrete cadences and signals (e.g., 'review referral logs weekly for self-referral patterns: same IP/device/payment').

Add an explicit validation checkpoint in the Design Framework, such as 'confirm the reward budget stays within 10-30% of product price and per-user caps cover projected volume before finalizing the output.'

Dimension	Reasoning	Score
Conciseness	The body is table-driven and dense with non-obvious benchmarks ("3%-5% conversion," "CAC 50%-70% lower," "10%-30% of product price") that Claude cannot reliably know, but 'Placement' guidance is duplicated in Best Practices and Implementation, and the referral-vs-affiliate distinction partially restates what Claude already knows — matching anchor 4's 'minor instances that could be trimmed'.	4 / 5
Actionability	Concrete parameters throughout (tiered reward example of $10/$15/$20, 30-90 day attribution windows, named tools with use cases, a defined Output Format) give mostly executable guidance, but a few soft directives ('audit referrals regularly,' 'Use tool anti-fraud features') and the absence of any example output template leave minor gaps, matching anchor 4.	4 / 5
Workflow Clarity	The Initial Assessment → Design Framework (5 sequenced steps) → Output Format flow is clear and 'Monitor & optimize: ... A/B test rewards and flow' provides a feedback loop, but there are no explicit validation checkpoints (e.g., verifying the recommended program against budget/fraud constraints before output), matching anchor 4 rather than 5.	4 / 5
Progressive Disclosure	Well-organized single-file structure with clear section headers and no nested references, but at ~130 lines it exceeds the under-50-line simple-skill exception, and the detailed tool/reward tables plus the duplicated Placement guidance are content that could be split or trimmed — good structure with minor organization gaps, matching anchor 4.	4 / 5
	Total	16 / 20 Passed

Description

90%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-crafted description with comprehensive natural trigger terms, an explicit what+when structure, and a boundary delegation to a sibling skill. The only weakness is that the capability description is a single strategy-level deliverable expressed through three generic lifecycle verbs rather than multiple concrete, distinct actions.

Suggestions

Replace the generic lifecycle verbs with the skill's distinct concrete outputs (e.g., 'Design referral reward structures, choose tracking/attribution mechanisms, and select fraud-prevention measures for AI/SaaS products').

Dimension	Reasoning	Score
Specificity	The description names the domain and three actions ("plan, implement, or optimize referral program strategy"), but these are lifecycle synonyms for a single strategy deliverable rather than multiple distinct concrete capabilities, matching anchor 3 rather than anchor 4's list of separate specific actions.	3 / 5
Completeness	Both questions are answered explicitly: what ("plan, implement, or optimize referral program strategy") and when ("When the user wants to... Also use when the user mentions..."), with concrete trigger phrases — a textbook match for anchor 5.	5 / 5
Trigger Term Quality	Ten natural trigger phrases are listed ("referral program," "refer-a-friend," "word-of-mouth growth," "referral code," "viral loop"), covering comprehensive synonyms users would actually say.	5 / 5
Distinctiveness Conflict Risk	The referral niche has distinct triggers and the explicit boundary hand-off ("For referral landing copy, use landing-page-generator") removes the nearest conflict risk, matching the clear-niche anchor 5.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: kostja94/marketing-skills
Path: skills/channels/partnerships/referral-program/SKILL.md
Commit: 26cef34

Reviewed: 23 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.