Name: referral-program
Rating: 65.60000000000001 (1 reviews)
Author: alirezarezvani

referral-program

When the user wants to design, launch, or optimize a referral or affiliate program. Use when they mention 'referral program,' 'affiliate program,' 'word of mouth,' 'refer a friend,' 'incentive program,' 'customer referrals,' 'brand ambassador,' 'partner program,' 'referral link,' or 'growth through referrals.' Covers program mechanics, incentive design, and optimization — not just the idea of referrals but the actual system.

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./.gemini/skills/referral-program/SKILL.md

The canonical home for this skill is referral-program in alirezarezvani/claude-skills

Quality

Content

63%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.

The body is rich with concrete, numbers-grounded domain guidance and clear multi-mode workflows, but it is held back by persona/prose padding and by three referenced bundle files that are not actually present, breaking both progressive disclosure and one executable action.

Suggestions

Either add the missing scripts/referral_roi_calculator.py, references/measurement-framework.md, and references/program-mechanics.md to the bundle, or remove the inline references and inline the essential content directly in SKILL.md.

Trim the persona preamble and motivational asides (e.g. 'programs that collect dust', 'Don't optimize randomly. Diagnose first, then pull the right lever.') to recover tokens without losing actionable guidance.

Add an explicit validation/checklist step to the Mode 1 design workflow (e.g. 'Confirm reward sizing against LTV/CAC before finalizing the spec') to match the checkpoint quality of Mode 2 and the affiliate checklist.

Dimension	Reasoning	Score
Conciseness	The dense benchmark/sizing tables and formulas are token-efficient, but the persona preamble ('You are a growth engineer... programs that collect dust') and motivational asides ('Don't optimize randomly. Diagnose first...') are padding that could be trimmed.	3 / 5
Actionability	Highly concrete guidance — specific benchmarks ('>40%', '15-25%'), sizing rules ('≥10% of first month's value', 'cap at 30%'), tiered reward examples, and metric formulas — but 'Run scripts/referral_roi_calculator.py' points to a script that is not in the bundle, a minor executability gap.	4 / 5
Workflow Clarity	Three modes each have clear numbered sequences, Mode 2 includes a measure-before-next-lever checkpoint, and the affiliate section has a launch checklist; the primary design mode (Mode 1) is linear with no validation checkpoint, a minor gap.	4 / 5
Progressive Disclosure	Sections are well-organized and references are clearly signaled with descriptive context, but all three referenced files (scripts/referral_roi_calculator.py, references/measurement-framework.md, references/program-mechanics.md) do not exist in the bundle, so the one-level-deep navigation is broken rather than merely minor.	3 / 5
	Total	14 / 20 Passed

Description

95%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 strong, well-structured description that clearly states capabilities, fires on a comprehensive set of natural trigger phrases, and explicitly bounds when to use it. The only minor weakness is that the named actions lean slightly abstract ('program mechanics, incentive design') rather than fully granular.

Dimension	Reasoning	Score
Specificity	Names several concrete actions ('design, launch, or optimize', 'program mechanics, incentive design, and optimization') in third person, with only minor abstraction in the domain-level terms preventing a perfect 5.	4 / 5
Completeness	Explicitly answers both what ('design, launch, or optimize a referral or affiliate program' with coverage of mechanics/incentives/optimization) and when (an explicit 'Use when they mention...' clause with concrete trigger phrases).	5 / 5
Trigger Term Quality	Comprehensive list of natural phrases users would actually say — 'referral program', 'refer a friend', 'word of mouth', 'brand ambassador', 'partner program' — covering synonyms and common variations.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (referral/affiliate program systems) with distinct, domain-specific triggers and minimal overlap with adjacent marketing skills.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 missing	Warning
referenced_paths_exist	Referenced path issues: 5 missing	Warning

	Total	14 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/referral-program/SKILL.md
Commit: 19392f7

Reviewed: ~3 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.