CtrlK
BlogDocsLog inGet started
Tessl Logo

referral-program

You are an expert in viral growth and referral marketing with access to referral program data and third-party tools. Your goal is to help design and optimize programs that turn customers into growth engines.

38

Quality

37%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/referral-program/SKILL.md

The canonical home for this skill is referral-program in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

38%Scale 1-5

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

This skill is a comprehensive but excessively verbose marketing guide that reads more like a textbook chapter than a skill file for Claude. It extensively covers referral and affiliate program concepts that Claude already knows from training data, adding very little novel or project-specific knowledge. The content would benefit enormously from being condensed to ~100 lines of truly unique guidance with references to separate files for templates, case studies, and tool comparisons.

Suggestions

Reduce content by 70-80% by removing explanations of concepts Claude already knows (what referral programs are, case studies of Dropbox/Uber, basic marketing definitions) and focus only on the decision frameworks, formulas, and checklists that provide unique procedural value.

Split email templates, outreach templates, tool comparisons, and case studies into separate bundle files referenced from the main SKILL.md to improve progressive disclosure.

Add validation checkpoints to the launch workflow — e.g., 'Test the complete referral flow end-to-end and verify tracking fires correctly before announcing to customers' with specific verification steps.

Make the skill more actionable by including concrete tool-specific implementation steps (e.g., actual API calls or configuration steps for at least one referral platform) rather than just listing tool names.

DimensionReasoningScore

Conciseness

Extremely verbose at ~500+ lines. Extensively explains concepts Claude already knows (what referral vs affiliate programs are, basic marketing concepts, what Dropbox's referral program was). The case studies, outreach templates, email sequences, and tool listings are all information Claude has in its training data. Very little here is novel or project-specific knowledge that Claude wouldn't already possess.

2 / 5

Actionability

Provides some concrete frameworks (K-factor formula, incentive sizing calculation, checklists) but most content is descriptive rather than executable. No actual code for implementation, no API examples for the tools mentioned, and the 'actionable' elements are mostly strategic advice and templates rather than concrete technical steps Claude could execute with tools.

3 / 5

Workflow Clarity

The launch checklist provides a reasonable sequence, and the referral loop diagram shows a clear process. However, there are no validation checkpoints or feedback loops in the workflows. The optimization section lists problems and fixes but doesn't sequence them into a diagnostic workflow. The 'Before Starting' section gathers context but doesn't clearly connect to decision points in the rest of the document.

3 / 5

Progressive Disclosure

All content is inlined in a single monolithic file with no bundle files. The tool comparisons, case studies, email templates, affiliate outreach templates, and detailed commission structures could easily be split into separate reference files. The 'Related Skills' section references other skills but the current file itself has no progressive disclosure structure — everything is dumped into one long document.

2 / 5

Total

10

/

20

Passed

Description

36%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.

This description is too vague and aspirational, reading more like a persona prompt ('You are an expert...') than a skill description. It lacks concrete actions, explicit trigger conditions, and uses second-person voice ('Your goal') rather than third-person. The referral marketing domain provides some focus, but the description needs significantly more specificity and a clear 'Use when...' clause.

Suggestions

Add a 'Use when...' clause with trigger terms like 'referral program', 'refer-a-friend', 'invite codes', 'referral rewards', 'viral loops'.

Replace vague language with concrete actions such as 'Designs referral reward structures, analyzes referral conversion funnels, configures invite flows, and tracks referral attribution'.

Rewrite in third person ('Designs and optimizes referral programs...') instead of the current persona-style framing ('You are an expert... Your goal is to help').

DimensionReasoningScore

Specificity

Names the domain (referral marketing, viral growth) but actions are vague — 'help design and optimize programs' is generic and doesn't list concrete actions like 'analyze referral conversion funnels', 'configure reward tiers', or 'generate referral links'.

2 / 5

Completeness

Has a vague 'what' (design and optimize referral programs) but no explicit 'when' clause or trigger guidance. The description never states when Claude should select this skill, which caps this dimension per the rubric guidelines.

2 / 5

Trigger Term Quality

Includes some relevant keywords like 'referral marketing', 'referral program', and 'viral growth', but misses natural user phrases like 'refer-a-friend', 'invite codes', 'referral links', 'word of mouth', or 'customer acquisition'.

3 / 5

Distinctiveness Conflict Risk

The referral marketing niche provides some distinctiveness, but the broad framing ('growth engines', 'viral growth') could overlap with general marketing, growth hacking, or customer acquisition skills.

3 / 5

Total

10

/

20

Passed

Validation

81%

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

Validation9 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (609 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

9

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
Reviewed

Table of Contents

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.