When the user wants to create, optimize, or analyze a referral program, affiliate program, or word-of-mouth strategy. Also use when the user mentions 'referral,' 'affiliate,' 'ambassador,' 'word of mouth,' 'viral loop,' 'refer a friend,' or 'partner program.' This skill covers program design, incentive structure, and growth optimization.
78
73%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./config/claude/skills/referral-program/SKILL.mdQuality
Discovery
89%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 is a well-structured description with strong trigger term coverage and clear completeness, explicitly stating both what the skill does and when to use it. The main weakness is that the capability descriptions are somewhat high-level ('create, optimize, or analyze') rather than listing granular, concrete actions. Overall it would serve well for skill selection among a large set of skills.
Suggestions
Add more specific concrete actions to improve specificity, e.g., 'design tiered reward structures, calculate referral economics, draft referral messaging, benchmark conversion rates' instead of the general 'create, optimize, or analyze.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (referral/affiliate programs) and mentions some actions ('create, optimize, or analyze') along with areas covered ('program design, incentive structure, and growth optimization'), but these are somewhat high-level rather than listing multiple concrete, specific actions like 'design tiered reward structures, calculate referral conversion rates, draft referral email templates.' | 2 / 3 |
Completeness | Clearly answers both 'what' (create, optimize, or analyze referral/affiliate programs; covers program design, incentive structure, growth optimization) and 'when' (explicit 'Use when' clause with specific trigger terms and scenarios). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'referral,' 'affiliate,' 'ambassador,' 'word of mouth,' 'viral loop,' 'refer a friend,' 'partner program.' These are natural phrases a user would actually use when seeking help with this topic. | 3 / 3 |
Distinctiveness Conflict Risk | The description carves out a clear niche around referral and affiliate programs with distinct trigger terms like 'viral loop,' 'refer a friend,' and 'ambassador' that are unlikely to conflict with other skills such as general marketing or growth strategy skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill with good progressive disclosure and clear organization, but it suffers from moderate verbosity—explaining concepts Claude already understands (referral vs affiliate distinctions, general characteristics) and including generic statistics. Actionability is decent with checklists and email templates but lacks truly concrete, executable deliverables. The workflow could benefit from explicit validation checkpoints.
Suggestions
Remove the 'Referral vs. Affiliate' characteristics section—Claude already knows these distinctions. Replace with a brief decision heuristic (e.g., 'Use referral if LTV < $X and natural WOM exists; use affiliate if reaching new audiences').
Add concrete output examples: show a complete incentive structure document, a filled-out referral program brief, or a specific commission tier table rather than generic placeholders.
Add validation checkpoints to the launch checklist workflow, e.g., 'Test complete referral flow end-to-end and verify attribution tracking before announcing to customers.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary explanatory content (e.g., explaining what referral vs affiliate programs are, listing characteristics Claude already knows, 'typical findings' statistics that are generic). The 'Referral vs. Affiliate' section and some context-gathering questions add bulk without adding unique actionable value. However, it's not egregiously verbose. | 2 / 3 |
Actionability | The skill provides structured guidance with checklists, tables, and email templates, which are somewhat actionable. However, it lacks concrete executable examples—the email template is a skeleton with placeholders, the referral loop is a simple text diagram, and much of the content is strategic advice rather than specific, copy-paste-ready deliverables. It describes what to do more than showing exactly how. | 2 / 3 |
Workflow Clarity | The launch checklist provides a clear sequence, and the 3-step referral program design process is well-ordered. However, there are no validation checkpoints or feedback loops—no 'verify this before proceeding' steps. For a program involving incentive structures and fraud prevention, the lack of explicit validation gates (e.g., test the flow before announcing) is a gap, though the checklist partially addresses sequencing. | 2 / 3 |
Progressive Disclosure | The skill effectively uses one-level-deep references to separate files (references/program-examples.md, references/affiliate-programs.md, tools integrations) while keeping the overview concise. Navigation is clear with well-signaled links, related skills are listed, and the tool integration table provides a clean discovery mechanism. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
2c6f6e8
Table of Contents
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.