referral-program
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 skill 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—terms like 'program design' and 'growth optimization' could be more concrete with specific deliverables or actions. Overall, it would perform well in a multi-skill selection scenario.
Suggestions
Replace high-level phrases like 'program design, incentive structure, and growth optimization' with more concrete actions such as 'design tiered reward structures, model referral economics, draft referral messaging, and track viral coefficients.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (referral/affiliate programs) and mentions some actions like 'create, optimize, or analyze' and topics like 'program design, incentive structure, and growth optimization,' but these are somewhat high-level rather than listing multiple concrete, specific actions (e.g., 'design tiered reward structures, calculate referral conversion rates, draft referral email templates'). | 2 / 3 |
Completeness | The description clearly answers both 'what' (create, optimize, or analyze referral/affiliate programs, covering program design, incentive structure, and growth optimization) and 'when' (explicit trigger clause with 'Also use when the user mentions...' listing specific keywords). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'referral,' 'affiliate,' 'ambassador,' 'word of mouth,' 'viral loop,' 'refer a friend,' 'partner program.' These are terms users would naturally use when seeking help with this type of program. | 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 moderately well-structured skill that serves as a reasonable overview of referral and affiliate program design. Its main strengths are progressive disclosure with clear references to detailed files and a comprehensive launch checklist. Its weaknesses are verbosity in explaining concepts Claude already understands, lack of truly concrete/executable guidance, and missing validation checkpoints in the workflow.
Suggestions
Trim the 'Referral vs. Affiliate' section significantly—Claude knows these distinctions. Replace with a brief decision matrix (e.g., 'Use referral if X, affiliate if Y').
Add concrete, copy-paste-ready examples: specific tool configuration snippets (e.g., Rewardful setup), specific incentive calculations (e.g., 'If LTV=$500, set reward at 10-20% = $50-100'), and a complete sample referral page wireframe.
Add explicit validation gates to the launch checklist, e.g., 'Test complete flow end-to-end and verify: reward triggers correctly, attribution tracks, fraud rules block test abuse case—only then proceed to launch.'
| 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, the optimization advice is generic ('simplify to one click'), and there's no specific code, configuration, or tool-specific implementation steps. It describes rather than instructs in many places. | 2 / 3 |
Workflow Clarity | The launch checklist provides a clear sequence with before/during/after phases, and the referral loop outlines steps. However, there are no explicit validation checkpoints or feedback loops—no 'verify this before proceeding' gates. The optimization section lists things to test but doesn't sequence them into a clear iterative workflow. | 2 / 3 |
Progressive Disclosure | The skill effectively uses one-level-deep references to separate files (references/program-examples.md, references/affiliate-programs.md, tools registry, individual tool guides). The main content serves as an overview with clear signposting to detailed materials. Navigation is well-organized with clear section headers. | 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 | |
- Repository
- freekmurze/dotfiles
- Commit
05d40bb
- 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.