create-revenuecat-project
Set up a complete RevenueCat project from scratch — creates apps, products, entitlements, offerings, and packages in the correct order.
80
72%
Does it follow best practices?
Impact
90%
1.32xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./revenuecat/skills/create-revenuecat-project/SKILL.mdQuality
Discovery
67%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description is strong in specificity and distinctiveness, clearly naming the RevenueCat platform and listing the concrete entities it creates. However, it lacks an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill, and it could benefit from additional natural trigger terms related to subscriptions and monetization.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to set up a new RevenueCat project, configure in-app purchases, or initialize subscription infrastructure.'
Include additional natural trigger terms users might say, such as 'subscriptions', 'in-app purchases', 'paywall', 'monetization', or 'IAP setup'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: creates apps, products, entitlements, offerings, and packages. Also specifies 'in the correct order' and 'from scratch', which add meaningful detail about the capability. | 3 / 3 |
Completeness | Clearly answers 'what' (creates apps, products, entitlements, offerings, packages in RevenueCat) but lacks an explicit 'Use when...' clause. The 'when' is only implied by 'from scratch' and 'set up'. This caps the score at 2 per the rubric guidelines. | 2 / 3 |
Trigger Term Quality | Includes good domain-specific terms like 'RevenueCat', 'apps', 'products', 'entitlements', 'offerings', 'packages', but misses common user variations like 'in-app purchases', 'subscriptions', 'paywall', 'monetization', or 'IAP' that users might naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | RevenueCat is a very specific platform, and the description targets a clear niche — initial project setup with specific RevenueCat entities. This is highly unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
77%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, actionable skill that clearly guides Claude through a multi-step RevenueCat project setup with specific tool names, parameter examples, and a logical dependency-aware ordering. The workflow clarity is strong with good error handling and conditional branching. Minor improvements could be made in conciseness by trimming explanatory asides and in progressive disclosure by referencing external docs for advanced topics.
Suggestions
Trim explanatory parentheticals like '(rc_billing is RevenueCat's own web billing engine...)' — Claude can explain this to users if asked without it being in the skill.
Consider adding a bundle file for advanced configuration scenarios (e.g., store credential setup, SDK integration patterns) and reference it from the 'Next Steps' section.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary explanation (e.g., explaining what rc_billing is, noting API keys are public). The discovery phase questions could be slightly tighter, but overall it respects Claude's intelligence reasonably well. | 2 / 3 |
Actionability | Provides specific MCP tool names for every step, concrete examples of parameters (lookup_key: 'default', $rc_monthly, $rc_annual), bundle ID formats, and a complete output template. Each step is directly executable with the named tools. | 3 / 3 |
Workflow Clarity | The three-phase workflow is clearly sequenced with explicit dependency ordering noted ('Execute in this order — dependencies matter'). Steps are numbered, conditional logic is provided (e.g., existing app store setup vs test_store), and error handling includes a feedback loop (report, suggest fix, retry or skip, continue). | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear phases and sections, but everything is in a single file with no bundle files for supporting content. The summary template and error handling could potentially be split out, and there are no references to external documentation for advanced configuration. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- RevenueCat/rc-claude-code-plugin
- Commit
407e465
- 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.