integrate-revenuecat
End-to-end RevenueCat integration — sets up the dashboard side via the RevenueCat MCP (project, app, public API key) and installs/configures the Purchases SDK in the app. Use when the user asks to add RevenueCat, integrate Purchases, install the RevenueCat SDK, set up a RevenueCat API key, configure Purchases on launch, or set up a brand new RevenueCat integration on iOS, Android, Kotlin Multiplatform, Flutter, or React Native.
68
81%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%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 an excellent skill description that clearly communicates what the skill does (end-to-end RevenueCat integration including dashboard and SDK setup), when to use it (with a comprehensive 'Use when...' clause), and covers multiple natural trigger terms and platform variations. It is highly specific, complete, and distinctive with minimal risk of conflicting with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'sets up the dashboard side via the RevenueCat MCP (project, app, public API key)' and 'installs/configures the Purchases SDK in the app'. These are clearly defined, actionable steps. | 3 / 3 |
Completeness | Clearly answers both 'what' (end-to-end RevenueCat integration with dashboard setup and SDK installation) and 'when' with an explicit 'Use when...' clause listing multiple trigger scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'add RevenueCat', 'integrate Purchases', 'install the RevenueCat SDK', 'set up a RevenueCat API key', 'configure Purchases on launch', plus platform names (iOS, Android, Kotlin Multiplatform, Flutter, React Native). These are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a specific third-party service (RevenueCat) with specific tooling (RevenueCat MCP, Purchases SDK). Very unlikely to conflict with other skills due to the narrow, well-defined niche. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%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 integration skill with a clear end-to-end workflow, good conditional branching, and explicit verification steps. Its main weaknesses are the absence of the referenced platform files (which contain the actual executable code), some verbosity in sections like store-side setup and shared concepts that could be trimmed or externalized, and the lack of inline code examples for the core configure step.
Suggestions
Include the referenced platform files (platforms/ios.md, platforms/android.md, etc.) in the bundle, or inline at least one minimal configure snippet so the skill is actionable without external files.
Move Section 5b (Store-side setup) to a separate reference file like 'store-setup.md' to reduce the main skill's length and improve progressive disclosure.
Trim Section 3b (Shared concepts) — most of these points (anonymous users, configure once, debug logging) are better placed in the platform-specific files where they can include concrete code.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some unnecessary explanation (e.g., explaining what bundle IDs are, what anonymous users are, general concepts Claude already knows). Section 5b on store-side setup is quite verbose and could be a separate reference file. The 'Shared concepts' section explains things like 'configure once per app launch' that are better left to the platform files. | 2 / 3 |
Actionability | The skill provides a clear procedural flow with specific MCP tool names (list-projects, create-app, list-public-api-keys) and a concrete platform detection algorithm. However, it lacks executable code examples directly in the body — all actual configure snippets and install commands are deferred to platform files which are not provided. The verification section describes what to check but doesn't give concrete commands or log patterns. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced across 5 numbered sections with logical ordering (gather info → dashboard setup → SDK install → verify → next steps). It includes explicit validation in Section 4 (build must succeed, configuration banner must appear, no auth errors), conditional branching (jump to Section 3 if project exists, hand off to another skill if no project), and clear decision points throughout. | 3 / 3 |
Progressive Disclosure | The skill references platform-specific files (platforms/ios.md, platforms/android.md, etc.) and other skills (create-revenuecat-project, revenuecat-paywall, etc.) which is good structure. However, no bundle files are provided, so the referenced platform files don't actually exist. Additionally, Section 5b (store-side setup) is lengthy inline content that would be better as a separate reference file, and the skill itself is quite long for an overview document. | 2 / 3 |
Total | 9 / 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.