revenuecat-troubleshoot
Diagnose and resolve RevenueCat integration issues — inspects dashboard configuration through the RevenueCat MCP, walks the SDK debug logs, and covers code-side gotchas. Use when the user says offerings are empty, products not loading, entitlement not active after purchase, paywall won't load, transactions not appearing, customer info shows no entitlements, sandbox purchase not working, or RevenueCat is broken on iOS, Android, Kotlin Multiplatform, Flutter, or React Native.
72
88%
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 defines its purpose, lists concrete diagnostic actions, and provides an extensive 'Use when' clause with natural trigger phrases users would actually say. The description is well-scoped to a specific domain (RevenueCat troubleshooting) with platform coverage, making it highly distinguishable from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'inspects dashboard configuration through the RevenueCat MCP', 'walks the SDK debug logs', 'covers code-side gotchas'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (diagnose and resolve RevenueCat integration issues via dashboard inspection, debug log analysis, and code-side gotchas) and 'when' (explicit 'Use when' clause with extensive list of trigger scenarios and platforms). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural user phrases: 'offerings are empty', 'products not loading', 'entitlement not active after purchase', 'paywall won't load', 'transactions not appearing', 'sandbox purchase not working', 'RevenueCat is broken'. Also includes platform names (iOS, Android, Flutter, React Native, Kotlin Multiplatform) that users would naturally mention. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a very specific niche (RevenueCat integration debugging) with domain-specific triggers like 'offerings are empty', 'entitlement not active', and 'RevenueCat MCP'. Extremely unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 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 strong, highly actionable troubleshooting skill with excellent workflow clarity and systematic diagnosis steps. Its main weakness is that it packs a lot of reference material inline (error code tables, platform checklists, known issues) that could be offloaded to separate files for better progressive disclosure. The content is mostly concise but the overall length could be reduced by extracting reference sections.
Suggestions
Extract the reference sections (SDK error codes, known platform issues, configuration checklists, common issues) into a separate reference file like `reference/error-codes.md` and `reference/known-issues.md` to reduce the main SKILL.md length and improve progressive disclosure.
Remove minor duplication between the universal checklist (steps 3, 5, 6) and the platform configuration checklists at the bottom, or consolidate them into one location.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is generally well-structured and avoids explaining basic concepts, but it's quite long (~300 lines). Some sections like the reference tables and common issues could be tightened. The diagnostic report template is useful but verbose. The platform configuration checklists partially duplicate the universal checklist items (e.g., bundle ID matching, product status). | 2 / 3 |
Actionability | Highly actionable throughout: specific MCP tool calls with exact function names, concrete code snippets for cache refresh, exact error codes mapped to solutions, specific paths to check in dashboards, and a clear diagnostic report template with fixable actions. The checklist items are precise and executable. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with clear sequencing: detect platform → universal checklist → dashboard inspection (phases A/B/C) → platform specifics → verify fix. Includes explicit validation in step 5 (verify the fix) with three concrete criteria. The dashboard inspection has a systematic checklist with verification checkboxes and a confirm-before-fix pattern for destructive MCP operations. | 3 / 3 |
Progressive Disclosure | References five platform-specific files (platforms/ios.md, platforms/android.md, etc.) which is good progressive disclosure, but no bundle files were provided to verify they exist. The SKILL.md itself is quite long with extensive reference sections (error codes, known issues, configuration checklists, common issues) that could be split into separate reference files. The inline reference material makes the main file heavier than ideal. | 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.