CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

rc-configuring-the-sdk

Use this skill when adding and configuring the RevenueCat Android SDK (purchases-android, artifact com.revenuecat.purchases:purchases) in an app. Covers the Gradle dependency, Purchases.configure with PurchasesConfiguration, initial app user id strategy, and log level.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced configuration guide with executable code, decision tables, validation checkpoints, and a useful diagnostics table. Its main weaknesses are redundant error-cause explanations repeated between the execute phase and the pitfalls table, and inline time-sensitive version/date details that would be better isolated.

Suggestions

Deduplicate the offerings error diagnosis: keep it in the Common pitfalls table and cut the long explanatory paragraph in section 3.3, or vice versa.

Move time-sensitive details (the 10.27.1 version pin dated 2026-10-13 and the Play Billing Library 7 deadline dates) into a dedicated 'Versions and deadlines' section so staleness is isolated and easy to update.

Consider splitting the detailed error catalog and pitfalls into a references/ file (e.g. TROUBLESHOOTING.md) to slim the main SKILL.md toward a leaner overview.

DimensionReasoningScore

Conciseness

The body is mostly efficient tables and code with no padding about concepts Claude already knows, but the offerings error diagnosis is duplicated in full both in the section 3.3 prose ('ConfigurationError means the dashboard has no products configured...') and again in the Common pitfalls table, and time-sensitive version/date info ('Use 10.27.1 (latest as of 2026-10-13)', 'after August 31, 2026') sits inline rather than in a dedicated section. It fits 'mostly efficient but... could be tightened' better than level 4's 'minor instances', since the duplication spans a full paragraph plus table rows.

3 / 5

Actionability

Fully executable throughout: concrete rg search commands, copy-paste Gradle and Kotlin snippets, manifest registration instructions, and a runnable offerings-fetch verification with error handling; the '<latest>' placeholder is immediately resolved by 'Use 10.27.1'.

5 / 5

Workflow Clarity

The three phases are explicitly ordered ('Work through the phases in order') with a discovery checklist table, a safety checkpoint ('If Purchases.configure already runs, stop and confirm with the user before changing it'), an explicit validation step ('Confirm the wiring with a minimal offerings fetch'), and symptom-to-fix recovery guidance in the pitfalls table — matching the top anchor's checklist, validation, and feedback-loop criteria.

5 / 5

Progressive Disclosure

The single-file body is well-sectioned with one clearly signaled external reference ('The [full chapter on revenuecat.com]... has the complete reference text'), but at ~155 lines with no bundle files, detailed material like the inline error catalog could be split into a reference file. This places it at 'good structure; minor organization gaps' rather than the level 5 clear split across files.

4 / 5

Total

17

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with an explicit 'Use this skill when...' trigger clause, a concrete enumeration of capabilities, and highly specific platform/artifact identifiers that make it distinct. The only gap is modest synonym coverage for trigger terms like 'in-app purchases' or 'subscriptions'.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete actions — 'the Gradle dependency, Purchases.configure with PurchasesConfiguration, initial app user id strategy, and log level' — which comprehensively matches the skill's actual scope, satisfying the top anchor rather than leaving coverage gaps.

5 / 5

Completeness

It explicitly answers both questions: 'Use this skill when adding and configuring the RevenueCat Android SDK... in an app' gives a concrete trigger, and the 'Covers...' sentence concretely lists what it does — clearly above the level 4 anchor where the 'when' is only vaguely specified.

5 / 5

Trigger Term Quality

Natural phrases like 'adding and configuring the RevenueCat Android SDK', 'Gradle dependency', and 'app user id' are present, but common user synonyms such as 'in-app purchases', 'subscriptions', or 'Play Billing' are missing, matching 'good keyword coverage; a few natural terms missing' rather than comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

It names the exact platform and artifact ('purchases-android, artifact com.revenuecat.purchases:purchases'), establishing a clear niche with minimal conflict risk beyond trivially related sibling RevenueCat skills.

5 / 5

Total

19

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

RevenueCat/ai-toolkit

Path

revenuecat-play-billing/skills/rc-configuring-the-sdk/SKILL.md

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.