android-networking
Integrate Retrofit, OkHttp, and Kotlinx Serialization for type-safe API communication in Android. Use when building API clients, adding interceptors, or configuring network security.
74
70%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/android/android-networking/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-crafted skill description that clearly identifies its niche (Android API networking with specific libraries), includes an explicit 'Use when' clause, and uses natural trigger terms developers would search for. The main area for improvement is listing more specific concrete actions beyond the high-level capabilities mentioned.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Android networking) and key libraries (Retrofit, OkHttp, Kotlinx Serialization) with some actions ('building API clients, adding interceptors, configuring network security'), but doesn't list multiple concrete granular actions like defining endpoints, handling serialization adapters, or setting up certificate pinning. | 2 / 3 |
Completeness | Clearly answers both 'what' (integrate Retrofit, OkHttp, and Kotlinx Serialization for type-safe API communication in Android) and 'when' (Use when building API clients, adding interceptors, or configuring network security) with an explicit 'Use when...' clause. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Retrofit', 'OkHttp', 'Kotlinx Serialization', 'API clients', 'interceptors', 'network security', 'Android', 'type-safe API communication'. These cover the main terms a developer would use when seeking this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific combination of Retrofit + OkHttp + Kotlinx Serialization on Android. The trigger terms are narrowly scoped to Android networking with these specific libraries, making conflicts with other skills unlikely. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is well-structured and concise, correctly assuming Claude's familiarity with Android networking libraries. However, it critically lacks any inline executable code or concrete examples, making the body itself largely non-actionable — it reads more like a checklist of principles than an instructional skill. The heavy reliance on a single reference file for all implementation details weakens both actionability and progressive disclosure.
Suggestions
Add at least one inline executable code example showing a minimal Retrofit + OkHttp + Kotlinx Serialization setup (e.g., a complete API interface and Retrofit builder) so the skill body is actionable on its own.
Include a concrete example of the Result/Either wrapper pattern in the Repository layer, since this is a key architectural decision mentioned but not demonstrated.
Split the single reference file into distinct references (e.g., setup.md, interceptors.md, testing.md) or at minimum link to specific sections, so progressive disclosure is more navigable.
Add a validation step or verification checkpoint (e.g., 'Verify certificate pinning with a test request' or 'Confirm ProGuard rules don't strip serialization annotations') to improve workflow clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It avoids explaining what Retrofit, OkHttp, or Kotlinx Serialization are, assumes Claude's competence with these libraries, and every bullet point conveys a specific, non-obvious instruction. | 3 / 3 |
Actionability | The skill provides no executable code, no concrete examples, and no copy-paste ready snippets. All concrete guidance is deferred to a reference file. The body itself only describes what to do at a high level without showing how. | 1 / 3 |
Workflow Clarity | Steps are numbered and sequenced (Configure → Define → Add concerns), but there are no validation checkpoints, no feedback loops for error recovery, and no verification steps for operations like certificate pinning or ProGuard rule configuration. | 2 / 3 |
Progressive Disclosure | There is a reference file linked, but the same reference (references/implementation.md) is linked multiple times for different purposes, and the main body is too thin — it defers almost all actionable content to one file rather than providing a useful quick-start overview with code inline. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 9 / 11 Passed | |
- Repository
- HoangNguyen0403/agent-skills-standard
- Commit
4c72e76
- 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.