Handle navigation graphs, back stack behavior, app links, intents, and destination ownership for Android apps.
72
66%
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-navigation-deeplinks/SKILL.mdQuality
Discovery
82%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 strong description with excellent specificity and trigger term quality for Android navigation development. Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The domain-specific terminology makes it highly distinctive and unlikely to conflict with other skills.
Suggestions
Add a 'Use when...' clause such as 'Use when the user asks about Android navigation, deep linking, back stack management, or routing between screens in an Android app.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: navigation graphs, back stack behavior, app links, intents, and destination ownership. These are distinct, well-defined Android development concepts. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific capabilities, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. Per rubric guidelines, this caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes natural keywords Android developers would use: 'navigation graphs', 'back stack', 'app links', 'intents', 'destination ownership', 'Android apps'. These are terms developers naturally use when discussing Android navigation. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific to Android navigation architecture. The combination of navigation graphs, back stack, app links, intents, and destination ownership creates a clear niche that is unlikely to conflict with other skills. | 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.
This skill provides a reasonable structural framework for Android navigation and deep links, with some useful Kotlin code snippets for route ownership and back-stack behavior. However, it leans too heavily on abstract process guidance and general software engineering principles that Claude already knows, while lacking the concrete, step-by-step technical depth needed for complex navigation graph and deep-link implementation. The workflow would benefit from explicit validation steps and more complete, executable examples.
Suggestions
Replace abstract workflow steps ('Confirm the user-visible journey') with concrete technical steps like 'Add NavHost with navGraph builder' → 'Register deep link in AndroidManifest.xml' → 'Validate with adb shell am start -a android.intent.action.VIEW -d "scheme://host/path"'
Add a complete, executable example showing a full navigation graph setup with deep link registration, including the AndroidManifest.xml entry and the NavHost/composable destination wiring
Add explicit validation checkpoints such as 'Test deep link with: adb shell am start -W -a android.intent.action.VIEW -d "yourscheme://task?taskId=123"' and expected output verification
Remove or significantly trim the Guardrails and Anti-Patterns sections that state general Android best practices Claude already knows, and replace with navigation-specific gotchas (e.g., 'NavDeepLink requires exact URI match including scheme')
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill has some unnecessary verbosity in its workflow and guardrails sections that describe general software engineering practices Claude already knows (e.g., 'handle loading, success, empty, and error states'). The anti-patterns section also states obvious best practices. However, the code examples are reasonably lean. | 2 / 3 |
Actionability | The Kotlin code snippets are concrete and executable, but they are small fragments rather than complete workflows. The workflow steps are high-level process descriptions ('Confirm the user-visible journey') rather than specific, actionable instructions. The example commands reference project structures that may or may not exist without further context. | 2 / 3 |
Workflow Clarity | The workflow lists steps in sequence but they are abstract process steps rather than concrete technical operations. There are no explicit validation checkpoints or feedback loops for error recovery during the navigation/deep-link implementation process. For a skill involving XML manipulation and navigation graph configuration, missing validation steps caps this at 2. | 2 / 3 |
Progressive Disclosure | The content is reasonably structured with clear sections and references to handoff skills. However, it doesn't effectively use progressive disclosure — everything is inline in one file with no references to deeper documentation files. The official references are external links only, and there's no indication of companion files for advanced topics like deep-link testing or back-stack debugging. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 10 / 11 Passed | |
c5bf673
Table of Contents
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.