CtrlK
BlogDocsLog inGet started
Tessl Logo

android-navigation

Implement screen routes and deep-link/App Link routing with Jetpack Compose Navigation on Android. Use when the primary task is Compose route configuration or external URL routing; defer typed-route APIs, XML/fragments, generic back-stack, and transition questions to their specific navigation skills.

64

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/android/android-navigation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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.

The content is admirably concise and well-structured with a genuine backing reference, but the body itself stays at the directive level — it lacks inline executable examples and an explicit sequenced workflow with validation checkpoints.

Suggestions

Add one short inline Kotlin snippet in the Guidelines (e.g., a sealed-class route + NavHost composable with deepLinks) so the body is actionable without forcing a file hop.

Convert the navigation setup into a short numbered workflow with an explicit validation checkpoint (e.g., verify autoVerify intent-filter and argument IDs before rendering) to lift workflow clarity.

Either inline a 1–2 line pointer to a specific section of navigation-patterns.md, or add a second targeted reference, to make progressive disclosure fully one-level-deep and clearly signaled.

DimensionReasoningScore

Conciseness

The body is lean and efficient — terse guideline and anti-pattern bullets with no padded explanations of concepts Claude already knows; every token earns its place.

5 / 5

Actionability

The body names specific APIs (navigation-compose, sealed classes, intent-filter, deepLinks) but provides no executable code inline; concrete examples live only in the reference file, leaving the body as high-level directives rather than copy-paste guidance.

3 / 5

Workflow Clarity

There is no sequenced multi-step workflow; validation is mentioned ('Validate arguments before loading content') but without checkpoints or an explicit sequence, so the structure is a list of guidelines rather than a guided process.

3 / 5

Progressive Disclosure

A single well-signaled one-level reference (references/navigation-patterns.md) backs a lean overview, and the reference file is real and well-organized; minor gaps (only one reference, no in-body section links) keep it just below 5.

4 / 5

Total

15

/

20

Passed

Description

87%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.

The description is well-crafted: it states concrete capabilities, gives explicit 'Use when' triggers, and proactively distinguishes itself from sibling navigation skills. Minor keyword-synonym gaps keep trigger term quality and specificity just below perfect.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ('Implement screen routes and deep-link/App Link routing with Jetpack Compose Navigation'), with only minor coverage gaps; not quite comprehensive enough for a 5.

4 / 5

Completeness

Explicitly answers both what ('Implement screen routes and deep-link/App Link routing...') and when ('Use when the primary task is Compose route configuration or external URL routing') with concrete trigger phrasing.

5 / 5

Trigger Term Quality

Natural phrases like 'Compose route configuration' and 'external URL routing' plus metadata keywords (NavController, NavHost, composable, navArgument, deepLinks) give good coverage, though a few common synonyms are absent.

4 / 5

Distinctiveness Conflict Risk

The explicit deferral clause ('defer typed-route APIs, XML/fragments, generic back-stack, and transition questions to their specific navigation skills') carves out a clear niche with minimal conflict risk.

5 / 5

Total

18

/

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.

Validation14 / 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
HoangNguyen0403/agent-skills-standard
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.