android-gradle-build-performance

Diagnose and improve Android and Gradle build performance with scans, cache checks, and bottleneck audits.

Quality

62%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/android-gradle-build-performance/SKILL.md

Quality

Content

57%

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

This is a well-structured skill with good progressive disclosure and clear scope boundaries, but it leans toward procedural guidance rather than concrete, executable instructions. The workflow is logical but lacks explicit validation checkpoints and feedback loops for what is essentially a diagnostic/optimization process. The examples section with actual script commands is a strength, but the core workflow could benefit from more specific, actionable details.

Suggestions

Add concrete Gradle commands and expected output snippets in the Workflow section (e.g., show the specific gradle.properties flags to check, what a configuration cache diagnostic command looks like, and how to interpret --scan output).

Add explicit validation/feedback loops in the workflow: after step 4, specify how to measure improvement (e.g., 'run the audit script again and compare JSON output') and what threshold indicates success vs. needing further investigation.

In the Guardrails or Anti-Patterns section, provide a brief concrete example of a common smell and its fix (e.g., show a before/after of converting kapt to ksp in a build.gradle.kts snippet) rather than only describing patterns abstractly.

Dimension	Reasoning	Score
Conciseness	The content is reasonably efficient but includes some sections that restate things Claude would know (e.g., explaining what dynamic dependency versions do, general advice about not mixing concerns). The 'When To Use' section has some redundancy with the description. However, it avoids egregious verbosity.	2 / 3
Actionability	The skill provides concrete script commands in the Examples section and references specific tools (--profile, --scan), but the core Workflow and Guardrails sections are procedural guidance without executable code or specific Gradle commands/configurations. The audit script commands are actionable, but the optimization steps themselves remain abstract (e.g., 'check gradle.properties' without showing what to look for or change).	2 / 3
Workflow Clarity	The workflow has a clear 5-step sequence with a logical measure-then-fix approach, and the Done Checklist provides validation criteria. However, there are no explicit validation checkpoints or feedback loops within the workflow steps themselves—step 4 mentions 'compare before and after' but doesn't specify how to validate success or what to do if the optimization doesn't help.	2 / 3
Progressive Disclosure	The skill effectively uses one-level-deep references to patterns.md and scenarios.md with clear signals about when to read them. It also cleanly hands off to related skills (android-gradle-build-logic, android-ci-cd-release-playstore). The content is well-organized into distinct sections without being monolithic.	3 / 3
	Total	9 / 12 Passed

Description

67%

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 concise and specific about its domain (Android/Gradle build performance) with concrete actions listed. Its main weakness is the absence of an explicit 'Use when...' clause, which limits Claude's ability to know exactly when to select this skill. Adding natural trigger terms that users would say (e.g., 'slow build', 'build time') would also improve discoverability.

Suggestions

Add a 'Use when...' clause, e.g., 'Use when the user reports slow Android builds, wants to optimize Gradle build times, or needs help with build scan analysis.'

Include common user-facing trigger terms like 'slow build', 'build time', 'build cache', 'configuration cache', 'Gradle daemon', or 'build optimization' that users would naturally mention.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'diagnose and improve build performance', 'scans', 'cache checks', and 'bottleneck audits'. These are concrete, actionable capabilities rather than vague language.	3 / 3
Completeness	Clearly answers 'what does this do' (diagnose and improve build performance with scans, cache checks, bottleneck audits), but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this at 2 per the rubric.	2 / 3
Trigger Term Quality	Includes relevant keywords like 'Android', 'Gradle', 'build performance', 'scans', 'cache checks', and 'bottleneck audits'. However, it misses common user variations like 'slow build', 'build time', 'build cache', 'configuration cache', 'build scan', or '.gradle' that users would naturally say.	2 / 3
Distinctiveness Conflict Risk	The combination of 'Android', 'Gradle', 'build performance', 'scans', 'cache checks', and 'bottleneck audits' creates a very clear niche that is unlikely to conflict with other skills. This is highly specific to Android/Gradle build optimization.	3 / 3
	Total	10 / 12 Passed

Validation

90%

Warnings & errors only

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

Repository: krutikJain/android-agent-skills
Commit: c5bf673

Reviewed: 2 months ago

Table of Contents

Discovery Implementation Validation

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.