CtrlK
BlogDocsLog inGet started
Tessl Logo

android-version-platform-adapt

依据 Android 官方「版本」文档完成平台适配:按版本号 N 抓取行为变更(所有应用、 targetSdk=N)、changes/features 子页与探索新功能/API;归纳影响项并落地到 Manifest/Gradle/工具类封装。在用户要求 Android 版本适配、行为变更排查、 targetSdk 升级、新 API 封装或对照 developer.android.com/about/versions 时使用。

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 well-structured, actionable workflow with concrete URL templates, an executable scan script, and a clean division-of-labor table, backed by a real one-level reference. It loses points for some URL/checklist duplication and only-implicit retry loops.

Suggestions

Deduplicate the Android 17 URLs: keep one canonical URL table and reference it from the workflow and fixed-example sections instead of restating the links.

Make the bash scan script literally runnable by substituting {N} via a shell variable (e.g. N=17) rather than a literal placeholder, or note that {N} must be replaced before execution.

Add an explicit fetch-failure retry loop (WebFetch fails → WebSearch + retry N times → flag missing page in the summary) to strengthen the validation feedback loop.

DimensionReasoningScore

Conciseness

Lean with no concept padding and dense, useful tables, but repeats Android 17 URLs across the URL table, the fixed-example list, and workflow steps, and the checklist duplicates the workflow — minor over-explanation.

4 / 5

Actionability

Provides executable URL templates with {N} substitution, a runnable bash curl/grep scan script, and a copyable markdown summary template; minor gaps include the non-literal {N} shell substitution and conditional 'if it exists, read it' instructions.

4 / 5

Workflow Clarity

Clear numbered 0→1→2→3→4 sequence with a checklist and explicit validation checkpoints (dedup, 补读 before updating, 核对方法签名, 必须补 release-notes); not a full 5 because the validate→fix→retry loop and retry-on-fetch-failure guidance are only implicit.

4 / 5

Progressive Disclosure

A single one-level-deep reference (references/reference.md) is clearly signaled multiple times with section anchors, and bulk scanned-path/API-level detail is appropriately offloaded; minor gaps include slight inline duplication and an anchor that does not exactly match the heading text.

4 / 5

Total

16

/

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 specific, complete description with explicit 'Use when...' trigger guidance and a distinct Android-version-adaptation niche. Minor synonym coverage gaps keep trigger term quality at 4 rather than 5.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — '抓取行为变更(所有应用、targetSdk=N)', 'changes/features 子页与探索新功能/API', '归纳影响项并落地到 Manifest/Gradle/工具类封装' — with comprehensive coverage.

5 / 5

Completeness

Explicitly answers both what ('完成平台适配' with concrete actions) and when ('在用户要求... 时使用'), with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural phrases users would say ('Android 版本适配、行为变更排查、targetSdk 升级、新 API 封装') plus the developer.android.com/about/versions URL trigger; a few synonyms (e.g. compileSdk) are missing, placing it just above the midpoint.

4 / 5

Distinctiveness Conflict Risk

A clear niche — Android version/platform adaptation anchored to developer.android.com/about/versions — with distinct triggers unlikely to conflict with other skills.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository
afkT/DevUtils
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.