BF android-adb-skill
Android 开发调试技能，通过系统 ADB 工具操作 Android 设备。以下场景必须触发此技能：(1) 直接 ADB 操作——安装 APK、查看设备列表、抓取 logcat 日志、查看已安装应用、清除应用数据、截图、重启设备、拉取/推送文件、查看 CPU/内存/电池信息、adb shell 操作；(2) Android 开发编码任务——编写或修改 Android/Flutter/HarmonyOS 代码、修复 Android 端 Bug、实现 Android 功能、调整 AndroidManifest、修改 Gradle 配置等一切涉及安卓端的开发工作，编码完成后必须主动提示用户通过 ADB 部署验证修改成果；(3) 验证与测试——用户说"试一下""看看效果""测试一下""跑一下""装到手机上"等语句，只要上下文是 Android 项目，立即触发设备检测并引导安装验证。即使用户只说"帮我装一下"或"看看日志"，只要上下文涉及 Android 设备或 Android 项目，也必须触发此技能。
As a process F 35/100 · Will not run — References files that are not bundled: references/install-errors.md
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: references/install-errors.md
Process rating: all ten parameters 35/100
- 0Tools and files. 1 referenced file(s) missing: references/install-errors.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 100Steps. 10 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1279 tokens
- 100Running it twice. No mutating operations
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 455: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 10 items
- +4Has examples (16 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.