BC adb-claw
Your eyes, hands, and ears on Android. See the screen (screenshot + indexed UI tree), interact (tap, swipe, scroll, type, clear-field), navigate via deep links (bypass CJK text input limits), wait for UI state changes instead of polling, monitor live UI text via accessibility framework (works during video playback), capture system audio (Android 11+, WAV stream for piping to ASR tools), manage full app lifecycle (install/uninstall/clear), control screen (on/off/unlock/rotation), run shell commands, and transfer files. Agent-optimized: structured JSON output, indexed element targeting, and App Profiles with pre-built deep links and layouts for popular apps.
As a process C 63/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, progress reporting
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 3. 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
body-longSKILL.md body ≈ 5981 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 63/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 5981 tokens
- 100Steps. 61 steps
- 100Failures and branches. 6 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
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)
- +1No license
- +2Single-language instructions
- +3Description length 664: enough signal without eating the budget
- +4Structure: 51 headings
- +3Step-by-step instructions: 61 items
- +3Output format is stated explicitly
- +4Has examples (38 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 64.