CC subwave-app-android
Get the SUB/WAVE mobile app (the Expo project in `app/`) onto a physical Android phone and confirm it runs. Use this skill whenever the user wants to install, reinstall, sideload, run, or load the app on a connected Android device or "their pixel" — by any phrasing. Covers both modes: (1) dev/live — run over USB/cable with Metro so code edits hot-reload on the phone ("run it on my phone", "see my edits live", "test my changes with hot reload", "point it at the metro server"); and (2) standalone/release — build a self-contained APK that runs unplugged over WiFi/cellular ("production build", "release apk", "test it in the wild", "hand off the phone"). Also handles the "app crashed / I deleted it, reinstall fresh" case. Manages adb, the Metro reverse tunnel, the dev-client deep link, and the JDK-17 release build (Android Studio's bundled JDK 21 fails the build). Always screenshots to verify. Do NOT use this for the Docker radio stack (controller/liquidsoap/web) — that's `subwave-control` / `subwave-deploy`. Android phone app only (no iOS).
The skill promises to deploy the SUB/WAVE Android app on a physical phone in two modes: USB dev with hot reload and standalone APK for offline use. It contains one instruction file with 2385 tokens.
Tests found only a lint error—description is too long. No critical issues, broken links, or missing files. Quality score sits at 53/100, process at 64/100. The skill hasn't run through model validation or sandbox testing, so instruction accuracy and edge case coverage remain unclear.
Install if you're willing to verify the steps manually before first use. No model validation data available.
Get the SUB/WAVE mobile app (the Expo project in app/) onto a physical Android phone and confirm it runs.
As a process C 64/100 · Has gaps — weak spots: result and completion, inputs and preconditions
How to improve
- Shorten the description to 1024 characters.
- 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: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1052 chars, limit 1024 - warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Get the SUB/WAVE mobile app (the Expo project in `app/`) onto a ph… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 64/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 65Failures and branches. 3 branches
- 100Steps. 7 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2385 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
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
- +3Description length 1052: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +5Description quotes 10 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 16 headings
- +3Step-by-step instructions: 7 items
- +4Has examples (16 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 53.