BD subwave-control
Start or stop the SUB/WAVE radio stack (a personal internet radio station) in dev or production mode — no builds, no rebuilds, no config rendering. Use this skill any time the user wants to "start subwave", "stop subwave", "bring up the radio", "shut down the radio", "boot subwave in dev/prod", "turn subwave on/off", "is subwave running?", or otherwise just power the stack up or down. Detects which compose file (dev vs prod) is already running and matches it; if nothing is running, asks dev or prod. Dev mode also launches the Next.js web dev server on :7700 in the background. Always verifies the stream is on-air after a start. Do NOT use this skill for first-time setup, `git pull` + rebuilds, jingle generation, or config changes — that's `subwave-deploy`. If the user asks for any of those, hand off rather than starting.
This skill controls the SUB/WAVE stack—brings the radio station up or down in dev or prod without rebuilds. Detects which compose file is already running and matches it; if nothing runs, it asks which mode. In dev it also starts Next.js on :7700. After startup it verifies the stream is on-air.
Grade B with quality 82—one file, no critical issues, but process score stuck at 43. Broken references suggest incomplete setup: likely missing or mismatched configs. Never ran on models. Works for routine mode switches, but not for initial setup or git pull.
Install if the radio already lives on your machine and you need a quick restart command. If the stack hasn't launched yet—do it by hand first.
Start or stop the SUB/WAVE radio stack (a personal internet radio station) in dev or production mode — no builds, no rebuilds, no config rendering.
As a process D 43/100 · Unfinished process — References files that are not bundled: scripts/setup.sh
How to improve
- 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: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: scripts/setup.sh
Process rating: all ten parameters 43/100
- 0Tools and files. 1 referenced file(s) missing: scripts/setup.sh
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 5 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 65Failures and branches. 3 branches
- 100Steps. 18 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1402 tokens
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 831: 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 7 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 12 headings
- +3Step-by-step instructions: 18 items
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.