SKILLEMALL.ai
GitHub ↗ RU Sign in

DC subwave-deploy

Set up, deploy, or update SUB/WAVE (a personal internet radio station). On a fresh checkout, runs scripts/setup.sh, prompts for Navidrome + Ollama credentials, brings the stack up, and generates jingles. On an already-running stack, pulls the latest, rebuilds only the Docker services whose code actually changed, recreates them, and verifies the stream is on-air. Use this skill any time the user wants to install, set up, bootstrap, deploy, update, sync, redeploy, refresh, restart, or "pull and restart" SUB/WAVE — including phrases like "set up subwave", "install subwave", "first boot", "bootstrap the radio", "pull subwave", "update the radio", "deploy subwave", "rebuild controller", "restart sub-wave", "redeploy after pull", "git pull and restart as needed", "check if the stream is healthy", or simply "deploy" / "install" / "set up" while in the subwave repo. Trigger proactively whenever the user is working in the subwave repo and mentions setting up, installing, deploying, updating, rebuilding, restarting, or checking the running stack — even if they don't name the skill. Free to pull, rebuild, recreate, render Icecast config, generate jingles, and run health probes; confirm before destructive ops like wiping `state/`, removing volumes, full `down -v`, or overwriting an existing controller/.env that already has the operator's Navidrome password.

Not recommendedcritical or high security findings · low grade D
perminder-klair/subwave Agent Skills author: perminder-klair 2 files · 1 script body ≈ 5 499 tokens Open the sourcegithub.com↗ analyzed 13 d ago

Set up, deploy, or update SUB/WAVE (a personal internet radio station).

As a process C 64/100 · Has gaps — References files that are not bundled: scripts/setup.sh, scripts/**

ProcedureDockerInfrastructuretype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
D
65/100
safety, quality, tests
Safety 60%
81
Quality 40%
40
Run on models
none yet
Process rating
C
64/100
Has gaps
References files that are not bundled: scripts/setup.sh, scripts/**
Tools and files w 18
0
Result and completion w 14
0
Execution cost w 6
70
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Concealment
If you install

The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.

For the author

Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. Shorten the description to 1024 characters.
  3. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  4. The text references files that are not there: add them or drop the references.
For the model run — optional
  • 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 · 2

  • high Concealment en-hide-from-user SKILL.md:280
    Instruction to hide actions from the user
    Do not use `docker compose restart` for code changes — it will appear to succeed and silently run the old code (see Fact #2).
Medium and low: 1
  • low Exfiltration read-dotenv SKILL.md:96
    Reads a .env file
    cp controller/.env.example controller/.env

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 1367 chars, limit 1024
  • warning body-long SKILL.md body ≈ 5499 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: scripts/setup.sh
  • warning missing-ref reference to a missing file: scripts/**

Process rating: all ten parameters 64/100

Will not run. References files that are not bundled: scripts/setup.sh, scripts/**
  • 0Tools and files. 2 referenced file(s) missing: scripts/setup.sh, scripts/**
  • 0Result and completion. Does not say what the result is
  • 70Execution cost. Instruction body is 5499 tokens
  • 85Steps. 53 steps, 2 vague phrases
  • 100When it triggers. States when to use and when not to
  • 100Inputs and preconditions. Inputs and preconditions are listed
  • 100Failures and branches. 5 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • low The response is described with custom markup (6 tags): a typed call is more reliable

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

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 1367: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -5TODO / placeholder text left in the skill
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 16 example trigger phrases
  • +4Structure: 24 headings
  • +3Step-by-step instructions: 53 items
  • +4Has examples (17 code blocks)
  • +3All 1 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 40.