SKILLEMALL.ai
GitHub ↗ RU Sign in

DC subwave-app-android-release

Cut a NEW Android build of the SUB/WAVE app (the Expo project in `app/`) in the cloud with EAS and ship it — to the live Google Play Store, or as a direct install link for testers. Use this skill whenever the user wants to "release the android app", "ship the android app", "push a new Play Store build", "build a new android version", "send the android build to testers", "get a shareable install link for android", "make an apk for the testers", "submit android", "distribute the android app", or "put android on testers' phones" — anything aimed at producing a fresh Android build and getting it out. Trigger it even when the user doesn't say "EAS" by name. Two paths: a **Play Store release** (`production` profile builds an `.aab`, which you upload to the Play Console by hand — the app is LIVE in production), and a **quick sideload test** (`preview` profile builds an APK + install link/QR, no Google account needed). Do NOT use this skill for putting the app on a LOCAL phone over USB/adb with hot reload — that's `subwave-app-android`. Do NOT use it for the iOS app — that's `subwave-app-ios-release`.

Not recommendedcritical or high security findings · low grade D
perminder-klair/subwave Agent Skills author: perminder-klair 1 file body ≈ 3 123 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Cut a NEW Android build of the SUB/WAVE app (the Expo project in app/) in the cloud with EAS and ship it — to the live Google Play Store, or as a direct…

As a process C 60/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

GeneratorSales and CRMtype 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
71/100
safety, quality, tests
Safety 60%
82
Quality 40%
55
Run on models
none yet
Process rating
C
60/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
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.
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 · 1

  • high Concealment en-hide-from-user SKILL.md:249
    Instruction to hide actions from the user
    present, so the Play upload is manual via the Console. Don't tell the user a

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 1110 chars, limit 1024
  • warning frontmatter-yaml SKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Cut a NEW Android build of the SUB/WAVE app (the Expo project in `… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value

Process rating: all ten parameters 60/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 10 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (web) that frontmatter does not declare
  • 100Steps. 18 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 3123 tokens
  • 100Progress reporting. Reports progress
  • low 10 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

  • +3Description length 1110: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 10 example trigger phrases
  • +4Description says when NOT to use the skill
  • +4Structure: 12 headings
  • +3Step-by-step instructions: 18 items
  • +4Has examples (10 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 55.