SKILLEMALL.ai
GitHub ↗ RU Sign in

DA ios-qa

Live-device iOS QA for SwiftUI apps. (gstack)

garrytan/gstack Agent Skills author: garrytan MIT 31 files · 27 scripts body ≈ 10 996 tokens Open the sourcegithub.com↗ analyzed 3 d ago

Live-device iOS QA for SwiftUI apps.

As a process A 82/100 · Runs to the end — weak spots: execution cost, running it twice

ProcedureAI and agentsSoftware developmenttype 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
73/100
safety, quality, tests
Safety 60%
86
Quality 40%
54
Run on models
none yet
Process rating
A
82/100
Runs to the end
Running it twice w 4
30
Execution cost w 6
40
When it triggers w 12
50
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 10

✓ No critical or high findings

Medium and low: 10
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Bash Read Write Edit Grep Glob AskUserQuestion
  • low Secrets in code secret-high-entropy-token daemon/src/devicectl.ts:117
    High-entropy token-like string (may be an id, hash or a credential)
    export function getD…ctl(
  • low Secrets in code secret-high-entropy-token daemon/src/devicectl.ts:238
    High-entropy token-like string (may be an id, hash or a credential)
    const fromDevicectl = getD…ctl(opts.udid, spawn);
  • low Secrets in code secret-high-entropy-token daemon/src/tunnel-bootstrap.ts:30
    High-entropy token-like string (may be an id, hash or a credential)
    getD…ctl,
  • low Secrets in code secret-high-entropy-token daemon/src/tunnel-bootstrap.ts:424
    High-entropy token-like string (may be an id, hash or a credential)
    let address = getD…ctl(device.identifier, spawn);
  • low Secrets in code secret-high-entropy-token daemon/test/tunnel-bootstrap.test.ts:8
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    getD…ctl,
    fixture
  • low Secrets in code secret-high-entropy-token daemon/test/tunnel-bootstrap.test.ts:903
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    describe('getD…ctl', () => {
    fixturequoted
  • low Secrets in code secret-high-entropy-token daemon/test/tunnel-bootstrap.test.ts:911
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    expect(getD…ctl('TEST-UDID', spawn)).toBe('fde4…::1');
    fixture
  • low Secrets in code secret-high-entropy-token daemon/test/tunnel-bootstrap.test.ts:921
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    expect(getD…ctl('UDID', spawn)).toBe('fd00…eef');
    fixture
  • low Secrets in code secret-high-entropy-token daemon/test/tunnel-bootstrap.test.ts:928
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    expect(getD…ctl('UDID', spawn)).toBeNull();
    fixture

Files scanned: 29. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 10996 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "preamble-tier"
  • note frontmatter-key unknown frontmatter key "triggers"
  • note edit-residue the text marks something as outdated (lines 480): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 82/100

  • 30Running it twice. 15 mutating operations with no state check
  • 40Execution cost. Instruction body is 10996 tokens: crowds the task out of the window
  • 50When it triggers. No condition that starts the skill
  • 60Result and completion. Output format stated, no completion criterion
  • 100Tools and files. Tools declared in frontmatter
  • 100Steps. 94 steps
  • 100Inputs and preconditions. Inputs and preconditions are listed
  • 100Failures and branches. 9 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 32 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (17 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

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 45: 120–800 characters recommended
  • -5TODO / placeholder text left in the skill
  • -2localhost URLs: will not work for another user
  • -32 of 2 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +4Structure: 38 headings
  • +3Step-by-step instructions: 94 items
  • +3Output format is stated explicitly
  • +4Has examples (12 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 54.

In the sandbox The scripts kept to themselves

The skill's scripts were run in a throwaway machine: no network, fake keys in the home directory, a tracer watching. We wrote down what they did. Reaching for the network or for secrets caps the technical grade at C; a quiet run adds no points.

Запущено 12 скриптов, ещё 2 не поместились в лимит; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.

scripts/gen-accessors.test.tsничего за пределами своей папки
scripts/gen-accessors.tsничего за пределами своей папки
daemon/src/allowlist.tsничего за пределами своей папки
daemon/src/audit.tsничего за пределами своей папки
daemon/src/auth-mint.tsничего за пределами своей папки
daemon/src/cli-mint.tsничего за пределами своей папки
daemon/src/devicectl.tsничего за пределами своей папки
daemon/src/index.tsничего за пределами своей папки
daemon/src/proxy.tsничего за пределами своей папки
daemon/src/session-tokens.tsничего за пределами своей папки
daemon/src/single-instance.tsничего за пределами своей папки
daemon/src/tailscale-localapi.tsничего за пределами своей папки

16 Oct 2026