Skip to content
Agentmart
Submit a tool

load-test-cases

Detect test mode (ad-hoc vs regression) and return a list of test cases to run.

Skill by hoangdh2001

IndexedMIT★ 2
Write a review

Chalk Labs

Need help deploying load-test-cases?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/hoangdh2001-load-test-cases

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Detect test mode (ad-hoc vs regression) and return a list of test cases to run. Used by all platform agents (iphone-tester, ipad-tester, macos-tester). For regression: reads tests/ios-tests.yaml or infers cases from the codebase. For ad-hoc: generates a minimal test plan from the user's description.

Use cases: testing, marketing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/load-test-cases

What's inside

Skill name
load-test-cases
Description
Detect test mode (ad-hoc vs regression) and return a list of test cases to run. Used by all platform agents (iphone-tester, ipad-tester, macos-tester). For regression: reads tests/ios-tests.yaml or infers cases from the codebase. For ad-hoc: generates a minimal test plan from the user's description.
License
MIT
Instructions
78 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Skill: load-test-cases

## Input
- `user_message` — the original request from the user
- `project_root` — absolute path to the directory containing the `.xcodeproj` file

## Step 1: Detect mode

| User says | Mode |
|-----------|------|
| "test [feature X]", "kiểm tra [X]", "thử [X]" | Ad-hoc |
| "run regression", "chạy regression", "test all", "test toàn bộ" | Regression |

## Step 2a: Ad-hoc mode

Generate a minimal test plan from the user's description:
- What screen/tab does this feature live on?
- What interactions are needed to reach it?
- What is the expected result?

Return the generated cases and proceed immediately. No file read needed.

## Step 2b: Regression mode

Check if the YAML file exists:

```bash
ls <project_root>/tests/ios-tests.yaml 2>/dev/null && echo "FOUND" || echo "NOT FOUND"
```

**If FOUND:** Read and parse it. Return all entries under `cases:`.

**If NOT FOUND:** Infer from the codebase:

```bash
ls <project_root>/<AppName>/Features/
```

For each feature directory:
1. Identify the primary user action (what does a user *do* with this feature?)
2. Generate one test case covering its core happy path

Present the inferred cases to the user and **wait for confirmation** before returning.

## Test Case YAML Schema

```yaml
suite: Suite Name
version: 1.0
cases:
  - id: kebab-case-id
    name: "Human readable name"
    feature: "Tab > Section"
    steps:
      - navigate: <tab name>      # tap tab bar item by accessibility label
      - tap: "<element label>"    # tap UI element by accessibility label
      - select: "<option>"        # tap item in picker/context menu
      - type: "<text>"            # type text into focused field
    expect:
      - ui_contains: "<label>"
      - element_not_exists: "<label>"
```

## Step Translation: YAML verbs → axe commands

| YAML step | axe command |
|-----------|-------------|
| `navigate: Settings` | `tap --label Settings --wait-timeout 5` |
| `tap: "Start Focus"` | `tap --label 'Start Focus' --wait-timeout 5` |
| `select: "Dark"` | `tap --label 'Dark' --wait-timeout 3` |
| `type: "hello"` | `type 'hello'` |

If `--label` fails with "multiple matches": run `axe describe-ui --udid <UDID>` and use coordinate-based tap.

## Output
List of test case objects ready for the agent to pass into `run-test-case`.

From hoangdh2001/apple-app-ui-test-automation, MIT.

Signals

Stars
2
Forks
0
Open issues
0
Last commit (this folder)
Apr 20, 2026 (6 months ago)
Last release
Apr 27, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from hoangdh2001

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get load-test-cases running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying load-test-cases?

CallGet help
Cite this page

load-test-cases skill. Agent Mart. https://agentmart.dev/skills/hoangdh2001-load-test-cases (last updated 2026-10-24)