load-test-cases
Detect test mode (ad-hoc vs regression) and return a list of test cases to run.
Skill by hoangdh2001
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.
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.
About
Use cases: testing, marketing
Reviews
Write a reviewNo 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.
More from hoangdh2001/apple-app-ui-test-automation
- 0.443score
select-ipad-simulator
hoangdh2001
List available simulators, filter to iPad only, and recommend one based on test content.
SkillDFreshness: D★ 2Claude Code +9 - 0.440score
select-iphone-simulator
hoangdh2001
List available simulators, filter to iPhone only, and recommend one based on test content.
SkillDFreshness: D★ 2Claude Code +9 - 0.440score
select-mac-target
hoangdh2001
Resolve the correct Xcode destination and scheme for a macOS test run.
SkillDFreshness: D★ 2Claude Code +9 - 0.440score
verify-cli-env
hoangdh2001
Verify that xcodebuildmcp and axe CLIs are installed and available.
SkillDFreshness: D★ 2Claude Code +9 - 0.440score
generate-test-report
hoangdh2001
Generate a Markdown test report from completed test case results.
SkillDFreshness: D★ 2Claude Code +9 - 0.440score
run-test-case
hoangdh2001
Execute a single UI test case and return its result.
SkillDFreshness: D★ 2Claude Code +9
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
- Source
- GitHubgithub-graphql
More from hoangdh2001
- 0.443score
select-ipad-simulator
hoangdh2001
List available simulators, filter to iPad only, and recommend one based on test content.
SkillDFreshness: D★ 2Claude Code +9 - 0.440score
select-iphone-simulator
hoangdh2001
List available simulators, filter to iPhone only, and recommend one based on test content.
SkillDFreshness: D★ 2Claude Code +9 - 0.440score
select-mac-target
hoangdh2001
Resolve the correct Xcode destination and scheme for a macOS test run.
SkillDFreshness: D★ 2Claude Code +9 - 0.440score
verify-cli-env
hoangdh2001
Verify that xcodebuildmcp and axe CLIs are installed and available.
SkillDFreshness: D★ 2Claude Code +9 - 0.440score
generate-test-report
hoangdh2001
Generate a Markdown test report from completed test case results.
SkillDFreshness: D★ 2Claude Code +9 - 0.440score
run-test-case
hoangdh2001
Execute a single UI test case and return its result.
SkillDFreshness: D★ 2Claude Code +9
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.
Cite this page
load-test-cases skill. Agent Mart. https://agentmart.dev/skills/hoangdh2001-load-test-cases (last updated 2026-10-24)