Skip to content
Agentmart
Submit a tool

run-test-case

Execute a single UI test case and return its result.

Skill by hoangdh2001

IndexedMIT★ 2
Write a review

Chalk Labs

Need help deploying run-test-case?

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-run-test-case

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

Execute a single UI test case and return its result. Works across iPhone, iPad, and macOS — pass the platform param to adjust behavior. Requires the app to already be built and running before calling this skill. Returns: pass, flaky, or fail — with screenshot path, logs, and root cause on failure.

Use cases: design, testing

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/run-test-case

What's inside

Skill name
run-test-case
Description
Execute a single UI test case and return its result. Works across iPhone, iPad, and macOS — pass the platform param to adjust behavior. Requires the app to already be built and running before calling this skill. Returns: pass, flaky, or fail — with screenshot path, logs, and root cause on failure.
License
MIT
Instructions
132 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Skill: run-test-case

## Input
- `test_case` — one parsed test case object (id, name, feature, steps, expect)
- `platform` — `"iphone"` | `"ipad"` | `"macos"`
- `udid` — simulator UDID *(omit for macOS)*
- `bundle_id` — app bundle identifier
- `report_dir` — path to write screenshots, e.g. `tests/reports/screenshots`

---

## Step 1: Reset app state

**iPhone / iPad:**

Navigate to a known base state before running:

```bash
axe tap --label Dashboard --udid <UDID> --wait-timeout 3
```

If this fails (modal blocking, crash):
```bash
xcodebuildmcp simulator stop --simulator-id <UDID> --bundle-id <bundle>
xcodebuildmcp simulator launch-app --simulator-id <UDID> --bundle-id <bundle>
```
Then poll until interactive (max 30s, retry every 3s):
```bash
axe describe-ui --udid <UDID>
# Success: root element has "type": "Application"
```

**macOS:** Skip reset. macOS apps do not have a tab bar to navigate to. Proceed directly to Step 2.

---

## Step 2: Execute interactions

Translate all YAML steps into a single axe batch call via stdin.

**iPhone / iPad:**
```bash
axe batch --udid <UDID> --stdin << 'EOF'
tap --label <label> --wait-timeout 5
type '<text>'
EOF
```

**macOS:**
```bash
axe batch --stdin << 'EOF'
tap --label <label> --wait-timeout 5
type '<text>'
EOF
```

Rules:
- Always use `--stdin`, not `--step` or `--file`
- Add `--wait-timeout` to every `tap` and `navigate` step

---

## Step 3: Verify expected state

Run `describe-ui` in a **separate** call (batch is fire-and-forget):

**iPhone / iPad:** `axe describe-ui --udid <UDID>`
**macOS:** `axe describe-ui`

For each `expect` entry:
- `ui_contains: "X"` → assert element with `AXLabel == "X"` exists
- `element_not_exists: "X"` → assert NO element with `AXLabel == "X"` exists

If all pass, capture screenshot and return ✅:

**iPhone / iPad:** `axe screenshot --udid <UDID> --output <report_dir>/<id>-pass.png`
**macOS:** `axe screenshot --output <report_dir>/<id>-pass.png`

---

## Step 4: Handle failure

If any assertion fails:

1. Capture error screenshot:
   - iPhone/iPad: `axe screenshot --udid <UDID> --output <report_dir>/<id>-error.png`
   - macOS: `axe screenshot --output <report_dir>/<id>-error.png`

2. Start log capture:
   ```bash
   xcodebuildmcp logging start-simulator-log-capture \
     --simulator-id <UDID> \       # omit on macOS
     --bundle-id <bundle> \
     --capture-console true
   # Save the returned logSessionId
   ```

3. Retry the **failing step only** with `--wait-timeout 5`, then re-run `describe-ui` and assert again.

4. Stop log capture:
   ```bash
   xcodebuildmcp logging stop-simulator-log-capture --log-session-id <logSessionId>
   ```

5. Determine result:
   - Retry passed → ⚠️ flaky
   - Retry failed → ❌ fail

6. Suggest root cause from logs:
   - "Element not found" → label changed, wrong screen, animation still running
   - "Multiple matches" → use coordinate-based tap fallback
   - Crash in logs → report crash type

---

## Output

```
{

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 run-test-case 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 run-test-case?

CallGet help
Cite this page

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