agentleFS
Sign inStart free
4taras44taras4/claude-simulator-ui-tester/skills/ui-test/SKILL.md

ui-test

Skill1 starsChanged 4 months agoMITView on GitHub

Run UI test cases on the Xcode-selected iOS Simulator and get a visual pass/fail report, or scaffold a new test case from the template. Use when the user says "run ui tests", "test this feature on the simulator", "validate the screen", "is the UI good", or after implementing a UI feature that needs validation.

  • Installs packages

5 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions5 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 5

    1. zly2006/zhihu-plus-plus★ 4.4ksame name
    2. browserbase/agent-browse★ 3.7ksame name
    3. thefrederiksen/cc-director★ 110same name
    4. thefrederiksen/devthrottle★ 110same name
    5. Zengxiansheng007/skills-old★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If the project has no ui-tests/TEMPLATE.md, bootstrap it before anything else:

    line 20
  2. Very specific:

    Create ui-tests/cases/ and ui-tests/reports/screenshots/.

    line 21
  3. Distinctive:

    If failures look like implementation bugs and the user asked you to implement the feature, fix the code, then re-run only the failed cases …

    line 39
  4. Very specific:

    Create ui-tests/cases/TC-<next-number>-<kebab-feature>.md from the template, filling in steps and checks from what you know about the …

    line 44

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/ui-test — simulator UI testing

Arguments ($ARGUMENTS):

  • (empty) or all — run every case in ui-tests/cases/
  • <case-id or keyword> — run only matching cases (match against file name, id:, feature:, or title)
  • new <feature name> — scaffold a new test case, don't run anything
  • init — set up ui-tests/ in this project without running anything

First run in a project (auto-init)

If the project has no ui-tests/TEMPLATE.md, bootstrap it before anything else:

  1. Create ui-tests/cases/ and ui-tests/reports/screenshots/.
  2. Copy TEMPLATE.md (and TC-001-app-launch-smoke.md into cases/) from this plugin's bundled templates/ directory — resolve it via ${CLAUDE_PLUGIN_ROOT}/../templates/ relative to this skill, or locate the installed plugin under ~/.claude/plugins/.
  3. Prerequisite check: xcodebuildmcp --version — if missing, install with npm install -g xcodebuildmcp@latest (or brew install getsentry/xcodebuildmcp/xcodebuildmcp).

Mode: run

  1. Glob ui-tests/cases/*.md and select the cases matching $ARGUMENTS. If none match, list available cases and stop.
  2. Confirm a simulator is booted (xcrun simctl list devices booted). If not, note that the agent will boot one.
  3. Launch the simulator-ui-tester agent (Agent tool, subagent_type: simulator-ui-tester, run synchronously) with a prompt containing:
    • the absolute paths of the selected case files,
    • the project/scheme if known from context or CLAUDE.md,
    • whether a fresh build is required (yes if source files changed this session),
    • the report naming: ui-tests/reports/<YYYY-MM-DD>-<short-run-name>.md. For 3+ independent cases, split across up to 3 parallel agents (they share one simulator — tell each agent the app may be relaunched by others, so each case must start with its own launch/reset).
  4. Relay the agent's results to the user: overall pass/fail counts, each failure with concrete observed reason and screenshot path, link to the report file.
  5. If failures look like implementation bugs and the user asked you to implement the feature, fix the code, then re-run only the failed cases until they pass or the failure is a test-case/design question for the user.

Mode: new

  1. Read ui-tests/TEMPLATE.md.
  2. Create ui-tests/cases/TC-<next-number>-<kebab-feature>.md from the template, filling in steps and checks from what you know about the feature (ask the user only if the flow is genuinely unknown).
  3. Show the user the case and remind them it runs with /ui-test TC-<number>.

Conventions

  • Screenshots: ui-tests/reports/screenshots/<case-id>/step-<n>.<ext>
  • Reports: ui-tests/reports/<date>-<run>.md — never overwrite an old report.
  • A case with status: draft in frontmatter is skipped by all unless named explicitly.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free