control-ui-e2e
Use when testing, fixing, or extending the OpenClaw Control UI GUI with Vitest + Playwright end-to-end checks, mocked Gateway WebSocket flows, mocked dashboard runs, screenshots/videos, or agent-verifiable browser proof.
65
77%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/control-ui-e2e/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description excels at distinctiveness and completeness with a clear 'Use when...' clause and highly specific product/technology references. Its main weakness is that the 'what' portion leans more toward listing technologies and concepts rather than describing concrete actions the skill performs. The description could benefit from more explicit action verbs describing what the skill actually does beyond 'testing, fixing, or extending'.
Suggestions
Replace the generic verbs 'testing, fixing, or extending' with more specific actions like 'writes e2e test cases, debugs test failures, generates Playwright test scripts, captures screenshots for visual regression'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (OpenClaw Control UI GUI testing) and mentions several specific technologies and concepts (Vitest, Playwright, mocked Gateway WebSocket flows, screenshots/videos), but it reads more like a list of technologies than concrete actions. The verbs are limited to 'testing, fixing, or extending' which are somewhat generic. | 2 / 3 |
Completeness | The description explicitly starts with 'Use when...' providing clear trigger conditions, and the rest describes what the skill covers (testing/fixing/extending with specific tools and approaches). Both 'what' and 'when' are addressed. | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms a user would say: 'testing', 'fixing', 'Vitest', 'Playwright', 'end-to-end', 'WebSocket', 'screenshots', 'videos', 'browser proof', 'mocked', 'dashboard runs'. These are terms a developer working on this specific UI would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific product name 'OpenClaw Control UI GUI' combined with the specific tech stack (Vitest + Playwright) and domain-specific concepts (Gateway WebSocket flows, mocked dashboard runs). Very unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable E2E testing skill with excellent concrete code examples and specific commands. Its main weaknesses are moderate verbosity in the visual proof section and a lack of explicit validation checkpoints in the multi-step workflows. The mock pattern example is particularly strong and immediately usable.
Suggestions
Tighten the 'Visual Proof Default' section by removing explanatory phrases like 'not only demo capture' and condensing the bullet points into a more compact checklist format.
Add explicit validation checkpoints to the recording workflow, e.g., 'Verify mock server is responding before proceeding to capture' and structured error recovery steps.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but has some verbose sections. The 'Visual Proof Default' section is somewhat wordy and could be tightened. The 'Test Shape' bullet about preferring existing .browser.test.ts tests is useful context but slightly padded. Overall respects Claude's intelligence but could trim ~20% without losing clarity. | 2 / 3 |
Actionability | Provides fully executable code examples including the mock pattern with real TypeScript, concrete bash commands for running tests, specific file paths, specific selectors, and exact API calls like `gateway.waitForRequest('chat.send')`. The mock pattern example is copy-paste ready and demonstrates the full flow. | 3 / 3 |
Workflow Clarity | The mock pattern provides a clear sequence, and the visual proof section outlines steps. However, the recording-as-validation workflow lacks explicit validation checkpoints and error recovery loops — it mentions 'if the recorder fails or shows surprising behavior, stop, fix...' but doesn't provide structured feedback loops. The overall document reads more as a collection of guidelines than a clearly sequenced workflow. | 2 / 3 |
Progressive Disclosure | The content is reasonably well-organized with clear section headers (Test Shape, Commands, Visual Proof Default, Mock Pattern, Standalone Recording). However, there are no references to external files for deeper content, and the Visual Proof Default section is quite long and could be split out. No bundle files are provided, so there's no progressive structure beyond this single file. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- openclaw/openclaw
- Commit
982e888
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.