run-smoke-tests
Run Playwright smoke tests, debug failures, and verify fixes
52
56%
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 ./cursor-team-kit/skills/run-smoke-tests/SKILL.mdQuality
Discovery
40%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description identifies a clear niche around Playwright smoke testing, which gives it good distinctiveness. However, it lacks an explicit 'Use when...' clause and could benefit from more specific actions and broader trigger term coverage to help Claude reliably select it from a large skill set.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks to run Playwright tests, debug e2e test failures, or verify test fixes.'
Include common keyword variations users might say, such as 'e2e tests', 'end-to-end tests', 'browser tests', 'test automation', or 'flaky tests'.
Expand the specific actions listed, e.g., 'analyze test failure logs, capture screenshots on failure, re-run specific test suites, update test selectors'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Playwright smoke tests) and lists some actions (run, debug failures, verify fixes), but doesn't elaborate on specific concrete actions like reading test reports, analyzing error screenshots, or re-running specific test suites. | 2 / 3 |
Completeness | Describes what the skill does (run Playwright smoke tests, debug failures, verify fixes) but has no explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 2, and the 'what' is also fairly thin, placing this at 1. | 1 / 3 |
Trigger Term Quality | Includes 'Playwright', 'smoke tests', 'debug failures', and 'verify fixes' which are relevant keywords, but misses common variations like 'e2e tests', 'end-to-end', 'browser tests', 'test automation', or 'flaky tests' that users might naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Playwright smoke tests' is quite specific and creates a clear niche that is unlikely to conflict with other skills; Playwright is a distinct testing framework and 'smoke tests' further narrows the scope. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A concise and well-structured skill that provides useful npm commands and sensible guardrails. However, the workflow steps are too abstract—particularly around debugging failures and inspecting traces—which limits actionability. Adding concrete debugging commands (e.g., how to view Playwright traces, specific log locations) would significantly improve the skill.
Suggestions
Add concrete commands for debugging failures, e.g., `npx playwright show-trace trace.zip` or specific log file paths to inspect.
Make workflow step 3 more actionable by specifying how to inspect traces/logs (exact commands, file locations, or patterns to look for).
Include a brief example of a common failure pattern and its fix to make the 'Apply a minimal fix' step more concrete.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. No unnecessary explanations of what smoke tests are or how Playwright works. Every section earns its place and assumes Claude's competence. | 3 / 3 |
Actionability | Provides concrete npm commands which are useful, but the workflow steps (1-4) are fairly generic and abstract—'Build prerequisites for the target app' and 'inspect traces/logs and isolate the root cause' lack specific commands or techniques. No executable code for debugging or trace inspection. | 2 / 3 |
Workflow Clarity | The workflow has a clear sequence (build → run → debug → fix → rerun) with an implicit feedback loop in step 4, but lacks explicit validation checkpoints and concrete guidance on how to inspect traces/logs or determine root cause. The 'rerun until stable' step is vague. | 2 / 3 |
Progressive Disclosure | For a simple, short skill with no bundle files, the content is well-organized into clear sections (Trigger, Workflow, Example Commands, Guardrails, Output) that are easy to scan and navigate. | 3 / 3 |
Total | 10 / 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
- cursor/plugins
- Commit
b8f2564
- 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.