running-smoke-tests
This skill runs smoke tests to verify critical application functionality. It executes pre-defined test suites that check system health, authentication, core features, and external integrations. Use this skill after deployments, upgrades, or significant configuration changes to ensure the application is operational. Trigger this skill using the terms "smoke test" or "st".
Install with Tessl CLI
npx tessl i github:jeremylongshore/claude-code-plugins-plus-skills --skill running-smoke-tests56
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
85%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 is a well-crafted skill description that clearly explains what the skill does (smoke testing for system health, auth, features, integrations) and when to use it (post-deployment/upgrade scenarios). The main weakness is limited trigger term coverage - while 'smoke test' and 'st' are included, common synonyms like 'health check' or 'sanity test' are missing.
Suggestions
Expand trigger terms to include natural variations like 'health check', 'sanity test', 'verify deployment', 'post-deploy check', or 'quick test'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'runs smoke tests', 'executes pre-defined test suites', and specifies what is checked: 'system health, authentication, core features, and external integrations'. | 3 / 3 |
Completeness | Clearly answers both what (runs smoke tests, executes test suites checking health/auth/features/integrations) AND when (after deployments, upgrades, configuration changes) with explicit trigger terms provided. | 3 / 3 |
Trigger Term Quality | Includes 'smoke test' and 'st' as explicit triggers, but misses natural variations users might say like 'health check', 'sanity test', 'quick test', 'verify deployment', or 'post-deploy check'. | 2 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on smoke testing with distinct triggers ('smoke test', 'st') and specific use cases (post-deployment verification), unlikely to conflict with general testing or other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
7%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill content describes what smoke testing is and when to use it, but fails to provide any actionable guidance on how to actually execute smoke tests. It lacks concrete commands, test file locations, actual test code, or specific implementation details. The content reads like documentation about the concept rather than instructions Claude can follow.
Suggestions
Add concrete commands showing how to execute the smoke test suite (e.g., `npm run smoke-test` or `pytest tests/smoke/`)
Include the actual test file locations and structure so Claude knows where tests are defined
Provide example test output showing what pass/fail results look like and how to interpret them
Remove the explanatory sections ('Overview', 'When to Use', 'Best Practices') and replace with executable implementation details
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is verbose and explains concepts Claude already knows (what smoke tests are, when to use them). The 'How It Works' section describes obvious steps, and 'Best Practices' contains generic advice that doesn't add actionable value. | 1 / 3 |
Actionability | No concrete code, commands, or executable guidance is provided. The skill describes what will happen conceptually but never shows how to actually run tests, what test files exist, or what commands to execute. Examples describe outcomes rather than providing actual implementation. | 1 / 3 |
Workflow Clarity | The workflow is vague and abstract ('Execute the smoke test suite'). There are no actual commands, no validation checkpoints, no error handling guidance, and no concrete steps Claude can follow to perform the smoke tests. | 1 / 3 |
Progressive Disclosure | The content is organized into clear sections with headers, but it's a monolithic document with no references to external files for test configurations, test scripts, or detailed documentation. The structure exists but content that should be actionable is instead descriptive. | 2 / 3 |
Total | 5 / 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.
- 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.