blazemeter-performance-testing
Comprehensive guide for BlazeMeter Performance Testing, including load configuration, reporting, JMeter configuration, Taurus, scenarios, and advanced features. Use when working with Performance tests for (1) Configuring load settings and distribution, (2) Creating and running tests (JMeter, Browser, URL/API, Multi-Test), (3) Analyzing reports and filtering data, (4) Configuring JMeter properties and scenarios, (5) Using Taurus for test configuration, (6) Advanced features (AI Log Analysis, APM Integration, Network Emulation, Mainframe Testing), (7) Troubleshooting test issues, or any other Performance Testing tasks.
61
71%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./resources/skills/blazemeter-performance-testing/SKILL.mdQuality
Discovery
100%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 strong skill description that clearly identifies the BlazeMeter performance testing domain, lists specific concrete capabilities across seven numbered categories, and includes an explicit 'Use when' clause with detailed trigger scenarios. The description uses proper third-person voice and includes numerous natural trigger terms that users would employ when seeking help with BlazeMeter or performance testing tasks.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: configuring load settings, creating/running tests (with specific types), analyzing reports, configuring JMeter properties, using Taurus, AI Log Analysis, APM Integration, Network Emulation, Mainframe Testing, and troubleshooting. | 3 / 3 |
Completeness | Clearly answers both 'what' (comprehensive guide for BlazeMeter Performance Testing with specific capabilities listed) and 'when' (explicit 'Use when working with Performance tests for...' clause with seven numbered trigger scenarios plus a catch-all). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'BlazeMeter', 'Performance Testing', 'load', 'JMeter', 'Taurus', 'reports', 'API', 'Browser', 'Network Emulation', 'Mainframe Testing', 'APM Integration'. These cover a wide range of terms a user working with BlazeMeter would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific focus on BlazeMeter as a product, combined with specific tools like JMeter and Taurus. Unlikely to conflict with generic testing or other performance tool skills due to the clear product-specific niche. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is well-structured as a navigation hub with clear progressive disclosure to reference files, and provides useful MCP tool integration details. However, it suffers from significant verbosity with redundant sections (e.g., 'When to Use Each Reference' duplicates reference file descriptions), lacks concrete executable examples with actual parameter values, and the workflows miss validation checkpoints needed for reliable test execution.
Suggestions
Remove the redundant 'When to Use Each Reference' and 'When to Use MCP Tools' sections, as this information is already conveyed by the reference file descriptions and tool listings respectively.
Add concrete examples with actual parameter values for MCP tool calls, e.g., show a real `blazemeter_tests` call with action `configure_load` including sample users/duration/ramp-up values.
Add validation checkpoints to workflows, such as verifying test configuration after creation (read back the test) and checking execution status before retrieving results.
Replace the 'Quick Start' section with a genuinely actionable quick-start example showing a minimal end-to-end test creation and execution flow with specific tool calls.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is verbose and repetitive. The 'When to Use MCP Tools' section restates what's already obvious from the tool descriptions. The 'When to Use Each Reference' section at the bottom repeats what's already stated in the Reference Files section headers. The 'Quick Start' section is just a table of contents, not actionable guidance. Multiple sections explain things Claude can infer. | 1 / 3 |
Actionability | The MCP tool descriptions provide concrete tool names, actions, and required arguments, and the example workflows give step-by-step sequences. However, there are no executable code examples, no actual parameter values shown, and no concrete input/output examples demonstrating real usage patterns. | 2 / 3 |
Workflow Clarity | The 'Creating and Running a Performance Test' and 'Analyzing Test Results' workflows provide clear sequences, but they lack validation checkpoints. There's no guidance on what to do if a step fails, no verification that load configuration was applied correctly before starting execution, and no feedback loops for error recovery. | 2 / 3 |
Progressive Disclosure | The skill has a clear overview structure with well-organized, one-level-deep references to seven separate reference files. Each reference is clearly signaled with descriptive labels indicating what topics it covers, making navigation straightforward. | 3 / 3 |
Total | 8 / 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
- Blazemeter/bzm-mcp
- Commit
6395eba
- 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.