AD perf-tester
Performance and load testing for APIs and web services. Design test scenarios, generate k6/locust/JMeter scripts, analyze response times, throughput, error rates, and identify bottlenecks. Follows industry-standard methodology (RFC 6390, ISO 25010). Use when: (1) load/stress/spike/soak testing, (2) writing k6 or locust scripts, (3) analyzing performance metrics (P50/P95/P99, TPS, error rate), (4) capacity planning, (5) performance baseline comparison, (6) SLA validation, (7) "性能测试", "压测", "负载测试", "并发测试", "TPS", "响应时间", "k6脚本", "locust脚本", "JMeter". NOT for: code-level profiling (use profiler tools), infrastructure monitoring (use Prometheus/Grafana), or functional API testing (use api-tester).
As a process D 47/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 47/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 100Steps. 9 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2131 tokens
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 702: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 9 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 97.