Claude Skill

performance-result-analysis

Use this skill when you need to interpret performance results, evidence quality, and risk without inventing conclusions; triggers include performance result analysis.

LLM Mart · 0 points · 1 views 0 listing impressions 0 install-command copies
Download naodeng-awesome-qa-skills-skills_en_testing-types_performance-result-analysis-9df700b.zip · 7 KB

Install

skills CLI npx skills add https://github.com/naodeng/awesome-qa-skills/tree/main/skills/en/testing-types/performance-result-analysis
Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install naodeng-awesome-qa-skills@llmmart
Git git clone https://github.com/naodeng/awesome-qa-skills.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole naodeng/awesome-qa-skills collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

Performance Result Analysis

When to Use

  • Use this skill when you need to interpret performance-test results for target attainment, knees, error patterns, and capacity risk.
  • Use it to review an existing plan, result, or evidence set and produce actionable improvements.
  • Use it when context is incomplete but a bounded first pass is still valuable.

Output Format Options

  • Default to Markdown for review, execution, and incremental refinement.
  • When the user requests tables, CSV, JSON, or ticket fields, preserve risk, evidence, priority, and boundary information.
  • For machine-consumed output, confirm the schema, enums, and required fields first.

How to Use

  1. Read and follow prompts/performance-result-analysis.md, including its input contract, execution rules, minimum coverage, and output order.
  2. Add only context that changes the decision: scope, environment, version, constraints, evidence, and success criteria.
  3. Audit the input, then separate confirmed facts, working assumptions, and open questions.
  4. Rank by risk and evidence strength, and produce an artifact that can be executed or reviewed directly.
  5. If information is missing, deliver a bounded first pass and state which conclusions remain unsupported.

Reference Files

  • Always read prompts/performance-result-analysis.md; it is the complete execution specification for this skill.
  • For evaluation or regression, read evals/eval.yaml and the relevant cases under evals/cases/.
  • Load references/, examples/, scripts/, or output-formats.md only when those directories exist and the task needs them.

Core Constraints

  • do not rely on average latency
  • validate the test run first
  • state workload and environment boundaries for conclusions
  • Never invent system behavior, fields, data, metrics, or root causes absent from the evidence.
  • Link important conclusions to evidence; mark unsupported conclusions as hypotheses with a verification method.
  • Explain priority using business impact, likelihood, or detectability.

Delivery Checklist

  • Covered: target attainment, stage stability, latency distribution, throughput, errors, resources, saturation point, data validity.
  • Separated facts, assumptions, gaps, and recommendations.
  • Gave high-risk items a priority, evidence basis, owner or next action.
  • Defined verifiable decision criteria instead of generic advice.
  • Performed no unauthorized production writes or destructive actions.

Common Pitfalls

  • Listing checks without preconditions, expected outcomes, or evidence.
  • Marking everything high priority and avoiding tradeoffs.
  • Substituting tool names or generic theory for domain reasoning.
  • Refusing incomplete input, or pretending incomplete evidence supports certainty.

Best Practices

  • Start with paths most likely to cause business loss, safety issues, or release blockage.
  • Reduce uncertainty through the smallest verifiable experiment and record reproduction conditions.
  • Make the artifact executable and independently reviewable by another engineer.
Files (awesome-qa-skills)
  • agents
    • openai.yaml 322 B
      Loading…
  • evals
    • cases
      • basic-success.yaml 861 B
        Loading…
      • edge-incomplete-input.yaml 902 B
        Loading…
      • edge-risk-priority.yaml 861 B
        Loading…
      • review-met-target-control.yaml 918 B
        Loading…
      • review-stage-targets-and-denominator.yaml 2 KB
        Loading…
    • eval.yaml 666 B
      Loading…
  • prompts
    • performance-result-analysis.md 3.3 KB
      Loading…
  • SKILL.md 3.5 KB
    ---
    name: performance-result-analysis
    description: Use this skill when you need to interpret performance results, evidence quality, and risk without inventing conclusions; triggers include performance result analysis.
    license: PolyForm-Noncommercial-1.0.0
    metadata:
      version: "1.0.0"
      compatibility: ""
      author: "Awesome QA Skills contributors"
      language: "en"
      category: "testing-types"
      source: "https://github.com/naodeng/awesome-qa-skills"
      license-url: "https://polyformproject.org/licenses/noncommercial/1.0.0"
    ---
    
    # Performance Result Analysis
    
    ## When to Use
    
    - Use this skill when you need to interpret performance-test results for target attainment, knees, error patterns, and capacity risk.
    - Use it to review an existing plan, result, or evidence set and produce actionable improvements.
    - Use it when context is incomplete but a bounded first pass is still valuable.
    
    ## Output Format Options
    
    - Default to Markdown for review, execution, and incremental refinement.
    - When the user requests tables, CSV, JSON, or ticket fields, preserve risk, evidence, priority, and boundary information.
    - For machine-consumed output, confirm the schema, enums, and required fields first.
    
    ## How to Use
    
    1. Read and follow `prompts/performance-result-analysis.md`, including its input contract, execution rules, minimum coverage, and output order.
    2. Add only context that changes the decision: scope, environment, version, constraints, evidence, and success criteria.
    3. Audit the input, then separate confirmed facts, working assumptions, and open questions.
    4. Rank by risk and evidence strength, and produce an artifact that can be executed or reviewed directly.
    5. If information is missing, deliver a bounded first pass and state which conclusions remain unsupported.
    
    ## Reference Files
    
    - Always read `prompts/performance-result-analysis.md`; it is the complete execution specification for this skill.
    - For evaluation or regression, read `evals/eval.yaml` and the relevant cases under `evals/cases/`.
    - Load `references/`, `examples/`, `scripts/`, or `output-formats.md` only when those directories exist and the task needs them.
    
    ## Core Constraints
    
    - do not rely on average latency
    - validate the test run first
    - state workload and environment boundaries for conclusions
    - Never invent system behavior, fields, data, metrics, or root causes absent from the evidence.
    - Link important conclusions to evidence; mark unsupported conclusions as hypotheses with a verification method.
    - Explain priority using business impact, likelihood, or detectability.
    
    ## Delivery Checklist
    
    - [ ] Covered: target attainment, stage stability, latency distribution, throughput, errors, resources, saturation point, data validity.
    - [ ] Separated facts, assumptions, gaps, and recommendations.
    - [ ] Gave high-risk items a priority, evidence basis, owner or next action.
    - [ ] Defined verifiable decision criteria instead of generic advice.
    - [ ] Performed no unauthorized production writes or destructive actions.
    
    ## Common Pitfalls
    
    - Listing checks without preconditions, expected outcomes, or evidence.
    - Marking everything high priority and avoiding tradeoffs.
    - Substituting tool names or generic theory for domain reasoning.
    - Refusing incomplete input, or pretending incomplete evidence supports certainty.
    
    ## Best Practices
    
    - Start with paths most likely to cause business loss, safety issues, or release blockage.
    - Reduce uncertainty through the smallest verifiable experiment and record reproduction conditions.
    - Make the artifact executable and independently reviewable by another engineer.
    

Comments (0)

Sign in to join the conversation.

No comments yet.

Reviews (0)

No reviews yet.