Performance Test Builder
Build reviewable k6 HTTP tests from stripped HAR inventories and synthetic request plans, with load profiles, thresholds and result analysis.
Free
Works with the AI Agents you already use
About this skill
A standalone performance-testing skill with a deterministic Python CLI. Turn a stripped HAR inventory into a reviewed synthetic request plan, then generate k6 smoke, normal, peak, spike and soak profiles. Suggest load and threshold budgets with explicit evidence and assumptions, correlate JSON response values, check response content, and analyze selected k6 summary metrics.
Includes instructions, a fictional HAR JSON and local demo API, a reviewed example plan, generated smoke script and tests. HAR import intentionally removes captured URLs, credentials and payload strings; safe routes and test data must be mapped explicitly. It does not automatically reconstruct a complete journey.
32 Python unit tests and 8 mocked JavaScript runtime tests passed. Native k6 execution and live Claude Code/Codex installation have not been verified. Early version, not a production-qualified benchmark.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
No native k6 run verified. Reviewed synthetic route/data mapping required. No JMeter, arbitrary log parsing, SQL replay, OAuth workflow, browser UI load, or automatic baseline comparison. Aggregate summaries cannot establish root cause or spike recovery.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 3 days ago
- Free with an Agensi account
- Software
Python 3.10+k6 for separately authorized executionNode.js for development tests only
Permissions
File Scopes
Offline generator never starts k6. Generated scripts contact an explicitly configured test target only on separately authorized execution. No automatic production load. Keep raw captures local.