Hire an AI performance benchmark planner

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A baseline table of what to measure, the number today (or MISSING) and the target.
• A test plan with load, stress, spike and endurance scenarios, and how many runs to do.
• A k6 test script to adapt for your path, with notes on what to change first.
• A ranked list of bottlenecks, drawn only from results you paste.
• Ranked fixes with the effort and the likely gain, marked as an estimate.
• A status against your goal: MEETS, FAILS or NOT DETERMINED, with the reason.

How it does the job well

• No invented figures. The original's examples (such as 850 ms to 180 ms or a saving in dollars) are not facts about this task. Do not repeat them as results.
• Do not claim a conversion, sales or cost gain unless the user gives data that shows it.
• Targets in the original profile are examples. Use the user's goal.
• Read the existing code, its conventions and its tests before changing anything. Match the project's patterns.
• Make the smallest change that fully solves the request. Keep unrelated refactors out.
• Reproduce a bug before fixing it, and add a test that fails without the fix.
• Treat input from users, files and networks as untrusted. Validate it at the boundary.

Mistakes it avoids

• Claiming code works without running it or its tests.
• Inventing APIs, package versions or settings instead of checking the installed ones.
• Changing behaviour outside the request, such as reformatting whole files or renaming public interfaces.

What a good result looks like

An example, not your task: You are about to launch, run a sale or send a big email, and need to know if the site will hold.

• Baseline. What to measure, today's number or MISSING, and the target for each.
• Test plan. Load, stress, spike and endurance scenarios, with users, length, runs and pass rules.
• Test script. A k6 script draft with checks and limits, and the lines you must change first.
• Results read. Each number you pasted, set against the baseline and the goal.
• Bottlenecks. The layers the numbers point to, with the evidence for each.
• Fixes, ranked. Fixes ordered by gain and effort, and the re-test that would prove each one.

How the work is checked

• The changed files build, and the relevant tests and linters pass. The commands and results are shown.
• Each change is explained in one line with its reason, and risky areas are named.
• Any check that could not run is reported as NOT_RUN with what it needs.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

• Set the baseline. It lists what to measure, the critical user paths, the goal for each, and how to record today's numbers.
• Design the tests. It plans load, stress, spike and endurance runs, a realistic mix of traffic, and the number of runs needed for a fair result.
• Write the script. It drafts a k6 script with checks for status and content, and thresholds that fail the run when the goal is missed.
• Read your results. It reads the numbers you paste, such as the 95th percentile, the error rate and the requests per second, and compares them with the baseline.
• Find the bottleneck. It looks at the database, the app code, the servers, the network and outside services, and names the layer the numbers point to.
• Rank the fixes. It orders fixes by gain against effort, and says which result would prove each fix worked.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id testing-performance-benchmarker only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/testing-performance-benchmarker/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• What to test, such as a page link, an API endpoint or a path like login then dashboard.
• Your speed goal, such as "95 percent of requests under 500 ms" (optional). Without one it proposes a goal and marks it as a proposal.
• Where you will test (staging or production) and who owns that system.
• Past numbers, such as a Lighthouse report, k6 output or server logs (optional).
• How many users you expect at peak (optional).

Helpful context (optional)

• A Lighthouse or PageSpeed report for the same page.
• A week of server or hosting logs.

Tools and access

• Claude Code or Codex: They can write the k6 script to a file and run it on a test system, if you allow it.
• Claude, ChatGPT or Gemini: In a plain chat they can plan the test and read the results you paste, but they cannot run the test.

Functions and deliverables

• Performance benchmark planner: Plan a repeatable speed and load test for your site or API. Get baselines, a test script, bottlenecks and ranked fixes from your own numbers.
  • A baseline table of what to measure, the number today (or MISSING) and the target.
  • A test plan with load, stress, spike and endurance scenarios, and how many runs to do.
  • A k6 test script to adapt for your path, with notes on what to change first.
  • A ranked list of bottlenecks, drawn only from results you paste.
  • Ranked fixes with the effort and the likely gain, marked as an estimate.
  • A status against your goal: MEETS, FAILS or NOT DETERMINED, with the reason.
  Source: Michael Sitarzewski and Agency Agents contributors.
• Website performance fix ranker: Rank your store speed fixes by orders gained per hour of work. Give it your audit problems and sales numbers. You get a plan for this week and next month.
  • A ranked fix list with expected gain as a range, effort, risk and who does it
  • The money at stake written as orders and revenue per month
  • A plan: top three this week, next five next month, the rest parked with a reason
  • What to measure before and after each fix
• Website speed repair planner: Share speed issues, traffic and sales figures. Get fixes ranked by effort and reach, with assumed gain ranges clearly marked.
  • Three fixes for this week
  • Five for next month, the rest parked
  • A range of extra orders for each
  • A check to run on your own data first
• Page speed fixer: Share PageSpeed or Lighthouse results and project access. Get ordered fixes, risk notes and a checklist for fresh test results.
  • Ranked list of issues by risk
  • Code fixes in ordered batches
  • Re-test after each batch
  • Notes on what changed
  Source: sickn33.
• AI project context organiser: Share your project and next task. Get a short rules file, a focused file list and a clear handoff for later sessions.
  • A ready rules file for your project
  • A list of which files to load for each task
  • Rules for when to reset or trim the session
  • A checklist for spotting drifting answers
  Source: Addy Osmani.

Tasks you can use it for

• You are about to launch, run a sale or send a big email, and need to know if the site will hold.
• Pages or an API feel slow and you want numbers before you pay for fixes.
• You made a speed fix and want proof that it helped.
• Your developer asks for "a performance budget" and you need one you can check each release.

Limits to check before starting

• You want to run a load test on a live production site without the owner's okay: stop, and test a staging copy instead.
• You want to read a Shopify speed report in plain words: use the Store speed report analyst.
• You want code changes that make one page faster: use the Website speed tuner.
• You want to check that an API returns the right answers: use the API test planner.
• You have test results to sort by failure cause: use the Test results analyst.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the pack. Add it to your AI as a skill, or paste SKILL.md and then references/source-agent.md into a new chat.
• Say what you want tested and your goal. Ask for a plan first, such as: Plan a baseline and a test for this page. Do not invent numbers.
• Check the baseline table. Fill in the MISSING numbers from your own tools, such as Lighthouse, your host's dashboard or your logs.
• Run the test yourself. You need k6 (free) and a staging copy of your system. Claude Code or Codex can run it for you if you allow it.
• Paste the raw results back. Ask for the bottleneck list and the ranked fixes.
• After each fix, run the same test again and paste the new numbers. Ask for a before and after comparison.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/testing-performance-benchmarker for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.