Publish Sign in

Performance Test Design Agent Skill

Design performance test cases and test data specifications for an entire system — from raw system documentation (BRD, FRD, use cases…

Install this skill Read the source first Free Written by phatnguyen975
Context cost
96.9k tokensestimated from the bundle, loaded when it triggers
Bundle
78 files · 387.7 kBtext throughout, nothing executable
Licence
MITthe author’s own terms
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

Design performance test cases and test data specifications for an entire system — from raw system documentation (BRD, FRD, use cases, NFR/SLA docs, architecture docs) to implementer-ready Performance Test Case Specifications — without depending on any specific load-testing tool (JMeter, k6, Gatling, LoadRunner). Use whenever the user needs to discover which Operational Profiles a system needs tested, design load/stress/spike/soak/scalability/volume test scenarios, define workload models, calculate virtual users and throughput, or produce test data specifications from requirements.

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

documentationperformancesecuritytesting
Filed under

Security & Testing

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md23.1 kB · preview
--- name: performance-test-design ---
6# Performance Test Design Skill
7
8## Overview
9
10This skill takes a system's requirements documentation and turns it into a complete set of implementer-ready **Performance Test Case Specifications** — one per Operational Profile the system needs tested — following the ISTQB Certified Tester Performance Testing (CT-PT) syllabus process, extended with real-world workload-modeling practice beyond what the syllabus covers at a summary level.
11
12The process has exactly **two phases**:
13
141. **Phase 1 — Operational Profile Discovery:** Read the system's documentation once, and produce a reviewed, approved list of every Operational Profile the system needs performance-tested.
152. **Phase 2 — Per-Profile Test Case Design:** For each approved profile, in order, run it through four dependent steps (profile analysis → load profile design → throughput/concurrency analysis → test case specification) to produce that profile's complete design, then pause for human review before moving to the next profile.
16
17This skill is the **design layer** — it stops at the specification. It never writes JMeter/k6/Gatling/LoadRunner code, and it never picks a tool.
18
19## When to Use
20
21- Starting performance test design for a system (or a release/module of one) from its requirements documentation, before any scripting begins.
22- Discovering and enumerating the full set of Operational Profiles a system needs tested — not just designing one test case in isolation.
23- Translating NFRs/SLAs into concrete, measurable, per-transaction test case specifications.
24- Determining defensible virtual-user counts, throughput targets, and think-time values — with the calculation shown, not guessed.
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md2,931 words
Files78
LicenceMIT
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈270
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
96,655
on trigger
The instruction body and 77 supporting files, read only when the skill fires.
48.5%
of a 200k window
Ten skills this size would not fit in the window together.
050k100k150k200k context window

96.9k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

78 files, 387.7 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md23.1 kB
  • LICENSE1.1 kB
  • README.md13.9 kB
  • examples/operational-profiles.md20.9 kB
  • examples/README.md11.4 kB
  • examples/PROF-01-registered-customer-browse-checkout/p1-profile-analysis.md11.7 kB
  • examples/PROF-01-registered-customer-browse-checkout/p2-load-profile.md7.8 kB
  • examples/PROF-01-registered-customer-browse-checkout/p3-workload-numbers.md8.9 kB
  • examples/PROF-01-registered-customer-browse-checkout/p4-test-data-specification.md11.9 kB
  • examples/PROF-01-registered-customer-browse-checkout/test-case-spec.md9.0 kB
  • examples/PROF-02-guest-customer-quick-checkout/p1-profile-analysis.md12.4 kB
  • examples/PROF-02-guest-customer-quick-checkout/p2-load-profile.md5.6 kB
  • examples/PROF-02-guest-customer-quick-checkout/p3-workload-numbers.md6.7 kB
  • examples/PROF-02-guest-customer-quick-checkout/p4-test-data-specification.md8.5 kB
  • examples/PROF-02-guest-customer-quick-checkout/test-case-spec.md6.6 kB
  • examples/PROF-03-warehouse-staff-order-fulfillment/p1-profile-analysis.md12.3 kB
  • examples/PROF-03-warehouse-staff-order-fulfillment/p2-load-profile.md8.7 kB
  • examples/PROF-03-warehouse-staff-order-fulfillment/p3-workload-numbers.md11.6 kB
  • examples/PROF-03-warehouse-staff-order-fulfillment/p4-test-data-specification.md12.1 kB
  • examples/PROF-03-warehouse-staff-order-fulfillment/test-case-spec.md7.2 kB
  • examples/PROF-04-system-regional-inventory-reconciliation/p1-profile-analysis.md10.1 kB
  • examples/PROF-04-system-regional-inventory-reconciliation/p2-load-profile.md6.5 kB
  • examples/PROF-04-system-regional-inventory-reconciliation/p3-workload-numbers.md7.6 kB
  • examples/PROF-04-system-regional-inventory-reconciliation/p4-test-data-specification.md8.6 kB
  • examples/PROF-04-system-regional-inventory-reconciliation/test-case-spec.md6.4 kB
  • phases/phase-1-operational-profile-discovery/anti-patterns.md1.8 kB
  • phases/phase-1-operational-profile-discovery/best-practices.md1.6 kB
  • phases/phase-1-operational-profile-discovery/output-quality-checklist.md1.8 kB
  • phases/phase-1-operational-profile-discovery/output-template.md1.3 kB
  • phases/phase-1-operational-profile-discovery/README.md2.7 kB
  • phases/phase-2-per-profile-test-design/README.md3.5 kB
  • phases/phase-1-operational-profile-discovery/resources/profile-types-reference.md2.9 kB
  • phases/phase-1-operational-profile-discovery/techniques/profile-boundary-definition.md6.1 kB
  • phases/phase-1-operational-profile-discovery/techniques/profile-prioritization.md5.4 kB
  • phases/phase-1-operational-profile-discovery/techniques/system-document-analysis.md5.5 kB
  • phases/phase-2-per-profile-test-design/step-1-profile-analysis/anti-patterns.md1.3 kB
  • phases/phase-2-per-profile-test-design/step-1-profile-analysis/best-practices.md1.5 kB
  • phases/phase-2-per-profile-test-design/step-1-profile-analysis/output-quality-checklist.md1.2 kB
  • phases/phase-2-per-profile-test-design/step-1-profile-analysis/output-template.md1.0 kB
  • phases/phase-2-per-profile-test-design/step-1-profile-analysis/README.md2.4 kB
  • phases/phase-2-per-profile-test-design/step-2-load-profile-design/anti-patterns.md0.7 kB
  • phases/phase-2-per-profile-test-design/step-2-load-profile-design/best-practices.md0.7 kB
  • phases/phase-2-per-profile-test-design/step-2-load-profile-design/output-quality-checklist.md0.9 kB
  • phases/phase-2-per-profile-test-design/step-2-load-profile-design/output-template.md0.7 kB
  • phases/phase-2-per-profile-test-design/step-2-load-profile-design/README.md1.9 kB
  • phases/phase-2-per-profile-test-design/step-3-throughput-concurrency/anti-patterns.md1.1 kB
  • phases/phase-2-per-profile-test-design/step-3-throughput-concurrency/best-practices.md1.1 kB
  • phases/phase-2-per-profile-test-design/step-3-throughput-concurrency/output-quality-checklist.md1.5 kB
  • phases/phase-2-per-profile-test-design/step-3-throughput-concurrency/output-template.md1.1 kB
  • phases/phase-2-per-profile-test-design/step-3-throughput-concurrency/README.md1.3 kB
  • phases/phase-2-per-profile-test-design/step-4-test-case-specification/anti-patterns.md0.9 kB
  • phases/phase-2-per-profile-test-design/step-4-test-case-specification/best-practices.md0.8 kB
  • phases/phase-2-per-profile-test-design/step-4-test-case-specification/output-quality-checklist.md1.6 kB
  • phases/phase-2-per-profile-test-design/step-4-test-case-specification/output-template-data-spec.md1.0 kB
  • phases/phase-2-per-profile-test-design/step-4-test-case-specification/output-template-test-case-spec.md2.9 kB
  • phases/phase-2-per-profile-test-design/step-4-test-case-specification/README.md1.9 kB
  • phases/phase-2-per-profile-test-design/step-1-profile-analysis/resources/common-failure-modes-reference.md2.1 kB
  • phases/phase-2-per-profile-test-design/step-1-profile-analysis/resources/data-gathering-sources.md2.4 kB
  • phases/phase-2-per-profile-test-design/step-1-profile-analysis/techniques/persona-behavioral-detailing.md3.5 kB
  • phases/phase-2-per-profile-test-design/step-1-profile-analysis/techniques/protocol-and-system-analysis.md4.3 kB
  • phases/phase-2-per-profile-test-design/step-1-profile-analysis/techniques/task-frequency-mapping.md6.6 kB
  • phases/phase-2-per-profile-test-design/step-1-profile-analysis/techniques/transaction-identification.md3.9 kB
  • phases/phase-2-per-profile-test-design/step-1-profile-analysis/techniques/transaction-mix-design.md5.5 kB
  • phases/phase-2-per-profile-test-design/step-2-load-profile-design/resources/load-generation-approaches.md1.3 kB
  • phases/phase-2-per-profile-test-design/step-2-load-profile-design/resources/performance-metrics-reference.md1.2 kB
  • phases/phase-2-per-profile-test-design/step-2-load-profile-design/techniques/load-shape-design.md3.6 kB
  • phases/phase-2-per-profile-test-design/step-2-load-profile-design/techniques/nfr-to-acceptance-criteria-mapping.md4.1 kB
  • phases/phase-2-per-profile-test-design/step-2-load-profile-design/techniques/test-type-selection.md7.0 kB
  • phases/phase-2-per-profile-test-design/step-3-throughput-concurrency/resources/workload-math-reference.md1.5 kB
  • phases/phase-2-per-profile-test-design/step-3-throughput-concurrency/techniques/littles-law-application.md4.3 kB
  • phases/phase-2-per-profile-test-design/step-3-throughput-concurrency/techniques/open-vs-closed-model.md3.9 kB
  • phases/phase-2-per-profile-test-design/step-3-throughput-concurrency/techniques/think-time-and-pacing.md2.4 kB
  • phases/phase-2-per-profile-test-design/step-3-throughput-concurrency/techniques/throughput-reconciliation.md3.3 kB
  • phases/phase-2-per-profile-test-design/step-4-test-case-specification/resources/test-data-types-reference.md1.5 kB
  • phases/phase-2-per-profile-test-design/step-4-test-case-specification/techniques/correlation-mapping-specification.md3.0 kB
  • phases/phase-2-per-profile-test-design/step-4-test-case-specification/techniques/data-diversity-rules.md4.2 kB
  • phases/phase-2-per-profile-test-design/step-4-test-case-specification/techniques/data-parameterization-specification.md4.2 kB
  • phases/phase-2-per-profile-test-design/step-4-test-case-specification/techniques/script-blueprint-specification.md3.2 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 78 files you can review in full before installing. The MIT licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Performance Test Design · 96.9k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/performance-test-design/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/performance-test-design" ] && { [ ! -e .claude/skills/performance-test-design ] || { mv .claude/skills/performance-test-design "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/performance-test-design" .claude/skills/ && echo "Installed .claude/skills/performance-test-design"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add phatnguyen975/performance-test-design

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/performance-test-design/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/performance-test-design/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/performance-test-design" ] && { [ ! -e ~/.claude/skills/performance-test-design ] || { mv ~/.claude/skills/performance-test-design "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/performance-test-design" ~/.claude/skills/ && echo "Installed ~/.claude/skills/performance-test-design" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/performance-test-design/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referencephatnguyen975/performance-test-design

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Who wrote it

PH
phatnguyen975

Publishes on mcprush.

0 servers listed1 skill listednot claimed
Profile
Publisher
Servers0
Claim this skill