Agent skill

Test Case Design

by mirumee in mirumee/nimara-ecommerce

Turn a requirement, spec, or feature into a gap-free set of test cases by equivalence partitioning — enumerate the distinct behaviour classes, pick a representative per class, then run them and…

BSD-3-ClauseAuto-check passedTesting & QA

Install Test Case Design

skills CLI
$ npx skills add mirumee/nimara-ecommerce --skill test-case-design -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mirumee/nimara-ecommerce test-case-design --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mirumee/nimara-ecommerce.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/test-case-design .claude/skills/test-case-design && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
test-case-design
GitHub stars
129
Token cost
~695 tokens
SKILL.md length
274 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
BSD-3-Clause

At a glance

Turn a requirement, spec, or feature into a gap-free set of test cases by equivalence partitioning — enumerate the distinct behaviour classes, pick a representative per class, then run them and…

  • Works in 4 steps: Partition, don't enumerate inputs. Find… → Anchor to a source of truth. For… → No silent gaps. Explicitly list every… → …
  • The user asks to design test cases
  • SKILL.md covers Operating principles, Workflow and References
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Test Case Design is an agent skill from mirumee/nimara-ecommerce. Turn a requirement, spec, or feature into a gap-free set of test cases by equivalence partitioning — enumerate the distinct behaviour classes, pick a representative per class, then run them and report. Use this skill whenever the user asks to design test cases, write a test plan, cover a feature "with no gaps", build equivalence classes/groups, or test a data-driven surface (like the checkout address fields) across many inputs. Produces a plan file plus a run report; can file findings as bugs. Do NOT use to…

Its SKILL.md is about 700 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA, covering Test generation. It works with shadcn/ui. The repository describes itself as: Headless, composable ecommerce storefront built with Next.js, Typescript, and shadcn/ui. The licence is BSD-3-Clause.

When your agent uses it

  • The user asks to design test cases
  • Write a test plan
  • Cover a feature with no gaps
  • Build equivalence classes/groups

Example prompts

  • “with no gaps”
  • “/test-case-design”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Partition, don't enumerate inputs. Find the variables that change behaviour; group inputs into equivalence classes where every member…
  2. Anchor to a source of truth. For data-driven UIs, derive classes from the data (e.g. google-i18n-address all.json…
  3. No silent gaps. Explicitly list every class and confirm each is covered; call out any class you deliberately skip and why.
  4. Reuse known behaviour. Field-level validation behaviours are already documented in MEMORY.md and [[Test Data & Fixtures]] — don't re-derive.

What it can do on your machine

Read from SKILL.md and the folder at commit b883dec. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Test Case Design loads about 695 tokens when it runs. Until then it costs about 145 tokens; SKILL.md has 274 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~145
When it runs · the whole SKILL.md, loaded when a task matches
~695

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mirumee/nimara-ecommerce at commit b883dec, republished under its BSD-3-Clause licence (© mirumee). 274 words, ~695 tokens.

Download SKILL.mdSave it as .claude/skills/test-case-design/SKILL.md (or your agent's skills folder).
name
test-case-design
description
Turn a requirement, spec, or feature into a gap-free set of test cases by equivalence partitioning — enumerate the distinct behaviour classes, pick a representative per class, then run them and report. Use this skill whenever the user asks to design test cases, write a test plan, cover a feature "with no gaps", build equivalence classes/groups, or test a data-driven surface (like the checkout address fields) across many inputs. Produces a plan file plus a run report; can file findings as bugs. Do NOT use to retest an existing ticket (use bug-retest-triage).

Test Case Design

Convert a requirement into a complete set of test cases — covering every distinct behaviour class, not random examples — then execute and report. This is how the address admin-area sweep found bugs an ad-hoc pass missed (MS-1238/1239/1240).

Operating principles

  1. Partition, don't enumerate inputs. Find the variables that change behaviour; group inputs into equivalence classes where every member behaves the same; cover each class with one representative + boundaries. See [[Coverage Maps]].
  2. Anchor to a source of truth. For data-driven UIs, derive classes from the data (e.g. google-i18n-address all.json require/sub_isoids/state_name_type), not from guesses.
  3. No silent gaps. Explicitly list every class and confirm each is covered; call out any class you deliberately skip and why.
  4. Reuse known behaviour. Field-level validation behaviours are already documented in MEMORY.md and [[Test Data & Fixtures]] — don't re-derive.

Workflow

  1. SCOPE — restate the requirement; identify the behaviour-driving variables (channel, auth, country, payment outcome, field state…).
  2. PARTITION — build the equivalence-class table: class → rule → expected behaviour → representatives (+ boundary/negative cases). Write it to qa/triage/plans/<NAME>-tests.md.
  3. PICK DATA — choose verified fixtures per representative from [[Test Data & Fixtures]]; request any missing data/accounts (ASK, never fabricate).
  4. RUN — execute each case with the cheapest reliable method ([[Test Method Playbooks]]); for data-driven UI, inspect the rendered control per representative (select vs text, required, sorted). Capture evidence → qa/triage/evidence/<NAME>/results.md.
  5. REPORT — table of class → expected → actual → pass/fail, with the gap analysis (every class accounted for).
  6. FILE (if asked) — generalise failures into classes and file bugs + a [DEV] spec ticket that Blocks them, per [[Defect Taxonomy & Severity]] and [[Jira & Board 74 Operating Manual]].

References

[[Coverage Maps]] · [[Test Data & Fixtures]] · [[Test Method Playbooks]] · [[Defect Taxonomy & Severity]]

© mirumee, BSD-3-Clause. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/test-case-design of mirumee/nimara-ecommerce.

Open the folder on GitHubat commit b883dec

Compare with similar skills

Test Case Design next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Test Case Design compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Test Case Design this skillmirumee/nimara-ecommerce129—~695Automated safety check: PassBSD-3-Clause
Write and Verify Playwright Testsappsmithorg/appsmith41k—~2.9kAutomated safety check: NotesApache-2.0
Adk Verify Snippetsgoogle/adk-python22k—~1.4kAutomated safety check: PassApache-2.0
Engine E2Ewix/react-native-navigation13k—~1.1kAutomated safety check: PassMIT
Hermetic Python Unit TestsdimensionalOS/dimos4.6k—~1.4kAutomated safety check: PassCustom licence
Emcaklofas/kicad-happy1.4k1 repos~2.8kAutomated safety check: PassMIT

Similar skills

  • Writes a Playwright end-to-end test from a prompt, runs it against a live Appsmith deployment and retries with fixes up to three times until it passes.

    41k GitHub stars~2.9k tokensUpdated today
    Testing & QAAuto-check: notes
  • Adk Verify Snippets

    google/adk-python

    Official

    Checks that every Python code block in a Markdown file actually compiles and runs, by extracting each block to a temporary file, executing it in an isolated subprocess, and writing a pass/fail…

    22k GitHub stars~1.4k tokensUpdated today
    Testing & QAAuto-check passed
  • Engine E2E

    wix/react-native-navigation

    Official

    Run Wix Engine (mobile-apps-engine) iOS E2E tests locally to validate RNN changes.

    13k GitHub stars~1.1k tokensUpdated 2 days ago
    Testing & QAAuto-check passed
  • Hermetic Python Unit Tests

    dimensionalOS/dimos

    Rules for writing, fixing and reviewing pytest unit tests that are hermetic: behavior-focused, deterministic, isolated and cheap to run.

    4.6k GitHub stars~1.4k tokensUpdated today
    Testing & QAAuto-check passed
  • Emc

    aklofas/kicad-happy

    EMC pre-compliance risk analysis for KiCad PCB designs — 18 check categories, 44 rule IDs covering ground planes, decoupling, I/O filtering, switching harmonics, clock routing, differential pair…

    1.4k GitHub starsUsed in 1 repo~2.8k tokens
    Testing & QAAuto-check passed
  • Swig Test

    swig/swig

    Run SWIG test suite for specific languages. An agent skill from swig/swig.

    6.3k GitHub stars~2.3k tokensUpdated yesterday
    Testing & QAAuto-check passed

More from mirumee/nimara-ecommerce

All 12 skills in this repo
  • Project Guidelines

    mirumee/nimara-ecommerce

    Guide for working with Nimara's layered monorepo architecture.

    129 GitHub stars~4.8k tokensUpdated 2 days ago
    Auto-check passed
  • Prd Modeling

    mirumee/nimara-ecommerce

    A skill your agent uses when creating, rewriting, refining, or stress-testing a Product Requirements Document (PRD), including turning an initiative or feature brief into product requirements.

    129 GitHub stars~824 tokensUpdated 2 days ago
    Auto-check passed
  • Rfc Modeling

    mirumee/nimara-ecommerce

    A skill your agent uses when designing, drafting, refining, or stress-testing an RFC for an approved PRD, including requests for a design doc, solution design, or how to build it.

    129 GitHub stars~920 tokensUpdated 2 days ago
    Auto-check passed
  • Ucp Agent

    mirumee/nimara-ecommerce

    Operate Nimara's UCP REST commerce API. An agent skill from mirumee/nimara-ecommerce.

    129 GitHub stars~1k tokensUpdated 2 days ago
    Auto-check passed
  • Show Me

    mirumee/nimara-ecommerce

    Help the user understand the current topic visually with concise diagrams, code-shape sketches, and focused HTML artifacts.

    129 GitHub starsUsed in 7 repos~809 tokens
    Auto-check passed
  • Bug Retest Triage

    mirumee/nimara-ecommerce

    Retest a reported defect on the live Nimara board (Jira project MS, board 74) and give it an evidence-backed verdict — still reproduces → Open, fixed → Done, blocked → leave In testing and ask.

    129 GitHub stars~888 tokensUpdated 2 days ago
    Auto-check passed

Works with

Categories

Questions about Test Case Design

What does Test Case Design do?

Turn a requirement, spec, or feature into a gap-free set of test cases by equivalence partitioning — enumerate the distinct behaviour classes, pick a representative per class, then run them and…. Test Case Design is an agent skill from mirumee/nimara-ecommerce. Turn a requirement, spec, or feature into a gap-free set of test cases by equivalence partitioning — enumerate the distinct behaviour classes, pick a representative per class, then run them and report.

When should I use Test Case Design?

Test Case Design fits situations like: the user asks to design test cases; write a test plan; cover a feature with no gaps; build equivalence classes/groups.

How do I install Test Case Design in Claude Code?

Run `npx skills add mirumee/nimara-ecommerce --skill test-case-design -a claude-code`. Or copy the skill folder (.claude/skills/test-case-design in mirumee/nimara-ecommerce) into .claude/skills/test-case-design in your project. Claude Code loads it when a task matches its description.

How do I install Test Case Design in Codex?

Run `npx skills add mirumee/nimara-ecommerce --skill test-case-design -a codex`. Or copy the skill folder (.claude/skills/test-case-design in mirumee/nimara-ecommerce) into .agents/skills/test-case-design in your project. Codex loads it when a task matches its description.

Can I use Test Case Design in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mirumee/nimara-ecommerce --skill test-case-design -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/test-case-design, .gemini/skills/test-case-design, .github/skills/test-case-design and .opencode/skills/test-case-design in your project.

What does Test Case Design need to run?

SKILL.md names no scripts, command-line tools or credentials: Test Case Design is instructions for the agent only.

Does Test Case Design access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Test Case Design safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Test Case Design use?

Test Case Design is published under the BSD-3-Clause licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Test Case Design use?

About 695 tokens (SKILL.md is roughly 2.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Test Case Design?

Skills that share tags, products or a category with Test Case Design: Write and Verify Playwright Tests (appsmithorg/appsmith, 41k stars), Adk Verify Snippets (google/adk-python, 22k stars), Engine E2E (wix/react-native-navigation, 13k stars) and Hermetic Python Unit Tests (dimensionalOS/dimos, 4.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Test Case Design?

mirumee (a GitHub organization) maintains it in mirumee/nimara-ecommerce, which has 129 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 6, 2026.

Source: mirumee/nimara-ecommerce on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.