Runs TypeScript code against JSON test files to verify correctness.

Install

mkdir -p .claude/skills/run-diana-uk && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14649" && unzip -o skill.zip -d .claude/skills/run-diana-uk && rm skill.zip

Installs to .claude/skills/run-diana-uk

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Run TypeScript solution against test cases. Use when user wants to test their code.
83 chars✓ has a “when” trigger
Beginner

Key capabilities

  • Find the TypeScript solution file
  • Find the corresponding test file
  • Execute the solution against test cases using `npx tsx`
  • Report clear pass/fail results for each test
  • Analyze test failures and offer debugging help
  • Offer to create a test file if none exists

How it works

The skill locates a TypeScript solution file and its corresponding JSON test file, then executes the solution using `npx tsx` and reports the results, indicating pass or fail for each test case.

Inputs & outputs

You give it
Path to a TypeScript solution file (e.g., `solution.ts`)
You get back
A clear report of test results, including pass/fail status, input, expected, and actual output for each case

When to use run

  • Running coding tests
  • Validating TypeScript logic
  • Debugging test failures

About this skill

Run the user's TypeScript solution against test cases.

File to run: $ARGUMENTS (If empty, look for solution.ts in current directory)

Process:

  1. Find the solution file
  2. Find corresponding test file (solution.test.json or tests.json in same directory)
  3. Execute with: npx tsx lib/leetcode_problem_runner/index.ts <file> [test-file]
  4. Report results clearly

Test file format expected:

{
  "functionName": "twoSum",
  "cases": [
    { "input": [[2,7,11,15], 9], "expected": [0,1] },
    { "input": [[3,2,4], 6], "expected": [1,2] }
  ]
}

Output format:

Running: [functionName]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Test 1: ✓ PASS (0.12ms)
  Input: [2,7,11,15], 9
  Expected: [0,1]
  Got: [0,1]

Test 2: ✗ FAIL (0.08ms)
  Input: [3,2,4], 6
  Expected: [1,2]
  Got: [0,2]

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Results: 1/2 passed
Total time: 0.20ms

If tests fail, analyze the failure and offer to help debug. If no test file exists, offer to create one based on the problem.

When not to use it

  • When the user does not want to test their code
  • When the solution is not a TypeScript file
  • When test cases are not in the specified JSON format

Limitations

  • The skill expects test files to be in a specific JSON format
  • The solution must be a TypeScript file
  • The execution environment uses `npx tsx`

How it compares

This skill automates the process of running TypeScript code against predefined test cases and provides structured feedback, unlike manual execution and verification.

Compared to similar skills

run side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
run (this skill)06moNo flagsBeginner
vitest416moNo flagsIntermediate
chrome-devtools417moReviewIntermediate
zod-4127moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

vitest

antfu

Vitest fast unit testing framework powered by Vite with Jest-compatible API. Use when writing tests, mocking, configuring coverage, or working with test filtering and fixtures.

41183

chrome-devtools

mrgoonie

Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.

41157

zod-4

prowler-cloud

Zod 4 schema validation patterns. Trigger: When creating or updating Zod v4 schemas for validation/parsing (forms, request payloads, adapters), including v3 -> v4 migration patterns.

1260

write-unit-tests

tldraw

Writing unit and integration tests for the tldraw SDK. Use when creating new tests, adding test coverage, or fixing failing tests in packages/editor or packages/tldraw. Covers Vitest patterns, TestEditor usage, and test file organization.

545

develop-ai-functions-example

vercel

Develop examples for AI SDK functions. Use when creating, running, or modifying examples under examples/ai-functions/src to validate provider support, demonstrate features, or create test fixtures.

536

obsidian-local-dev-loop

jeremylongshore

Configure Obsidian plugin development with hot-reload and fast iteration. Use when setting up development workflow, configuring test vaults, or establishing a rapid development cycle. Trigger with phrases like "obsidian dev loop", "obsidian hot reload", "obsidian development workflow", "develop obsidian plugin".

328

Search skills

Search the agent skills registry