Claude Skill

test-generator

Generate and run unit, API, and E2E tests (including Playwright) that match project conventions. Use when adding coverage or reproducing a bug with a failing test first.

LLM Mart · 0 points · 0 0 0

Virus-scanned Reviewed automatically before listing.

Full trust report

Download navinspire-ia-navin-navin_skills_test-generator-e9c73a3.zip · 0 KB

navinspire-ia/navin 31 4 forks AGPL-3.0 Updated 4d ago

Part of navinspire-ia/navin — 182 skills

Install

skills CLI npx skills add https://github.com/Navinspire-ia/navin/tree/main/navin/skills/test-generator

Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install navinspire-ia-navin@llmmart

Git git clone https://github.com/Navinspire-ia/navin.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole navinspire-ia/navin collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

Test Generator

Overview

Write tests the project already understands (pytest, vitest, jest, playwright). Prefer failing test → fix → green.

Workflow

Detect the test runner and layout (package.json, pyproject.toml, existing tests).
Choose level:
- unit for pure logic
- API/integration for handlers
- E2E for critical user paths
Add a focused test next to siblings; mirror naming/fixtures.
Run the smallest command that exercises the new test.
Iterate until green; avoid flaky sleeps - use explicit waits.

Rules

Do not snapshot huge blobs without need.
Keep tests deterministic; inject clocks/network.
For UI E2E, reuse playwright-browser guidance.

Files (navin)

SKILL.md 973 B

---
name: test-generator
description: Generate and run unit, API, and E2E tests (including Playwright) that match project conventions. Use when adding coverage or reproducing a bug with a failing test first.
metadata: {"navin":{"emoji":"✅","category":"devops"}}
---

# Test Generator

## Overview

Write tests the project already understands (pytest, vitest, jest, playwright). Prefer failing test → fix → green.

## Workflow

1. Detect the test runner and layout (`package.json`, `pyproject.toml`, existing tests).
2. Choose level:
   - unit for pure logic
   - API/integration for handlers
   - E2E for critical user paths
3. Add a focused test next to siblings; mirror naming/fixtures.
4. Run the smallest command that exercises the new test.
5. Iterate until green; avoid flaky sleeps - use explicit waits.

## Rules

- Do not snapshot huge blobs without need.
- Keep tests deterministic; inject clocks/network.
- For UI E2E, reuse `playwright-browser` guidance.