Skip to main content
skill CX Codex

w-test — Claude Code skill: what it does, how to install

w-test — a skill for Claude Code that executes project test commands and resolves failure causes step by step until the suite turns green.

MIT 647 installs ★ 1 updated 2026-10-02

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add blockmatic-icebox/basilic-skills --skill w-test -a claude-code
Open on GitHub

What w-test does

The skill picks the narrowest test suite for modified packages from package.json, using Turbo filters, pnpm test, or app E2E scripts. Full test suites run only on demand or when the failure context is unclear. It captures raw failure outputs without paraphrasing.

Fixes target one root cause at a time followed by a test rerun. Weakening assertions or skipping test cases to force a pass is prohibited. Execution stops once tests pass or when issues require human intervention, such as missing secrets, environment variables, or flaky infrastructure. If repository commands or behavior change during fixes, it triggers /w-docs.

What it helps with

  • run targeted tests for affected repository packages
  • resolve test failures one by one without weakening assertions
  • halt execution when failures require missing secrets or environment setup

Example prompts for the agent

  • Run the test suite and fix any failing tests
  • Execute affected package tests and resolve the root causes

How to install w-test

1Skills CLI (Vercel)

npx skills add blockmatic-icebox/basilic-skills --skill w-test -a claude-code

2Manually: put the files in place

~/.claude/skills/w-test/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/w-test/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about w-test

How to install w-test in Claude Code?

Run npx skills add blockmatic-icebox/basilic-skills --skill w-test -a claude-code. You can also place the skill file directly at ~/.claude/skills/w-test/SKILL.md.

What does w-test do?

It detects test scripts in package.json, runs targeted suites for changed code, and iteratively fixes failures until all tests pass.

When does w-test stop troubleshooting?

Troubleshooting stops when all tests pass, or when failures stem from missing environment variables, secrets, or flaky infrastructure.

Source text

SKILL.md · MIT
---
name: w-test
description: Run the repository test scripts and fix failures until they pass.
disable-model-invocation: true
---

Run the documented test scripts from package.json (filtered to the change when the repo supports it). Fix owning causes. Do not publish.

1. Identify the test command for the affected packages (`pnpm test`, Turbo filters, or the app E2E script). Prefer the narrowest suite that covers the change; use the full suite when the failure is unknown or the user asked for it.
2. Run the command. Capture failing tests, not a paraphrase.
3. Fix one owning cause at a time. Re-run the failed command. Do not weaken assertions or skip tests to obtain a pass. Stop when the suite is green or remaining failures need a human (secrets, env, flaky infra).
4. Docs: `/w-docs` if behavior or commands changed.

© blockmatic-icebox · MIT · blockmatic-icebox/basilic-skills

Similar skills

All skills for Testing and QA →

From the same set45

The whole set →
w-review w-review — a skill for Claude Code checks changes for evidenced defects and risks. Run it on a diff, branch, PR, or working tree without asking it to edit code. CX Codex +1 647installs w-api-test The w-api-test Claude Code skill adds API tests that check public HTTP behavior through the project’s existing harness. It runs on request to test an API. CX Codex +1 647installs w-unit The w-unit skill for Claude Code adds unit tests for the current change using the repository’s testing conventions. It checks public APIs, error paths, and related regressions. CX Codex +1 647installs w-tdd The w-tdd Claude Code skill guides implementation through red-green-refactor. It activates when a developer requests TDD or the repository requires it. CX Codex +1 647installs w-yolo The w-yolo Claude Code skill fixes failing local checks on request. It reruns the failing command or a check for the changes, without publishing them. CX Codex +1 647installs w-lint The w-lint Claude Code skill runs project linters and applies small fixes. It requires an explicit invocation because automatic invocation is disabled. CX Codex +1 647installs w-vercel The w-vercel Claude Code skill examines Vercel build failures and fixes the local build. It handles failures on the current branch. CX Codex +1 647installs w-gha w-gha — a Claude Code skill that retrieves GitHub Actions logs with gh, analyzes failures, and helps fix CI errors locally. Invoke it to investigate a failed workflow on the current branch. CX Codex +1 647installs

Project sponsors

Companies that keep this analytics open