60-validate-tests-150

[60] VALIDATE. Ensure new (staged and unstaged) changes are covered by tests at >70% and the full test suite is green. Use when asked to validate coverage for recent changes, add tests for modified code, or verify nothing else broke.

181 stars

Best use case

60-validate-tests-150 is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

[60] VALIDATE. Ensure new (staged and unstaged) changes are covered by tests at >70% and the full test suite is green. Use when asked to validate coverage for recent changes, add tests for modified code, or verify nothing else broke.

Teams using 60-validate-tests-150 should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/60-validate-tests-150/SKILL.md --create-dirs "https://raw.githubusercontent.com/majiayu000/claude-skill-registry/main/skills/data/60-validate-tests-150/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/60-validate-tests-150/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How 60-validate-tests-150 Compares

Feature / Agent60-validate-tests-150Standard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

[60] VALIDATE. Ensure new (staged and unstaged) changes are covered by tests at >70% and the full test suite is green. Use when asked to validate coverage for recent changes, add tests for modified code, or verify nothing else broke.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Validate-Tests 150 Protocol

## Goal

Cover current uncommitted changes with meaningful tests at >70% coverage (including **the changed lines**) and confirm the entire test suite is green.

## Workflow

1. **Identify current changes**
   - Check staged and unstaged changes (`git status`).
   - List changed files (`git diff --name-only` and `git diff --name-only --staged`).
   - Focus testing on these files and their direct dependencies.

2. **Find the coverage command**
   - Check `package.json` scripts for `test`, `coverage`, or `ci`.
   - If unclear, search for Jest/Vitest config files and default coverage options.

3. **Run coverage**
   - Execute the project’s coverage command.
   - Save the exact overall percentage and per‑file coverage for changed files (lines/branches).
   - Passing tests ≠ coverage: verify that **the changed lines** are executed (use coverage reports to confirm).

4. **Prioritize targets**
   - Start with changed files that are <70% covered.
   - Prefer pure functions, utilities, and deterministic logic.

5. **Add tests**
   - Write tests that directly exercise the **changed logic/markup** and assert behavior, edge cases, and failure paths.
   - Prefer behavior- or structure-level assertions that map to the changed lines (e.g., DOM structure/classes for UI changes).
   - Avoid snapshot‑only tests unless behavior is visual and stable.

6. **Re‑run coverage**
   - Confirm each changed file is **> 70%** covered (lines/branches where available).
   - Confirm the **specific changed lines** are covered (use coverage reports or direct evidence in tests).
   - If coverage tooling only provides overall numbers, explain the limitation and justify how tests exercise the changed code.
   - If not met, repeat steps 4–6.

7. **Run full test suite**
   - Execute the standard full test command for the repo (not just a subset).
   - Ensure all tests are green.

8. **Run lint**
   - Execute the standard lint command for the repo.
   - Ensure lint is green and **fix lint errors** introduced or surfaced in the process.
   - Do not leave lint in a failing state.

9. **Run compile**
   - Execute the standard compile command for the repo `npm run compile` or `tsc --noEmit`, best way is from root directory `npm run test && npm run lint:full`
   - Ensure compile is green and **fix compile errors** introduced or surfaced in the process.
   - Do not leave compile in a failing state.

10. **Report**
   - Summarize added tests, coverage changes, and full test results.
   - Note any files intentionally excluded or skipped and why.

## Validation checklist

- [ ] Staged and unstaged changes identified.
- [ ] Coverage command found and recorded.
- [ ] Baseline coverage captured.
- [ ] Tests added for changed files and direct dependencies.
- [ ] Changed files are >70% covered (lines/branches where available).
- [ ] Full test suite executed.
- [ ] All tests are green.
- [ ] Lint executed and green.
- [ ] Compile executed and green.

## Output expectations

- Provide the command used to measure coverage, to run the full test suite, and to run lint.
- Provide before/after coverage numbers and per‑file coverage for changed files.
- Explicitly state how the **changed lines** are exercised by the tests.
- List which files were targeted and why.
- Confirm the final threshold is met for changed files, or report remaining gaps.
- Confirm all tests and lint are green.
- Confirm compile is green.

Related Skills

add-unit-tests

181
from majiayu000/claude-skill-registry

Guide for adding unit tests to AReaL. Use when user wants to add tests for new functionality or increase test coverage.

62-validate-integrity-150

181
from majiayu000/claude-skill-registry

[62] VALIDATE. Final self-check before delivery. Verify goal alignment, completeness, correctness, and identify residual risks. Produces quality score (0-100) and delivery status. Use when completing any significant work, before handoff, or when you need confidence that work is ready.

61-validate-lint-150

181
from majiayu000/claude-skill-registry

[61] VALIDATE. Comprehensive code quality check combining ESLint, TypeScript compilation, and unused code detection. Runs full lint suite with detailed error reporting and fix suggestions. Use before commits, after major changes, or when ensuring code quality standards.

tech-blog

159
from majiayu000/claude-skill-registry

Generates comprehensive technical blog posts, offering detailed explanations of system internals, architecture, and implementation, either through source code analysis or document-driven research.

Content & DocumentationClaude

ontopo

159
from majiayu000/claude-skill-registry

An AI agent skill to search for Israeli restaurants, check table availability, view menus, and retrieve booking links via the Ontopo platform, acting as an unofficial interface to its data.

General Utilities

lets-go-rss

159
from majiayu000/claude-skill-registry

A lightweight, full-platform RSS subscription manager that aggregates content from YouTube, Vimeo, Behance, Twitter/X, and Chinese platforms like Bilibili, Weibo, and Douyin, featuring deduplication and AI smart classification.

Content & Documentation

whisper-transcribe

159
from majiayu000/claude-skill-registry

Transcribes audio and video files to text using OpenAI's Whisper CLI, enhanced with contextual grounding from local markdown files for improved accuracy.

Media Processing

grail-miner

159
from majiayu000/claude-skill-registry

This skill assists in setting up, managing, and optimizing Grail miners on Bittensor Subnet 81, handling tasks like environment configuration, R2 storage, model checkpoint management, and performance tuning.

DevOps & Infrastructure

chrome-debug

159
from majiayu000/claude-skill-registry

This skill empowers AI agents to debug web applications and inspect browser behavior using the Chrome DevTools Protocol (CDP), offering both collaborative (headful) and automated (headless) modes.

Coding & DevelopmentClaude

ux

159
from majiayu000/claude-skill-registry

This AI agent skill provides comprehensive guidance for creating professional and insightful User Experience (UX) designs, covering user research, information architecture, interaction design, visual guidance, and usability evaluation. It aims to produce actionable, user-centered solutions that avoid generic AI aesthetics.

UX Design & StrategyClaude

modal-deployment

159
from majiayu000/claude-skill-registry

Run Python code in the cloud with serverless containers, GPUs, and autoscaling using Modal. This skill enables agents to generate code for deploying ML models, running batch jobs, serving APIs, and scaling compute-intensive workloads.

DevOps & Infrastructure

vly-money

159
from majiayu000/claude-skill-registry

Generate crypto payment links for supported tokens and networks, manage access to X402 payment-protected content, and provide direct access to the vly.money wallet interface.

Fintech & CryptoClaude