Is the Build/Update Tests skill free?

Yes. The skill itself is free from enbyaugust/zacs-claude-skills. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Build/Update Tests SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.

How do I install Build/Update Tests?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Build/Update Tests with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Build/Update Tests

Risk-scores a file, then writes or fills in the unit/integration/E2E tests it's missing.

by enbyaugust · enbyaugust/zacs-claude-skills

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.8/10
Tested: Jul 16, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · d8efd4f

Ran it twice on a throwaway formatCurrency.ts: the skill-guided pass produced 11 organized P0/P1/P2 tests (null/NaN/rounding/unknown-currency-code edge cases, correct __tests__ path) versus 4 flat tests from an unguided baseline, all 15 passing under real vitest. Its 'CRITICAL' pattern-compliance step reads claude-patterns/testing-patterns.md, vitest-testing-patterns.md and playwright-best-practices.md, which don't ship with the skill and won't exist in a typical consumer repo, so that whole check silently no-ops out of the box.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 4/5

What Build/Update Tests does

Reads a target file, classifies it as High/Medium/Low risk, checks for existing unit/integration/E2E tests against pattern-compliance docs, then writes or updates the missing tests and reports gaps fixed. Triggers on phrases like "build tests for X", "update tests", "test [component]", or "check test coverage".

How to install Build/Update Tests

git clone https://github.com/enbyaugust/zacs-claude-skills
cd zacs-claude-skills
mkdir -p ~/.claude/skills
cp -r skills/build-update-tests ~/.claude/skills/build-update-tests

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Build/Update Tests

/build-update-tests Risk-scores a file, then writes or fills in the unit/integration/E2E tests it's missing.

It also activates on plain-language prompts like these:

check test coverage for the payment service before I ship it
write missing unit tests for my LoginForm component
test my new formatCurrency util for edge cases like null and NaN

Frequently asked questions

Is the Build/Update Tests skill free?: Yes. The skill itself is free from enbyaugust/zacs-claude-skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does Build/Update Tests work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Works with setup. Ran it twice on a throwaway formatCurrency.ts: the skill-guided pass produced 11 organized P0/P1/P2 tests (null/NaN/rounding/unknown-currency-code edge cases, correct __tests__ path) versus 4 flat tests from an unguided baseline, all 15 passing under real vitest. Its 'CRITICAL' pattern-compliance step reads claude-patterns/testing-patterns.md, vitest-testing-patterns.md and playwright-best-practices.md, which don't ship with the skill and won't exist in a typical consumer repo, so that whole check silently no-ops out of the box.
What is the Build/Update Tests SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install Build/Update Tests?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Build/Update Tests with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.