Is the Spec-Driven Test skill free?

Yes. The skill itself is free from Loveforwa/spec-test.skill. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Spec-Driven Test SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.

How do I install Spec-Driven Test?

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 Spec-Driven Test 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.

Spec-Driven Test

Three-agent, spec-first E2E web testing with methodology-graded test cases

by Loveforwa · Loveforwa/spec-test.skill

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Jul 17, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 2deac09

Exercised the test-design phase on a login feature: following the template forced a path-typed coverage table, a resource-dependency matrix that distinguishes intentional cumulative dependency from a deadlock, per-case teardown that closes the loop, and an exhaustive scenario self-check covering rate-limit lockout, email-enumeration protection and HttpOnly/Secure cookie assertions read via context.cookies() rather than document.cookie. An ad-hoc no-skill baseline produced a flat five-case list with no state verification, teardown, or invariant coverage. The gap is real and specific, though a full three-agent browser run was out of scope here.

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 7/10
Docs & honesty 5/5

What Spec-Driven Test does

A specification-based E2E testing workflow where a Cartographer reads code into a spec and test cases, an isolated Inspector reviews them against classical testing methodologies, and an Operator runs them in a real browser, behind two human review gates. Triggers on 'test this feature', 'do E2E testing', or 'spec-driven-test'. Heavyweight (100K-500K tokens per run); aimed at critical flows like login and payments.

How to install Spec-Driven Test

git clone https://github.com/Loveforwa/spec-test.skill.git
mkdir -p ~/.claude/skills
cd spec-test.skill && cp -r en ~/.claude/skills/spec-driven-test

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

Commands — how to trigger Spec-Driven Test

/spec-driven-test Three-agent, spec-first E2E web testing with methodology-graded test cases

It also activates on plain-language prompts like these:

Design spec-driven E2E test cases for our login feature before I code it.
Write test cases covering rate-limit lockout and cookie security for login.
Review this payment flow's test coverage against classical test methodology.

Frequently asked questions

Is the Spec-Driven Test skill free?: Yes. The skill itself is free from Loveforwa/spec-test.skill. SkillProof publishes the install command and an independent test verdict at no cost.
Does Spec-Driven Test work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Tested · Works. Exercised the test-design phase on a login feature: following the template forced a path-typed coverage table, a resource-dependency matrix that distinguishes intentional cumulative dependency from a deadlock, per-case teardown that closes the loop, and an exhaustive scenario self-check covering rate-limit lockout, email-enumeration protection and HttpOnly/Secure cookie assertions read via context.cookies() rather than document.cookie. An ad-hoc no-skill baseline produced a flat five-case list with no state verification, teardown, or invariant coverage. The gap is real and specific, though a full three-agent browser run was out of scope here.
What is the Spec-Driven Test SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.
How do I install Spec-Driven Test?: 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 Spec-Driven Test 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.