Is the Testing skill free?

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

What is the Testing SkillProof Score?

9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.

How do I install Testing?

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 Testing 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.

Testing

Writes layered tests with boundary/edge coverage, mocking rules, and flaky-test triage

by rsmdt · rsmdt/the-startup

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.2/10
Tested: Jul 31, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · fcc9ca5

Fetched the SKILL.md at plugins/team/skills/development/testing/; frontmatter parses (name+description) and its one referenced file, examples/test-pyramid.md, returns HTTP 200. No security smells. For output: I wrote applyDiscount(price,percent), then a naive baseline suite (3 tests) and a skill-following suite (11 tests) applying the body's boundary matrix (min-1/min/min+1/max-1/max/max+1) and one-behavior-per-test naming. Both passed on clean source (14/14 via jest). I then mutated the source (percent>100 to percent>101): the baseline suite still passed (missed the bug), while the skill suite's max+1 boundary test failed and caught it — a concrete, measured difference.

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 5/5

What Testing does

A test-authoring skill that enforces Arrange-Act-Assert structure, one-behavior-per-test naming, layer-appropriate mocking (mock at boundaries only, never internal code), and an explicit boundary/edge-case matrix. Triggers when writing tests, reviewing test quality, or debugging test failures, including flaky-test quarantine and layer-specific debugging steps for unit, integration, and E2E suites.

How to install Testing

git clone --depth 1 https://github.com/rsmdt/the-startup.git /tmp/testing-src
mkdir -p ~/.claude/skills
cp -R /tmp/testing-src/plugins/team/skills/development/testing ~/.claude/skills/testing
# Places SKILL.md at ~/.claude/skills/testing/SKILL.md plus examples/test-pyramid.md
# Note: SKILL body contains a $ARGUMENTS token (it ships as a plugin command in the-startup);
# as a standalone skill $ARGUMENTS is simply unsubstituted and harmless.
# No external tools/API keys required — it is instructional guidance only.

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

Commands — how to trigger Testing

/testing Writes layered tests with boundary/edge coverage, mocking rules, and flaky-test triage

It also activates on plain-language prompts like these:

Write unit tests for this service layer
Debug why this test is flaky
Review the quality of these test cases

Frequently asked questions

Is the Testing skill free?: Yes. The skill itself is free from rsmdt/the-startup. SkillProof publishes the install command and an independent test verdict at no cost.
Does Testing work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 31, 2026. Verdict: Tested · Works. Fetched the SKILL.md at plugins/team/skills/development/testing/; frontmatter parses (name+description) and its one referenced file, examples/test-pyramid.md, returns HTTP 200. No security smells. For output: I wrote applyDiscount(price,percent), then a naive baseline suite (3 tests) and a skill-following suite (11 tests) applying the body's boundary matrix (min-1/min/min+1/max-1/max/max+1) and one-behavior-per-test naming. Both passed on clean source (14/14 via jest). I then mutated the source (percent>100 to percent>101): the baseline suite still passed (missed the bug), while the skill suite's max+1 boundary test failed and caught it — a concrete, measured difference.
What is the Testing SkillProof Score?: 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install Testing?: 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 Testing 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.