Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Test Implementation Patterns · shinpr | DecimalAI

testingby shinpr

Test Implementation Patterns

shinpr/test-implement

Source shinpr/claude-code-workflows ↗License MIT

Implements React/TypeScript unit, integration, and browser E2E tests with the repository's configured runner, mocks, setup, and browser harness.

SkillScore32Maintained

Automatic

QA & Test Engineering pack

Last verified 8/18/2026

What it changes

Passed 8 of 25 test cases with the skill, and 4 of 25 without it.

Without skill16%

With skill32%

Checks it passed that the model alone missed

Each test runs in isolation from system time variations.
Each test runs independently without relying on prior test state.
The test implementation eliminates shared mutable state between test cases.

and 3 more in the full report

4 fixed4 passed either way17 still failing0 broke

Pass-rate lift: +16 pp
Tokens: -16%
Agent turns: 0%
Response time: -23%

Model gemini-3.6-flashMeasured 8/18/2026v28 of 25 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/shinpr-test-implement/SKILL.md https://app.decimal.ai/s/shinpr-test-implement/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add shinpr-test-implement, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/shinpr-test-implement/ and pins it in .decimal/skills.lock

decimalai skills add shinpr-test-implement

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/shinpr-test-implement/SKILL.md https://app.decimal.ai/s/shinpr-test-implement/SKILL.md

Raw file: /s/shinpr-test-implement/SKILL.md ↗ · machine-readable summary at /s/shinpr-test-implement.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 4

Prompt

We are introducing Playwright to implement full browser end-to-end tests for our web application. Which reference file should guide this implementation?

What was checked, without and with the skill
Checked	Without skill	With skill
The response identifies references/e2e.md as the reference for browser E2E tests.	Missed	Passed

case-19 · gemini-3.6-flash · 8/18/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md25 lines3 files

Test Implementation Patterns

Reference Selection

Test Type	Reference	When to Use
Unit / Integration	references/frontend.md	Implementing React component tests with the repository's configured runner and network mocking layer
E2E	references/e2e.md	Implementing browser-level E2E tests in the existing harness, or Playwright when the approved work introduces a harness

Common Principles

AAA Structure

All tests follow Arrange-Act-Assert:

Arrange: Set up preconditions and inputs
Act: Execute the behavior under test
Assert: Verify the expected outcome

Test Independence

Each test runs independently without depending on other tests
No shared mutable state between tests
Deterministic execution — mock random and time dependencies

Naming

Test names describe expected behavior from user perspective
One test verifies one behavior

Track record

Benchmark

8 / 25

test cases passed, vs 4 / 25 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

shinpr / claude-code-workflows

skills/test-implement/SKILL.md

View on GitHub ↗

License MITImported 8/10/2026Version v2Bundled 2 files

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

shinpr/frontend-typescript-testingDesigns frontend tests using the repository's configured React test and browser harnesses, including RTL, MSW, Vitest, and Playwright when present. Use when adding or reviewing component, loading/error-state, integration, or frontend E2E tests.Close match+22 pp pass-rate lift

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Test Implementation Patterns

Reference Selection

Common Principles

AAA Structure

Test Independence

Naming

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills