Ready to supercharge your AI agents?

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

Get Started Free →

Testing Skill · vm0-ai | DecimalAI

testingby vm0-ai

Testing Skill

vm0-ai/testing

Source vm0-ai/vm0 ↗License NOASSERTION

Comprehensive testing patterns and anti-patterns for writing and reviewing tests

SkillScore100Maintained

Automatic

QA & Test Engineering pack

Last verified 8/15/2026

What it changes

Passed 22 of 22 test cases with the skill, and 10 of 22 without it.

Without skill45%

With skill100%

Checks it passed that the model alone missed

Forbids mocking internal project code
Directs the user to mock only external services
Mentions docs/testing.md as the primary documentation

and 12 more in the full report

12 fixed10 passed either way0 still failing0 broke

Pass-rate lift: +55 pp
Tokens: -28%
Agent turns: 0%
Response time: -56%

Model gemini-3.6-flashMeasured 8/15/2026v122 of 22 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/vm0-ai-testing/SKILL.md https://app.decimal.ai/s/vm0-ai-testing/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add vm0-ai-testing, 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/vm0-ai-testing/ and pins it in .decimal/skills.lock

decimalai skills add vm0-ai-testing

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

curl -fsSL --create-dirs -o .claude/skills/vm0-ai-testing/SKILL.md https://app.decimal.ai/s/vm0-ai-testing/SKILL.md

Raw file: /s/vm0-ai-testing/SKILL.md ↗ · machine-readable summary at /s/vm0-ai-testing.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 12

Prompt

When working on Python testing in `crates/runner/mitm-addon`, what file serves as the primary doc guide?

What was checked, without and with the skill
Checked	Without skill	With skill
Mentions docs/testing.md as the primary documentation	Missed	Passed

case-19 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md26 linessingle file

Testing Skill

Use this skill when writing tests, reviewing test code, or investigating test failures.

Documentation

Read the testing guide and relevant reference based on context:

Context	Primary	Reference
General	docs/testing.md	—
Anti-patterns	docs/testing.md	anti-patterns.md
Patterns	docs/testing.md	patterns.md
CLI (`turbo/apps/cli`)	docs/testing.md	cli-testing.md
CLI E2E (`e2e/tests/`)	docs/testing.md	cli-e2e-testing.md
API (`turbo/apps/api`)	docs/testing.md	api-testing.md
App (`turbo/apps/platform`)	docs/testing.md	app-testing.md
Rust (`crates/`)	docs/testing.md	rust-testing.md
Python addon (`crates/runner/mitm-addon`)	docs/testing.md	mitm-addon-testing.md

Key Principles

Integration tests are primary — test at system entry points
Mock at the boundary — only mock external services, not internal code
Use real infrastructure — real database, real filesystem (temp dirs)
Test behavior, not implementation — verify outcomes, not mock calls

Track record

Benchmark

22 / 22

test cases passed, vs 10 / 22 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 — 8/3/2026

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

vm0-ai / vm0

.claude/skills/testing/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/3/2026Version v1

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

Testing Skill

Documentation

Key Principles

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills