Ready to supercharge your AI agents?

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

test-writing · jnmetacode | DecimalAI

testingby jnmetacode

test-writing

jnmetacode/test-writing

Source jnmetacode/skillet ↗License MIT

Write tests that catch real regressions — behavior-focused, minimal mocking, edge cases chosen from the code's actual branches.

SkillScore82Maintained

Automatic

QA & Test Engineering pack

Last verified 8/3/2026

What it changes

Passed 18 of 22 test cases with the skill, and 12 of 22 without it.

Without skill55%

With skill82%

Checks it passed that the model alone missed

Mocks are restricted to external system boundaries.
All test names express claims without using 'should'.
Assertions include descriptive custom error failure messages.

and 8 more in the full report

7 fixed11 passed either way3 still failing1 broke

Pass-rate lift: +27 pp
Tokens: +2%
Agent turns: 0%
Response time: -17%

Model gemini-3.6-flashMeasured 8/3/2026v118 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/jnmetacode-test-writing/SKILL.md https://app.decimal.ai/s/jnmetacode-test-writing/SKILL.md

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

decimalai skills add jnmetacode-test-writing

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 7

Prompt

I just added a new `parseConfig(filePath)` function in `src/config.js` that handles reading JSON files, environment variable overrides, and fallback defaults. Could you write a complete test file for this function? Output the test suite code so I can drop it directly into `tests/config.test.js`.

What was checked, without and with the skill
Checked	Without skill	With skill
The test suite creates temporary disk files using temporary directory helpers instead of mocking filesystem modules.	Missed	Passed
Assertions evaluate returned configuration values rather than checking filesystem call counts.	Missed	Passed

case-01 · gemini-3.6-flash · 8/3/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md36 linessingle file

test-writing

A test's value is the bug it catches later. Test behavior through the public surface, not implementation details — a good test survives a refactor; a bad one breaks with it.

Procedure

Match the house style first: open 2–3 existing test files; copy their runner, naming, setup helpers and assertion idioms exactly.
One behavior per test, named as a claim: install skips a broken entry and installs the rest — readable as a spec when the suite prints.
Choose cases from the code's branches, not from imagination. Read the function: every if, every early return, every catch is a candidate. Priority order:
- the happy path (one test, not five variations)
- each error/edge branch (empty input, missing file, duplicate, too-long, zero/negative, unicode)
- the bug you just fixed (regression test that fails without the fix — verify it actually fails by stashing the fix once)
Real objects over mocks. Mock only true boundaries (network, clock, randomness). If a test needs four mocks, the unit is wrong — test one level higher. For clock/randomness, inject (now, seed) rather than patching globals.
Make failure diagnosable: assert on specific values, not just truthiness; add a message when the assertion isn't self-explanatory (assert.ok(hit1 >= 0.88, 'ranking change regressed recall')).
Independence: each test builds its own state (tmp dirs via mkdtemp, fresh fixtures) and cleans up. Order-dependence is a flake factory.

Anti-patterns

Asserting a function was called instead of what it did.
Snapshot tests for logic (they assert "nothing changed", not "it's correct").
Testing private helpers directly — route through the public API.
A test that can't fail (asserting the mock you just configured).

Track record

Benchmark

18 / 22

test cases passed, vs 12 / 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 — 8/1/2026

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

jnmetacode / skillet

skills/test-writing/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version 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

test-writing

Procedure

Anti-patterns

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills