Ready to supercharge your AI agents?

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

Get Started Free →

Write Tests · cowork-os | DecimalAI

testingby cowork-os

Write Tests

cowork-os/write-tests

Source cowork-os/cowork-os ↗License MIT

Generate unit tests for existing code

SkillScore73Maintained

Automatic

QA & Test Engineering pack

Last verified 8/20/2026

What it changes

Passed 16 of 22 test cases with the skill, and 15 of 22 without it.

Without skill68%

With skill73%

Checks it passed that the model alone missed

Decline generating unit tests for visual snapshots.
Explicitly map test cases to specific syntax element parsers.

2 fixed14 passed either way5 still failing1 broke

Pass-rate lift: +5 pp
Tokens: -15%
Agent turns: 0%
Response time: -26%

Model gemini-3.6-flashMeasured 8/20/2026v1 · latest is v216 of 22 cases passed with skill

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

This benchmark measured an earlier version of the skill.

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/cowork-os-write-tests/SKILL.md https://app.decimal.ai/s/cowork-os-write-tests/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add cowork-os-write-tests, 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/cowork-os-write-tests/ and pins it in .decimal/skills.lock

decimalai skills add cowork-os-write-tests

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

curl -fsSL --create-dirs -o .claude/skills/cowork-os-write-tests/SKILL.md https://app.decimal.ai/s/cowork-os-write-tests/SKILL.md

Raw file: /s/cowork-os-write-tests/SKILL.md ↗ · machine-readable summary at /s/cowork-os-write-tests.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 2

Prompt

We are updating our React component library and want visual snapshot tests generated for the primary button component in components/Button.tsx using Jest snapshots.

What was checked, without and with the skill
Checked	Without skill	With skill
Decline generating unit tests for visual snapshots.	Missed	Passed

case-01 · gemini-3.6-flash · 8/20/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md40 linessingle file

Write Tests

Purpose

Generate unit tests for existing code

Routing

Use when: Use when the user requests missing test coverage for a specific file or module.
Do not use when: Don't use for snapshot tests or manual QA-only validation.
Outputs: Prioritized test plan and test cases with clear coverage mapping.
Success criteria: Includes positive/negative cases and test setup assumptions.

Trigger Examples

Positive

Use the write-tests skill for this request.
Help me with write tests.
Use when the user requests missing test coverage for a specific file or module.
Write Tests: provide an actionable result.

Negative

Don't use for snapshot tests or manual QA-only validation.
Do not use write-tests for unrelated requests.
This request is outside write tests scope.
This is conceptual discussion only; no tool workflow is needed.

Parameters

Name	Type	Required	Description
path	string	Yes	Path to the file to test
framework	select	Yes	Testing framework to use

Runtime Prompt

Current runtime prompt length: 339 characters.
Runtime prompt is defined directly in ../write-tests.json.

Track record

Benchmark

16 / 22

test cases passed, vs 15 / 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 v5 — 9/25/2026

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

cowork-os / cowork-os

resources/skills/write-tests/SKILL.md

View on GitHub ↗

License MITImported 9/25/2026Version v2

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

Write Tests

Purpose

Routing

Trigger Examples

Positive

Negative

Parameters

Runtime Prompt

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills