Ready to supercharge your AI agents?

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

Get Started Free →

Write the Failing Test First — measured AI agent skill | DecimalAI

archive228/write-failing-test-first

SkillScore36Maintained

Before fixing any bug, write a test that reproduces it and watch it fail. Use for every bug fix.

Testingby archive228

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

QA & Test Engineering pack

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

pip install decimalai

2 · Get the skill — writes .claude/skills/archive228-write-failing-test-first/SKILL.md

decimalai skills pull archive228-write-failing-test-first --out .claude/skills/

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

curl -fsSL --create-dirs -o .claude/skills/archive228-write-failing-test-first/SKILL.md https://app.decimal.ai/s/archive228-write-failing-test-first/SKILL.md

Raw file: /s/archive228-write-failing-test-first/SKILL.md ↗ · machine-readable summary at /s/archive228-write-failing-test-first.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 6h ago

—-36% tokens0% turns36% of whole cases pass with skill (8/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-02	✗→✓	▲ Improved	-7%	0%
case-12	✗→✓	▲ Improved	13%	0%
case-15	✗→✓	▲ Improved	-12%	0%
case-18	✗→✓	▲ Improved	29%	0%
case-20	✗→✓	▲ Improved	1527%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

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

archive228 / loopkit

skills/write-failing-test-first/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

Write the Failing Test First

The only proof you fixed a bug is a test that failed before and passes after.

Write the smallest test that reproduces the reported behavior.
Run it. Watch it fail for the right reason (read the assertion, not just red).
Now fix the code.
Run the test. It passes. Run the FULL suite — you didn't break anything else.

If you can't write the test easily, the architecture is telling you something (tight coupling). Say so. Never: fix first, test after (you'll write a test that passes regardless). Never: skip the watch-it-fail step.

Want to see if archive228/write-failing-test-first would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.