Ready to supercharge your AI agents?

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

A5c AI/Strict Tdd — measured AI agent skill | DecimalAI

a5c-ai/strict-tdd

SkillScore50Maintained

Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.

by a5c-ai

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

Automatic

Coding pack

decimalai skills pull a5c-ai-strict-tdd

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/a5c-ai-strict-tdd/SKILL.md

Raw file: /s/a5c-ai-strict-tdd/SKILL.md ↗ · machine-readable summary at /s/a5c-ai-strict-tdd.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 9d ago

Yes — +41% lift-15% tokens0% turns50% of whole cases pass with skill (11/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	5%	0%
case-05	✗→✓	▲ Improved	-31%	0%
case-09	✗→✓	▲ Improved	8%	0%
case-10	✗→✓	▲ Improved	-28%	0%
case-14	✗→✓	▲ Improved	-35%	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 — 7/31/2026

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

a5c-ai / babysitter

library/methodologies/pilot-shell/skills/strict-tdd/SKILL.md

View on GitHub ↗

License MITImported 7/31/2026Version v1

Skill contents

SKILL.md

TDD Cycle

RED Phase

Write a test that captures exactly one acceptance criterion
Run the test -- it MUST fail
Verify it fails for the RIGHT reason (not a syntax error)
Commit: test: add failing test for [criterion]

GREEN Phase

Write the MINIMUM code to make the test pass
Run the test -- it MUST pass
Verify only the target test turned green (no side effects)
Commit: feat: implement [criterion]

REFACTOR Phase

Clean up code while keeping ALL tests green
Remove duplication, improve naming, extract methods
Run full test suite -- ALL tests MUST pass
Commit: refactor: clean up [area]

Compliance Scoring

| Score | Meaning | |-------|---------| | 90-100 | Exemplary TDD: all cycles followed correctly | | 70-89 | Good TDD: minor deviations | | 50-69 | Partial TDD: some implementation before tests | | 0-49 | TDD violation: significant implementation without tests |

Verification Methods

Git History Analysis: Test files must appear in commits before implementation files
Coverage Analysis: New code must have >90% test coverage
Commit Message Convention: RED/GREEN/REFACTOR phases identifiable in messages

Want to see if a5c-ai/strict-tdd 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.