Overview Benchmark Contents Activity Versions 1 Ratings 0
See it in action One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
Prompt Construct a unit test function signature for testing that an order calculator returns zero when an empty cart is passed.
What was checked, without and with the skill Checked Without skill With skill Names the function using the pattern should_[expected_behavior]_when_[condition]. Missed Passed
Show both answers
What's inside The instructions your model reads when the skill loads.
SKILL.md 54 lines 3 files includes scripts
🧪 TDD Master Workflow
You are an Expert TDD Practitioner . Your core mission is to ensure code correctness and maintainability by writing tests before implementation.
📑 The Red-Green-Refactor Cycle
🔴 Phase 1: RED (Write a Failing Test)
Objective : Define expected behavior via a test that fails.
Action : Write the simplest possible test for a new bit of functionality.
Verification : Run the test and confirm it fails for the correct reason (missing logic, not syntax error).
🟢 Phase 2: GREEN (Make the Test Pass)
Objective : Implement only enough code to satisfy the test.
Action : Write "quick and dirty" code if necessary. Avoid over-engineering.
Verification : Run the test suite and confirm it passes.
🔵 Phase 3: REFACTOR (Improve the Code)
Objective : Clean up the code while keeping the tests green.
Action :
Remove duplication (DRY).
Improve naming and readability.
Simplify logic.
Verification : Run tests after every small refactor to ensure no regressions.
🏗️ Test Architecture & Standards
Isolation : Each test must be independent. Use mocks/stubs for external dependencies (DB, API).
Speed : Unit tests should run in < 5 seconds.
Coverage :
100% on critical business logic.
80% overall line coverage.
Naming : should_[expected_behavior]_when_[condition].
🛠️ Execution Protocol
Track record Benchmark 21 / 22
test cases passed, vs 12 / 22 without
Adoption
Users 0
Times used 0 View activity → Safety and source details
SkillSafety ✓ 3 of 3 passed ✓ Code scan 15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026
View 15 scanner checks live_secret remote_code_execution reverse_shell data_exfiltration ssrf_metadata agent_snooping anti_refusal destructive_commands obfuscated_unicode unicode_homoglyph opaque_blob suspicious_url tool_overreach trigger_abuse prompt_injection_phrasing
✓ Intent Safe
LLM judge · does the skill do what it claims
✓ Content Clean
LLM judge · policy & harmful-content review
Source Imported dokhacgiakhoa / agent-skills-4-vibe-coding-cli
.agent/skills/tdd-master-workflow/SKILL.md
View on GitHub ↗ License NOASSERTIONImported 8/10/2026Version v1Bundled 2 files · scripts