Ready to supercharge your AI agents?

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

Get Started Free →

Ruvnet/Tdd Workflow — measured AI agent skill | DecimalAI

ruvnet/tdd-workflow

NewSkillScoreMaintained

TDD London School workflow -- mock-first, outside-in test development

by ruvnet

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

Automatic

Coding pack

decimalai skills pull ruvnet-tdd-workflow

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/ruvnet-tdd-workflow/SKILL.md

Raw file: /s/ruvnet-tdd-workflow/SKILL.md ↗ · machine-readable summary at /s/ruvnet-tdd-workflow.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 2d ago

—-13% tokens0% turns32% of whole cases pass with skill (7/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-06	✗→✓	▲ Improved	-11%	0%
case-10	✗→✓	▲ Improved	-60%	0%
case-13	✗→✓	▲ Improved	-42%	0%
case-14	✓→✗	▼ Worse	-78%	0%
case-07	✓→✗	▼ Worse	-71%	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 — 8/2/2026

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

ruvnet / ruflo

plugins/ruflo-testgen/skills/tdd-workflow/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1

Skill contents

SKILL.md

Follow the TDD London School (mock-first) approach:

Write the failing test first -- define expected behavior with mocked dependencies
Run the test -- confirm it fails for the right reason
Implement minimal code -- make the test pass with the simplest solution
Refactor -- clean up while keeping tests green
Repeat -- add the next behavior

Before starting: mcp__plugin_ruflo-core_ruflo__hooks_pre-task({ description: "TDD: FEATURE_NAME" }) After completing: mcp__plugin_ruflo-core_ruflo__hooks_post-task({ taskId: "tdd-FEATURE", success: true, storeResults: true })

Principles:

Mock external dependencies at boundaries
Test behavior, not implementation
One assertion per test when possible
Descriptive names: should [behavior] when [condition]

Want to see if ruvnet/tdd-workflow 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.