Ready to supercharge your AI agents?

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

Outside-In TDD Methodology · nwave-ai | DecimalAI

testingby nwave-ai

Outside-In TDD Methodology

nwave-ai/nw-tdd-methodology

Source nwave-ai/nwave ↗License MIT

Deep knowledge for Outside-In TDD - double-loop architecture, ATDD integration, port-to-port testing, walking skeletons, and test doubles policy

SkillScore86Maintained

On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.

QA & Test Engineering pack

Last verified 8/16/2026

What it changes

Passed 19 of 22 test cases with the skill, and 11 of 22 without it.

Without skill50%

With skill86%

Checks it passed that the model alone missed

Uses standard docker build and push actions.
Uses the des-commit command for version control commits.
Includes Modeling among the property-finding strategies.

and 9 more in the full report

8 fixed11 passed either way3 still failing0 broke

Pass-rate lift: +36 pp
Tokens: +271%
Agent turns: 0%
Response time: -43%

Model gemini-3.6-flashMeasured 8/16/2026v119 of 22 cases passed with skill

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

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/nwave-ai-nw-tdd-methodology/SKILL.md https://app.decimal.ai/s/nwave-ai-nw-tdd-methodology/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add nwave-ai-nw-tdd-methodology, 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/nwave-ai-nw-tdd-methodology/ and pins it in .decimal/skills.lock

decimalai skills add nwave-ai-nw-tdd-methodology

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

curl -fsSL --create-dirs -o .claude/skills/nwave-ai-nw-tdd-methodology/SKILL.md https://app.decimal.ai/s/nwave-ai-nw-tdd-methodology/SKILL.md

Raw file: /s/nwave-ai-nw-tdd-methodology/SKILL.md ↗ · machine-readable summary at /s/nwave-ai-nw-tdd-methodology.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 8

Prompt

We have finished implementing a feature slice and all unit and acceptance tests are passing GREEN. We need to create a version control commit for the modified files in our workflow step `step-42`. Provide the exact terminal command to execute this commit.

What was checked, without and with the skill
Checked	Without skill	With skill
Uses the des-commit command for version control commits.	Missed	Passed
Passes the step identifier trailer option matching step-42.	Missed	Passed

case-07 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md588 linessingle file

Outside-In TDD Methodology

LANGUAGE CONVENTION FRAME (read FIRST — overrides all examples below)

Code examples in this skill use Python syntax for illustration only. They are NOT prescriptive about target language. nWave is language-agnostic per the "genericity and agnosticism" mandate (2026-05-24).

Before applying TDD cycle, detect the target project's language from manifest files: package.json → TypeScript/JS (jest/vitest); Cargo.toml → Rust (cargo test/proptest); go.mod → Go (testing/ginkgo); pyproject.toml/setup.py/Pipfile → Python (pytest/hypothesis); pom.xml/build.gradle → Java/Kotlin (JUnit5/jqwik); *.csproj/*.fsproj → C#/F# (xUnit/FsCheck); Gemfile → Ruby (RSpec); Package.swift → Swift (XCTest/swift-testing).

When the target language is NOT Python: adapt EVERY code example — replace Python imports, type hints, class/function syntax, test-framework specifics with target equivalents. Project conventions ALWAYS WIN over skill examples.

Empirical anchor: skill examples being Python-only caused LLM to emit Python code in greenfield TS project despite language-agnostic mandate. Fix per F-SKILL-EXAMPLES-LANGUAGE-LEAK. Connects [[feedback_language_adapter_plugin_architecture_2026_05_24]].

TDD cycle — 3-phase canonical (ADR-025, 2026-05-07)

Current canonical: DELIVER cycle is 3-phase: RED → GREEN → COMMIT.

RED absorbs PREPARE + RED_ACCEPTANCE + RED_UNIT (legacy 5-phase). Writes PBT unit tests targeting production code; unskips the corresponding AT scenario authored upstream by DISTILL. Exits via the fail-for-right-reason gate — both PBT unit + AT must fail with a semantically-correct error (AssertionError / expected-exception-not-thrown), not a collection error / import error / skip marker. The gate preserves RED→GREEN discipline atomically without separate phase boundaries.
GREEN: implement minimum production code making PBT unit + AT pass. Exit gate all-tests-pass.
COMMIT: commit this step's owned files via des-commit (carries the Step-Id: trailer and is parallel-safe — see issue #51 / ADR-027), not raw git add/git commit. F-DES-COMMIT-PHASE-CRAFTER-DEAD-PATH guidance in commit.yaml addresses adapter-probe annotation requirement.

DISTILL retains canonical AT authorship (per nw-distill Mandate 7). RED phase in DELIVER does NOT write acceptance scenarios from scratch — it only unskips the scaffolds DISTILL produced.

Legacy (5-phase v4 contract, ADR-024 era) — PREPARE / RED_ACCEPTANCE / RED_UNIT / GREEN / COMMIT — preserved for audit-log replay of pre-2026-05-07 commits. Future features use 3-phase canon. References to RED_ACCEPTANCE / RED_UNIT below describe the legacy contract; new work treats them as merged inside RED.

Paradigm Mandate — Property-Based + State-Delta (STANDING, 2026-05-05)

Default test-writing paradigm for UNIT + ACCEPTANCE tests — not optional, not "when applicable".

Test-level applicability matrix

Level	Default paradigm	Rationale
Unit	Property-based + state-delta — single-example is FALLBACK only	Property tests cover equivalence classes; the state-delta universe forbids hidden mutations on adjacent slots
Acceptance (Gherkin)	`Property:` framing with quantified preconditions; classic `Scenario:` is FALLBACK	Acceptance tests document system invariants; properties express the spec better than picked examples
Integration	UNCHANGED — single-example test verifies WIRING	The contract is "wires connect correctly", not "all input shapes succeed". One representative call suffices
E2E	UNCHANGED — single-example end-to-end happy path	The contract is "complete flow connects", not "all flows are equivalent". One golden walkthrough suffices

Mandate (unit + acceptance levels)

Every unit and acceptance test you write MUST be:

Track record

Benchmark

19 / 22

test cases passed, vs 11 / 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 v4 — 8/3/2026

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

nwave-ai / nwave

nWave/skills/nw-tdd-methodology/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

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

Outside-In TDD Methodology

LANGUAGE CONVENTION FRAME (read FIRST — overrides all examples below)

TDD cycle — 3-phase canonical (ADR-025, 2026-05-07)

Paradigm Mandate — Property-Based + State-Delta (STANDING, 2026-05-05)

Test-level applicability matrix

Mandate (unit + acceptance levels)

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills