ワンクリックでManusで任意のスキルを実行

vcsdd-tdd

スター27

フォーク4

更新日2026年4月1日 08:58

Run Phase 2a (test generation, Red phase) for the active VCSDD feature. Invokes vcsdd-builder to generate failing tests for all spec requirements. Records red phase evidence.

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

Manusで実行

ソース

sc30gsw

sc30gsw/vcsdd-claude-code

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Manusで実行

What

Runs the Red phase (Phase 2a): generates test cases for every requirement in the behavioral spec. Tests MUST FAIL before implementation begins. Records failure evidence.

When

Run after spec review gate (Phase 1c) passes. Requires active feature at phase 1c.

How

Read behavioral spec: extract all REQ-XXX requirements
Invoke vcsdd-builder agent to generate tests:
- One test function per requirement minimum
- Additional tests for each edge case in spec
- Tests for error conditions and boundary values
Create test-case beads: one per test function, linked to corresponding REQ-XXX bead
Transition to 2a: this starts sprint N for the current implementation cycle (transitionPhase(feature, '2a'))

Run tests and verify they FAIL:

npm test 2>&1 | tee .vcsdd/features/<name>/evidence/sprint-N-red-phase.log

Verify regression baseline: run existing tests separately to confirm they still pass
Record red phase evidence in the active sprint with explicit markers at the top of the log:
```
new-feature-tests: FAIL
regression-baseline: PASS
```
For coverage-retrofit sprints (adding tests to already-implemented code):
- Use coverage-retrofit: true instead of new-feature-tests: failing
- Example:
```
coverage-retrofit: true
regression-baseline: PASS
total-tests: 45
new-tests-added: 3
```
Append the raw failing test output after those markers so the gate can prove both conditions
Display summary: sprint number, N tests generated, all failing as expected

CRITICAL: Red Phase Validation

If ANY new test passes before implementation, STOP. The test is invalid (it's testing the wrong thing or the implementation already exists). Fix the test first.

Examples

/vcsdd-tdd
/vcsdd-tdd --framework vitest    # specify test framework
/vcsdd-tdd --framework pytest

このリポジトリの他の Skills

同じリポジトリ

vcsdd-adversarial-refinement

sc30gsw/vcsdd-claude-code

Use this skill when running or interpreting VCSDD adversarial reviews. Provides calibration guidance for the Adversary agent, finding severity classification, and anti-leniency enforcement patterns.

2026-04-0127

vcsdd-adversary

sc30gsw/vcsdd-claude-code

Run Phase 3 (adversarial review) for the active VCSDD feature. Spawns a fresh vcsdd-adversary agent with zero Builder context to review implementation against spec. Produces binary PASS/FAIL verdict per dimension.

2026-04-0127

vcsdd-commit

sc30gsw/vcsdd-claude-code

Create a git commit for the current VCSDD phase. Auto-generates a conventional commit message from state.json including phase, sprint, gate verdict, and affected bead IDs. Tags with vcsdd/<feature>/phase-<id>.

2026-04-0127

vcsdd-contract-review

sc30gsw/vcsdd-claude-code

Run the strict-mode sprint contract review after Phase 2c. Spawns a fresh vcsdd-adversary instance to review `contracts/sprint-N.md` and writes a PASS/FAIL verdict under `reviews/contracts/sprint-N/output/`.

2026-04-0127

vcsdd-converge

sc30gsw/vcsdd-claude-code

Run Phase 6 (convergence check) for the active VCSDD feature. Validates four-dimensional convergence: finding diminishment, finding specificity, criteria coverage, and duplicate detection.

2026-04-0127

vcsdd-convergence-detection

sc30gsw/vcsdd-claude-code

Use this skill during Phase 6 convergence checks. Provides four-dimensional convergence analysis, hallucination detection, and duplicate finding identification.

2026-04-0127

name	vcsdd-tdd
description	Run Phase 2a (test generation, Red phase) for the active VCSDD feature. Invokes vcsdd-builder to generate failing tests for all spec requirements. Records red phase evidence.

What

Runs the Red phase (Phase 2a): generates test cases for every requirement in the behavioral spec. Tests MUST FAIL before implementation begins. Records failure evidence.

When

Run after spec review gate (Phase 1c) passes. Requires active feature at phase 1c.

How

Read behavioral spec: extract all REQ-XXX requirements
Invoke vcsdd-builder agent to generate tests:
- One test function per requirement minimum
- Additional tests for each edge case in spec
- Tests for error conditions and boundary values
Create test-case beads: one per test function, linked to corresponding REQ-XXX bead
Transition to 2a: this starts sprint N for the current implementation cycle (transitionPhase(feature, '2a'))

Run tests and verify they FAIL:

npm test 2>&1 | tee .vcsdd/features/<name>/evidence/sprint-N-red-phase.log

Verify regression baseline: run existing tests separately to confirm they still pass
Record red phase evidence in the active sprint with explicit markers at the top of the log:
```
new-feature-tests: FAIL
regression-baseline: PASS
```
For coverage-retrofit sprints (adding tests to already-implemented code):
- Use coverage-retrofit: true instead of new-feature-tests: failing
- Example:
```
coverage-retrofit: true
regression-baseline: PASS
total-tests: 45
new-tests-added: 3
```
Append the raw failing test output after those markers so the gate can prove both conditions
Display summary: sprint number, N tests generated, all failing as expected

CRITICAL: Red Phase Validation

If ANY new test passes before implementation, STOP. The test is invalid (it's testing the wrong thing or the implementation already exists). Fix the test first.

Examples

/vcsdd-tdd
/vcsdd-tdd --framework vitest    # specify test framework
/vcsdd-tdd --framework pytest