From vcsdd
Generates failing tests for VCSDD feature spec requirements in Red phase (2a). Invokes builder, runs tests, records failure evidence and regression baseline. Supports vitest/pytest.
How this skill is triggered — by the user, by Claude, or both
Slash command
/vcsdd:vcsdd-tddThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
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.
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.
Run after spec review gate (Phase 1c) passes. Requires active feature at phase 1c.
N for the current implementation cycle (transitionPhase(feature, '2a'))npm test 2>&1 | tee .vcsdd/features/<name>/evidence/sprint-N-red-phase.log
new-feature-tests: FAIL
regression-baseline: PASS
For coverage-retrofit sprints (adding tests to already-implemented code):
coverage-retrofit: true instead of new-feature-tests: failingcoverage-retrofit: true
regression-baseline: PASS
total-tests: 45
new-tests-added: 3
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.
/vcsdd-tdd
/vcsdd-tdd --framework vitest # specify test framework
/vcsdd-tdd --framework pytest
npx claudepluginhub sc30gsw/vcsdd-claude-code --plugin vcsddImplements VCSDD Phase 2b (Green): minimal code via vcsdd-builder to pass failing tests; Phase 2c (Refactor): improves code while keeping tests green; logs npm test evidence. Use after Phase 2a.
Writes failing tests from feature specs for TDD RED phase, parsing acceptance criteria and user test cases to match project test framework and conventions.
Generates failing tests following TDD red phase principles, covering happy paths, edge cases, and error handling across multiple frameworks.