Skip to content
Back to skills

Tdd

ASecurity

Use when the plan-review verdict is PROCEED (or plan-review is disabled) and code has not yet been written. Writes RED tests first, defining the contract Builder must satisfy. The mandatory hop before any implementation.

  • 5 stars
  • 0 votes
  • 0 copies
  • 4 views
  • Added September 3, 2026
ai-agentsgodocumentation

Works with

  • cli

Security analysis

A100/100

Scanned October 6, 2026

npx -y skills add mickeyyaya/evolve-loop --skill tdd --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Tdd?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Tdd
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/mickeyyaya-tdd/badge)](https://www.skillsdirectory.com/skills/mickeyyaya-tdd)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: tdd
description: Use when the plan-review verdict is PROCEED (or plan-review is disabled) and code has not yet been written. Writes RED tests first, defining the contract Builder must satisfy. The mandatory hop before any implementation.
---

# tdd

> Sprint 3 composable skill. Wraps the existing TDD-engineer phase with addyosmani-style structure. Mandatory hop before `build`.

## When to invoke

- After `plan-review` returns PROCEED, OR after Scout if plan-review disabled
- Before any new feature implementation
- Before any bug fix (write a regression test first)

## When NOT to invoke

- Eval-only cycles (no implementation needed)
- Pure documentation cycles
- Refactor cycles where existing tests provide coverage (verify first)

## Workflow

| Step | Action | Exit criteria |
|---|---|---|
| 1 | Read scout-report.md and plan-review.md | Inputs verified |
| 2 | Write RED tests (must fail on current code) | Tests exist; running them fails |
| 3 | Document the test contract in `<workspace>/tdd-contract.md` | Contract written |
| 4 | Append section to `<workspace>/team-context.md` | Bus updated for Builder |

**Comments:** code written in this phase carries none; names, types and test names say it, and the build floor counts an added comment ([code-comments convention](../../docs/conventions/code-comments.md)).

## RED requirement

Tests MUST fail when run against the current codebase. A test that passes immediately is NOT a TDD contract — it does not exercise the new behavior. Builder will refuse to start without confirmed RED state.

## Handoffs (beyond the contract artifact)

- `<workspace>/tdd-contract.md` with sections: `## Tests Written`, `## RED Verification`, `## Contract for Builder`
- New/modified test files in the repo (Builder reads these)
- `<workspace>/team-context.md` has populated `## TDD Contract` section

<!-- GENERATED:phase-facts BEGIN — do not edit; run `evolve skills generate`. Sources: docs/architecture/phase-registry.json · go/internal/phasecontract · .evolve/profiles/tdd-engineer.json -->
## Phase facts

| Fact | Value |
|---|---|
| Phase | `tdd` (plan archetype, optional, gated by `workflow.phase_enables.tdd=on`) |
| Persona | `agents/evolve-tdd-engineer.md` |
| Profile | `.evolve/profiles/tdd-engineer.json` — CLI `claude-tmux`, tier `balanced`, single-writer |
| Inputs | `scout-report.md` · `plan-review-report.md` |
| Artifact | `test-report.md` (cycle workspace) |

## Output contract

`test-report.md` must declare:

- `## AC-Materialization` (also accepted: `## Acceptance`, `## Coverage Map`)
- `## RED Run Output` (also accepted: `## RED Tests`, `## Test Files Written`)

<!-- GENERATED:phase-facts END -->

## Composition

Invoked by:
- `/evo:tdd`
- `loop` macro after plan-review (or after discover when plan-review off)

## Reference

- `agents/evolve-tdd-engineer.md` (persona definition)
- `.evolve/profiles/tdd-engineer.json`
- Task priority: the computed inbox rank (CLAUDE.md "/evo:loop task priority", [ADR-0121](../../docs/architecture/adr/0121-inbox-priority-is-a-computed-rank.md))

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.