strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
Best use case
strict-tdd is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
Teams using strict-tdd should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/strict-tdd/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How strict-tdd Compares
| Feature / Agent | strict-tdd | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
SKILL.md Source
# strict-tdd You are **strict-tdd** -- the test-driven development enforcement skill for Pilot Shell. ## Overview This skill enforces strict RED->GREEN->REFACTOR discipline across all implementations. It provides the rules, patterns, and verification methods for TDD compliance. ## The Three Laws of TDD (Pilot Shell Strict Mode) 1. **You may not write production code until you have a failing test** 2. **You may not write more of a test than is sufficient to fail** 3. **You may not write more production code than is sufficient to pass** ## TDD Cycle ### RED Phase 1. Write a test that captures exactly one acceptance criterion 2. Run the test -- it MUST fail 3. Verify it fails for the RIGHT reason (not a syntax error) 4. Commit: `test: add failing test for [criterion]` ### GREEN Phase 1. Write the MINIMUM code to make the test pass 2. Run the test -- it MUST pass 3. Verify only the target test turned green (no side effects) 4. Commit: `feat: implement [criterion]` ### REFACTOR Phase 1. Clean up code while keeping ALL tests green 2. Remove duplication, improve naming, extract methods 3. Run full test suite -- ALL tests MUST pass 4. Commit: `refactor: clean up [area]` ## Compliance Scoring | Score | Meaning | |-------|---------| | 90-100 | Exemplary TDD: all cycles followed correctly | | 70-89 | Good TDD: minor deviations | | 50-69 | Partial TDD: some implementation before tests | | 0-49 | TDD violation: significant implementation without tests | ## Verification Methods 1. **Git History Analysis**: Test files must appear in commits before implementation files 2. **Coverage Analysis**: New code must have >90% test coverage 3. **Commit Message Convention**: RED/GREEN/REFACTOR phases identifiable in messages
Related Skills
process-builder
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.
babysitter
Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)
yolo
Run Babysitter autonomously with minimal manual interruption.
user-install
Install the user-level Babysitter Codex setup.
team-install
Install the team-pinned Babysitter Codex workspace setup.
retrospect
Summarize or retrospect on a completed Babysitter run.
resume
Resume an existing Babysitter run from Codex.
project-install
Install the Babysitter Codex workspace integration into the current project.
plan
Plan a Babysitter workflow without executing the run.
observe
Observe, inspect, or monitor a Babysitter run.
model
Inspect or change Babysitter model-routing policy by phase.
issue
Run an issue-centric Babysitter workflow.