Mmcp.market

strict-tdd skill

by a5c-ai·a5c-ai/babysitter·1.8k stars·MIT

Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.

A100/100content scan

Is the strict-tdd skill safe?

Clean: nothing in its files matched our rules. We read 2 files in the folder on 2026-09-28.

No findings.

Install the strict-tdd skill

A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description. 

git clone --depth 1 https://github.com/a5c-ai/babysitter.git /tmp/babysitter
mkdir -p ~/.claude/skills
cp -r /tmp/babysitter/library/methodologies/pilot-shell/skills/strict-tdd ~/.claude/skills/strict-tdd
available in every project

In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub

The instructions your agent would load

SKILL.md as published, without the frontmatter. Read it on GitHub

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

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

More skills from a5c-ai/babysitter

  • Aadversarial-reviewFresh adversarial code review with binary PASS/FAIL verdicts, evidence citations, and anchoring bias prevention via fresh reviewer spawning.
  • Aagent-boosterWASM-based instant code transforms for simple tasks, achieving 352x speedup over LLM inference with zero cost.
  • Aagent-coordinationCoordinate Crew (persistent) and Polecat (transient) agents using Gas Town's hook-based work distribution and GUPP principle.
  • Aagent-dispatch
  • Aanti-driftHierarchical coordination and drift detection with frequent checkpoints, shared memory coherence validation, role specialization enforcement, and short task cycles.
  • Aarchitecture-design
  • Aarchitecture-patternsSystem and API design guidance covering component boundaries, data flow, integration patterns, and scalability considerations.
  • Aassimilate-popular-workflowsThis skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable processes, babysitter plugins, and reusable procedural insights. Searches GitHub for SKILL.md files, classifies repos by archetype, and maintains structured research under docs/reference-repos/.
  • Aaudit-trail
  • AbabysitOrchestrate 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.)
  • Ababysit-babysitter-issuesThis skill should be used when the user asks to "babysit issues", "work on assigned issues", "check a5c-agent issues", "process babysitter issues", or wants to find and work on open GitHub issues assigned to a5c-agent in the babysitter repo.
  • Abehavior-contractBug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.

All agent skills → · MCP servers