Test-Driven Development (TDD) Skill

Trust Score 87/100

Enforce a strict TDD cycle (red→green→refactor) for feature work: require failing tests first, mock bootstrap validation, full-suite runs, and quality gates bef

triggers:test-driven developmenttddwrite tests firstred green refactormock bootstrap

GitHub SKILL.md

What it does

Provides a procedural TDD enforcement skill that guides agents through the Red→Green→Refactor cycle. It emphasizes test-first development, mock bootstrap validation for mockReset runners, and full-suite verification to avoid regressions.

When to use it

Use when implementing new features, fixing bugs, or adding deliberate test coverage. Trigger when the user requests test-first development, to add tests for a change, or to validate mock setups. Not intended for passive code review or simply running test suites.

What's included

Scripts: None in the skill directory (has_scripts=false)
References: None bundled (has_references=false)
Instructions: Step-by-step TDD process: write failing tests (including bootstrap test for mocks), implement minimal code to pass, run full suite, refactor safely, and run ESLint/TypeScript checks as quality gates. Includes example Vitest patterns and mock forwarding strategies.

Compatible agents

Agents with Node.js and test runner access (Vitest/Jest) and repository file edit capabilities (Claude Code, Copilot-like agents) will get the most value.

Audit Summary

A well-structured TDD enforcement skill that guides agents through a strict red-green-refactor cycle. Includes practical mock patterns for vitest/jest with mockReset handling. No scripts included — purely instructional via SKILL.md. Clear NEVER-rules and quality gates make it unambiguous. The mock bootstrap validation step is a thoughtful touch that prevents common testing pitfalls.

Watch Out

Requires vitest or jest in the target project
mockReset: true detection relies on grep which may miss config in package.json or tsconfig

Notes

No security concerns — purely instructional, no network calls, no credential handling, no destructive commands. The bash commands are standard test/lint invocations. Slightly niche audience (developers already committed to TDD) but genuinely useful for that group.

Information

Repository: agentic-tools
Stars: 11
Installs: 0

Trust Score

Overall87

Security95

Code Quality82

Architecture75

Usefulness72

Related Skills

Starlark Dev

Create, debug, and test Kurtosis Starlark packages — write package structure, run dry-runs, and inspect plan execution for reliable orchestration.

Run Execute

Orchestrates execution of work items across modes (autopilot, confirm, validate) with scripted init/complete tooling, plan/test/report artifacts and strict gati

GraphQL Inspector — Validate

Validate GraphQL operations against a schema with configurable depth, complexity, alias and directive limits to catch errors before runtime.

Alpha Forge Pre-Ship Quality Gates

Pre-merge quality gates for PRs that validate RNG determinism, forked URLs, runtime parameter ranges, and manifest synchronization to reduce review cycles.

OpenTestAI

Automated, high-confidence AI testing: bug detection, persona feedback, and prioritized test-case generation using many specialized tester profiles.

Blender Build-Go (bgo)

Automate build → remove → install → enable → launch cycle for Blender extensions or add-ons to speed up iteration and CI workflows.

Overnight — Autonomous Long-Running Coding

Orchestrates long-running coding goals: decomposes objectives into atomic tasks, dispatches isolated worktree workers, verifies acceptance criteria, and merges

EventKit Integration (iOS/macOS)

Expert EventKit patterns for iOS/macOS: permissions, bidirectional sync, zero-width identity signatures, batch operations, and zombie-task handling.

Back to Skills