Teaches Claude to proactively drive thorough testing via gap analysis, convergence loops, and persistent status tracking. Framework-agnostic core with stack-specific profiles.
npx claudepluginhub l3digitalnet/claude-code-plugins --plugin test-driverForce a full gap analysis on the current project. Detects project type, loads stack profile, inventories source and test files, identifies gaps, and optionally enters a convergence loop to fill them.
View current test posture from TEST_STATUS.json without running any tests or analysis.
Iterative test generation and fix engine. Use when filling test gaps identified by gap-analysis: generates tests in batches, runs them, fixes failures, and iterates until all pass or exit criteria are met. Includes oscillation detection, bug fix boundaries, and convergence reporting. Triggers on: convergence loop, test loop, generate and fix tests, iterate tests, fill test gaps, run tests until green, test convergence.
Test gap analysis methodology for finding missing tests across six categories (unit, integration, e2e, UI, contract, security). Use when conducting a gap analysis, auditing test coverage, identifying untested code, inventorying tests, or when /test-driver:analyze is invoked. Provides the step-by-step process for detecting project type, loading stack profiles, and producing a prioritized gap report.
Stack profile for Home Assistant custom integrations. Activated when test-driver detects manifest.json with a "domain" key and a custom_components/ directory. Defines applicable test categories, discovery conventions, execution commands, and coverage tools for HA custom components.
Stack profile for Django web applications. Activated when test-driver detects django in pyproject.toml dependencies. Defines applicable test categories, discovery conventions, execution commands, coverage tools, and UI testing via Charlotte or Playwright.
Stack profile for FastAPI and Starlette projects. Activated when test-driver detects fastapi or starlette in pyproject.toml dependencies. Defines applicable test categories, discovery conventions, execution commands, coverage tools, and key testing patterns for FastAPI APIs.
Stack profile for PySide6 and PyQt6 desktop applications. Activated when test-driver detects PySide6 or PyQt6 in pyproject.toml dependencies. Defines applicable test categories, discovery conventions, execution commands, coverage tools, and UI testing via pytest-qt and Qt Pilot.
Stack profile for Swift and SwiftUI iOS/macOS applications. Activated when test-driver detects Package.swift or .xcodeproj in the project. Defines applicable test categories, discovery conventions, execution commands, coverage tools, and UI testing via XCUITest.
Universal test design principles for writing effective tests regardless of framework. Use when writing tests, reviewing test quality, designing test structure, choosing what to test, or applying test patterns. Covers isolation, boundary testing, error paths, Arrange-Act-Assert, naming, mock boundaries, and meaningful assertions.
Persistent test status file management. Governs reading and writing docs/testing/TEST_STATUS.json, the persistent record of a project's testing posture. Use when checking test status, updating test results, reading TEST_STATUS.json, writing test reports, tracking test history, or managing deferred test gaps.
Always-on testing awareness driver. MUST consult during any implementation task to evaluate whether testing is needed at this point. Applies to every task involving code changes. Governs: when to suggest gap analysis, how to assess test coverage needs, delegation to framework-specific testing plugins, and non-intrusive suggestion cadence. Triggers on: test, implement, feature, fix, bug, refactor, build, create, modify, change, add, update, debug, complete, finish, deploy, merge, PR, commit.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research