Testing & Debugging for Claude Code

Essential AI agents: agent-manager, code-analyzer, file-analyzer, test-runner

Comprehensive testing: E2E, TDD, performance, security testing with multiple frameworks

Generic agentic evaluation for skills and agents. Provides end-to-end skills to analyze, test, score, review, and iteratively improve agent skills with MLflow support for experiment tracking, tracing, and reporting.

DSPy-powered AI safety monitor for detecting backdoors and malicious behavior in code with 90% detection rate

Essential development agents: planner, coder, reviewer, tester, and researcher

Core development methodology and Claude Code extensibility. Includes TDD, debugging, architecture, research, multi-agent coordination, plus skills/plugins/agents/hooks authoring for Claude Code and Codex configuration.

Outfitter Stack patterns: Result types, handler contract, error taxonomy for type-safe APIs

TDD London School agents, production validators, and comprehensive test automation

Call AdCP advertising agent tools over MCP or A2A, run protocol compliance scenarios, and query the AdCP registry. Includes built-in test agents for zero-config use.

Operational memory for coding agents: recall past mistakes before you act, encode the lesson when something goes wrong.

Track skill usage, tokens, and test coverage monthly

Exchange Online mail flow diagnostics and deliverability — guided 'email not received' troubleshooting, transport rules, quarantine, connectors, and SPF/DKIM/DMARC checks with client-safe explanations

Query Langfuse traces for debugging LLM calls, analyzing token usage, and investigating workflow executions

Build, debug, package, and certify custom Power BI visuals with the pbiviz toolchain — project scaffolding, capabilities and dataView mapping, the IVisual API, the modern format pane and formatting model, selection and cross-filtering, tooltips, unit testing, and AppSource certification — plus declarative Deneb (Vega and Vega-Lite) specs with cross-filtering, theme colors, and templates

Power BI paginated reports through Fabric — RDL authoring, VB.NET expressions, data source configuration, rendering/export, REST API automation, SSRS-to-Fabric migration, performance tuning, and troubleshooting

11 reusable skills for AI agents (planning, code-writing, testing, etc.) plus a /skillfold compiler command

Development autopilot — 14 skills for workflow, research, decisions, quality, lifecycle, debugging, and self-improvement

Evaluate AI skills across model tiers with blind testing and refinement recommendations

Ralph autonomous loop + Superpowers skills: brainstorming, TDD, systematic debugging, subagent-driven development, code review, and verification workflows

MOOS-IvP skills for apps, IvP behaviors, missions, test harnesses, documentation, and alog analysis.

English skills: evidence-disciplined testing framework, Playwright test review, test cases, Jira bug reports

Русская версия скиллов: дотошное тестирование с доказательной дисциплиной

Deep test, analyze, and audit Claude skills with API tracing, script I/O capture, and security/code review agents.

Expert Swift and SwiftUI guidance for state management, navigation, testing, dependency injection, performance optimization, and code quality patterns.

Skills plugin for Claude Code: analysis, TDD, debugging, and structured workflows

Auto-kills stuck Claude Code processes when CPU stays above 70% after stopping. Fixes the React/Ink render loop bug.

GPT-5.2 strategic advisor with deep reasoning. Read-only access for architecture decisions, security analysis, and complex debugging.

Prompt, skill, red-team, and agent behavior evaluation workflows.

Skills and agents for working with Ark - testing, setup, analysis, and research

Swift app build, debug, profile, package, App Store, TestFlight, simulator, macOS, iOS, and Xcode workflows.

Reduce token consumption by 70-80% when using Chrome DevTools MCP through smart snapshot strategies and optional Gemini Flash vision processing. Includes optimization rules, decision trees, and pattern guides for navigation, forms, debugging, and visual checks.

Multi-agent competitive simulations with 3 skills and 12 specialist agents for bug hunting, code quality, and user flow testing

Error diagnosis, fault isolation, log forensics, and incident investigation.

FastAPI async patterns and Pydantic models

5 knowledge cutoff awareness hooks for version verification and API compatibility checking

6 strict TypeScript typing hooks enforcing zero-any and explicit types

Kotlin Multiplatform architecture, Gradle diagnosis, Compose Multiplatform, interop, testing, data, governance, performance, security, publishing, and release workflows.

ML pipeline design, experiment tracking, model evaluation, training debugging, and reproducibility.