Tony363

Deep research on any topic combining real-time web search (Rube MCP) with multi-model consensus analysis (PAL MCP). Produces structured reports with sourced findings and confidence assessments.

Feature implementation with intelligent persona activation, task orchestration, and MCP integration. Use when implementing features, APIs, components, services, or coordinating multi-agent development. Triggers on requests for code implementation, feature development, or complex task orchestration.

Enforce KISS, Purity, SOLID, and Let It Crash principles through mandatory validation gates. Detects complexity violations, impure functions, design anti-patterns, and error handling issues.

Interactive multi-model consensus code review using PAL MCP. Reviews commits, staged changes, or branch diffs with user-directed scope and interactive decision points.

E2E testing workflow supporting Playwright, Cypress, and Selenium. Run, debug, record, trace, generate test scaffolds, and view reports. Use when running browser tests, debugging E2E failures, or generating test scaffolds.

Comprehensive MCP orchestration skill integrating PAL MCP (reasoning, consensus, debugging) and Rube MCP (500+ app automations). Central hub for all MCP-powered workflows.

Strict Test-Driven Development enforcer with Red-Green-Refactor workflow automation. Auto-detects frameworks, validates semantic test failures, and blocks production code until tests fail properly. Use for feature development, bug fixes with test coverage, or refactoring with safety nets.

Multi-remote git push with selective content filtering. Push to multiple remotes with per-remote path exclusions, branch mapping, and force-push controls.

Execute tests with coverage analysis, gap identification, test generation, and automated quality reporting. Use when running tests, analyzing coverage, generating missing tests, or debugging test failures.

Auto-update project documentation by analyzing git changes with cross-reference validation and staleness reporting. Supports single-file README updates or multi-document review. Use when synchronizing documentation with code changes.

Provide clear explanations of code, concepts, and system behavior with educational clarity. Use when understanding code, learning concepts, or knowledge transfer.

Analyze application logs, identify errors, perform root cause analysis, and interactively fix issues with a learned knowledge base. Use when debugging from logs, triaging errors, or fixing recurring issues.

LLM pipeline evaluation with oracle judge scoring. Runs prompts against gold standard datasets, evaluates output quality via LLM-as-judge, and generates scored reports with improvement recommendations.

Run all local CI checks before creating a PR with interactive failure remediation. Use when validating code quality before pull requests, running pre-flight checks, or fixing CI failures locally.