yonatangross

OrchestKit doctor for health diagnostics across manifest integrity, hook configuration, skill validation, agent frontmatter, MCP server connectivity, CC version compatibility, and permission rules. Reports issues with severity levels and auto-remediation suggestions. Validates component counts, detects orphaned entries, and checks CC version matrix compliance. Use when diagnosing plugin health, troubleshooting configuration issues, or running pre-release checks.

Interactive configuration wizard for OrchestKit plugin settings including MCP server enablement, hook permissions, keybindings, and installation presets (Complete/Standard/Lite). Supports preset shortcuts, per-category skill customization, and webhook configuration. Use when customizing plugin behavior or managing settings.

Vision, audio, video generation, and multimodal LLM integration patterns. Use when processing images, transcribing audio, generating speech, generating AI video (Kling v3, Sora 2, Veo 3.1 std/lite/fast, Runway Gen-4.5 via `gen4_turbo`), or building multimodal AI pipelines.

Evaluates platform upgrade readiness across Claude model versions, CC releases, and OrchestKit updates with 6-dimensional assessment. Researches target versions, detects current environment, produces structured migration plan with risk scores. Use when planning major version transitions or evaluating upgrade impact.

PR review using parallel specialized agents for code quality, security, testing, architecture, and performance analysis. Synthesizes findings into a review report with conventional comments (praise/issue/suggestion/nitpick) and approve or request-changes verdict. Use when reviewing pull requests, conducting security audits, or validating changes before merge.

Comprehensive verification using parallel test agents for unit tests, integration tests, E2E validation, security scanning, and type checking. Runs coverage analysis, detects regressions, and validates against project conventions. Reports pass/fail with detailed findings and coverage deltas. Use when verifying implementations, validating changes after /ork:implement, or running pre-merge quality gates.

Assesses and rates quality 0-10 across multiple dimensions (correctness, maintainability, security, performance, testability, simplicity) with pros/cons analysis. Compares against project conventions and prior decisions from memory. Produces structured evaluation reports with actionable improvement suggestions. Use when evaluating code, designs, architectures, or comparing alternative approaches.

API design patterns for REST/GraphQL framework design, versioning strategies, and RFC 9457 error handling. Use when designing API endpoints, choosing versioning schemes, implementing Problem Details errors, or building OpenAPI specifications.

Build AI-first applications with RAG pipelines, embeddings, vector databases, agentic workflows, and LLM integration. Master prompt engineering, function calling, streaming responses, and cost optimization for 2025+ AI development. Includes local LLM inference with Ollama for 93% CI cost reduction.

Use this skill when designing REST, GraphQL, or gRPC APIs. Provides comprehensive API design patterns, versioning strategies, error handling conventions, authentication approaches, and OpenAPI/AsyncAPI templates. Ensures consistent, well-documented, and developer-friendly APIs across all backend services.

Use this skill when documenting significant architectural decisions. Provides ADR templates following the Nygard format with sections for context, decision, consequences, and alternatives. Helps teams maintain architectural memory and rationale for backend systems, API designs, database choices, and infrastructure decisions.

Create beautiful ASCII art visualizations for plans, architectures, workflows, and data

Use when creating or developing anything, before writing code or implementation plans - refines rough ideas into fully-formed designs through structured Socratic questioning, alternative exploration, and incremental validation

Capture content from JavaScript-rendered pages, login-protected sites, and multi-page documentation using Playwright MCP tools or Claude Chrome extension. Use when WebFetch fails on SPAs, dynamic content, or auth-required pages.

Use this skill when designing database schemas for relational (SQL) or document (NoSQL) databases. Provides normalization guidelines, indexing strategies, migration patterns, and performance optimization techniques. Ensures scalable, maintainable, and performant data models.

Use this skill when creating or evolving design systems for applications. Provides design token structures, component architecture patterns, documentation templates, and accessibility guidelines. Ensures consistent, scalable, and accessible UI design across products.

Analyze ETFs — holdings composition, sector and geographic exposure, expense ratio, and index-tracking error. Use when the user asks about an ETF ticker (SPY, QQQ, VTI, etc.), wants to compare two ETFs, check overlap between funds, or understand what an ETF holds and costs. Provides top-holdings breakdown, overlap percentage, cost comparison, and tracking-error context. Do NOT use for individual-stock analysis (use global-stock-analysis) or Israeli mutual funds.

Analyze US and global stocks (NASDAQ, NYSE, S&P 500 constituents) with technical, fundamental, and sentiment signals. Use when the user asks about international stocks, tickers like AAPL/NVDA/MSFT, S&P 500 or NASDAQ names, or wants RSI/MACD/moving-average or valuation analysis on a non-Israeli symbol. Provides indicator computation (RSI, MACD, Bollinger Bands, EMA 20/50/200, CCI), fundamental ratios, and a structured buy/hold/sell rationale. Do NOT use for Israeli TASE stocks (use tase-stock-analysis) or cryptocurrency.

Screen the S&P 500 and NASDAQ-100 universe by technical and fundamental criteria to surface candidate stocks. Use when the user wants to filter or rank US stocks — 'S&P 500 names with RSI below 30', 'NASDAQ stocks above their 200-day average', oversold/overbought scans, or sector-relative screens. Returns a ranked table with the matched criteria per symbol. Do NOT use for single-symbol deep analysis (use global-stock-analysis) or Israeli TASE screening.