By jagreehal
Opinionated TypeScript patterns for AI-assisted development. Enforces fn(args, deps), Result types, Zod validation, and production-grade architecture.
npx claudepluginhub jagreehal/jagreehal-claude-skills --plugin jagreehal-claude-skillsReview the entire codebase against all jag-reehal-real-claude-skills patterns using the pattern-checker agent. Handles large codebases by chunking files.
Initialize a TypeScript project with jagreehal-claude-skills patterns (tsconfig, eslint, dependencies)
Analyze PR feedback patterns and suggest config updates to catch issues locally
Scaffold a new function following the fn(args, deps) pattern with Result types
Capture mistake or improvement opportunity with 5 whys root cause analysis
Verify that code follows jagreehal-claude-skills patterns (fn-args-deps, validation, result types, etc.)
Define the collaboration style between Claude Code and the user for the current session
Browser automation for web testing, form filling, screenshots, and data extraction. Ref-based workflow with best practices for reliable automation.
Ensures questions are answered literally before taking action. Triggers on user input containing '?' or patterns like 'why did you...?', 'will that work?', 'have you considered...?'. Use when user asks about your decisions, challenges an approach, or requests assessment. Prevents interpreting questions as implicit instructions or criticism.
Build production-ready HTTP APIs with clean handlers, consistent error envelopes, health checks, CORS, and operational excellence.
Use when implementation is complete and tests pass. Guides completion by presenting structured options for merge, PR, or cleanup.
Trace code execution path before implementing fixes. Forces understanding of fn(args, deps) flows, Result types, and workflow composition. Prevents guessing by requiring file:line references and execution diagrams.
Use when receiving code review feedback, before implementing suggestions. Requires technical verification, not performative agreement or blind implementation.
Enforce extreme brevity and high signal-to-noise ratio. Every word must justify its existence. Eliminates verbose explanations, filler phrases, and unnecessary elaboration.
Force honest confidence assessment. Express confidence as percentage, explain gaps, validate assumptions before presenting conclusions.
Validate config at startup, secrets in memory only. Never read config during requests, never store secrets in env vars. Use node-env-resolver for multi-source config.
Creates well-formed tasks following a template that engineers can implement. Use when creating tasks, defining work items, creating tasks from PRD, breaking down features, or converting requirements into actionable tasks.
Professional skepticism with pattern enforcement. Verify before agreeing, challenge violations, propose instead of asking. Concise output, research before asking, answer questions literally.
Visualization is communication. Chart selection, encoding hierarchy, accessibility, rendering performance. Use established algorithms - these problems are solved.
Evidence-based debugging with Iron Law discipline. Instrument before guessing, trace before theorizing. Use when encountering any bug, test failure, or unexpected behavior - before proposing fixes.
Use before any creative work - creating features, building components, adding functionality. Explores user intent, requirements, and design before implementation. One question at a time, multiple choice preferred.
Software design beyond syntax. Fail-fast over fallbacks, explicit over implicit, composition over inheritance. Integrates with fn(args, deps) and Result type patterns. Includes 8-dimension design analysis.
User-centered documentation quality framework. Eight quality dimensions, document type requirements, and review checklist. Documentation exists to serve readers, not demonstrate knowledge.
Enforce the fn(args, deps) pattern: functions over classes with explicit dependency injection
Use when starting feature work that needs isolation from current workspace. Creates isolated git worktrees with directory selection, safety verification, and baseline testing.
Use when you have a design or requirements for a multi-step task, before writing code. Creates bite-sized TDD task plans with exact file paths, complete code, and verification steps.
Three explicit investigation modes: LEARNING (build understanding), INVESTIGATION (diagnose problems), SOLVING (implement fixes). Prefix messages with mode, ask before transitioning.
Treat questions as literal questions. Answer them honestly without interpreting as hidden instructions. STOP after answering - don't immediately act on assumed implications.
Make functions observable with trace() wrapper, structured logging (Pino), and OpenTelemetry. Observability is orthogonal to business logic.
Use when facing 2+ independent tasks that can be worked on without shared state. Dispatch one agent per problem domain for concurrent investigation.
Enforce architectural patterns with ESLint rules. Block infra imports, enforce object params, prevent server/client leaks.
Load testing, chaos engineering, and performance validation. Prove your system works under pressure with k6, trace correlation, and progressive load profiles.
Modern React architecture patterns and web interface guidelines. Container/View split, framework adapters, React Query, dependency injection, Storybook-first development, accessibility, interactions, animations, performance. User experience over developer convenience.
Research-driven investigation. Validate solutions and explore documentation before presenting. Never ask questions you can answer yourself through research.
Add retry, timeout, and circuit breaker patterns at the workflow level. Business functions stay clean.
Never throw for expected failures. Use Result<T, E> types with explicit error handling and workflow composition.
Persistent task workflow with state machine. Every message MUST announce state. Uses .claude/ files for multi-session continuity. Never use TodoWrite. Never auto-advance tasks.
Use when creating, editing, or reviewing skills. Covers discovery optimization, structure patterns, testing approaches, and format decisions.
Evaluate and improve technical articles using the SPINE framework. Use when writing blog posts, technical documentation, tutorials, or reviewing draft articles for quality.
Create Storybook "user journey" storyboards for React apps (page/screen stories, MSW API mocking, interaction play functions, and optional Storybook test-runner setup). Use when the user wants Storybook demos of flows (not just atomic components), e.g., signup/login/checkout, with mocked APIs and scripted interactions.
Enforce patterns with TypeScript beyond strict:true. Include noUncheckedIndexedAccess, erasableSyntaxOnly, ts-reset, and type-fest. Advanced type patterns and ESLint enforcement.
Writing assistance with voice preservation. Structure content, ask clarifying questions, identify gaps. Small edits execute; large changes ask first.
Design systems for change. Trade-off analysis, ADR documentation, pattern selection. Architecture decisions must have documented rationale.
Strict TDD state machine with Result types. 7-state workflow (PLANNING, RED, GREEN, REFACTOR, VERIFY, BLOCKED, VIOLATION). Every message MUST announce state. Integrates with fn(args, deps), vitest-mock-extended, and typed error handling.
Test pyramid approach with unit, integration, and load tests. DI enables testability. Use vitest-mock-extended for typed mocks.
Design system principles for distinctive, implementation-ready interfaces. Context before design, show don't tell, every state documented.
Validate at the boundary with Zod schemas and branded types. Business functions trust validated input.
Use when about to claim work is complete, fixed, or passing. Requires running verification commands and confirming output before making any success claims. Evidence before assertions, always.
Principles for writing effective, maintainable tests. Covers naming conventions, assertion best practices, and comprehensive edge case checklists. Based on BugMagnet by Gojko Adzic.
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.
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
Complete developer toolkit for Claude Code
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, rules, and legacy command shims evolved over 10+ months of intensive daily use
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams