By jagreehal
Opinionated TypeScript patterns for AI-assisted development. Enforces fn(args, deps), Result types, Zod validation, and production-grade architecture.
Define the collaboration style between Claude Code and the user for the current session
Review 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
Automates real browsers from the command line using a ref-based snapshot-then-interact workflow. Use when you need to drive a live browser, navigating pages, filling and submitting forms, clicking buttons, taking screenshots, scraping or extracting data, testing or logging into web apps, mocking network requests, or verifying responsive layouts. Triggers include "open a website", "fill out this form", "take a screenshot", "scrape this page", "test this web app", "log in to a site", "automate browser actions", or any task requiring programmatic web interaction via the agent-browser CLI.
Detects question-shaped input and forces a literal answer before any action. Use when the user's message contains "?" or trigger patterns like "why did you…?", "will that work?", "have you considered…?", "shouldn't we…?", "doesn't that…?", "is that correct?", especially when the question challenges a decision, requests an assessment, or could be misread as criticism.
Builds production-ready HTTP APIs with thin handlers, consistent error envelopes, health/readiness checks, CORS, idempotency, rate limiting, and graceful shutdown. Use when designing or implementing HTTP endpoints, writing orpc route factories, defining Zod request/response schemas, mapping domain errors to status codes, or adding operational concerns (health checks, X-Request-ID, Retry-After) to a TypeScript API.
Guides completion of development work by verifying tests, presenting structured merge/PR/keep/discard options, and executing the chosen cleanup. Use when implementation is complete and tests pass, when wrapping up a feature branch, or when deciding how to land or discard work.
Traces a code execution path with file:line references and an execution diagram before any change is made, forcing real understanding of fn(args, deps) flows, Result propagation, and workflow composition. Use before fixing a bug, implementing a feature, refactoring, or starting a TDD cycle, whenever you are about to change non-trivial code.
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Opinionated TypeScript patterns for AI-assisted development. Skills, commands, and hooks for Claude Code that enforce production-grade architecture.
# Add the marketplace
/plugin marketplace add jagreehal/jagreehal-claude-skills
# List available plugins
/plugin list jagreehal-marketplace
# Install only what you need
/plugin install <plugin-name>@jagreehal-marketplace
This marketplace contains 10 plugins. Install only what you need.
| Plugin | Skills | Description |
|---|---|---|
typescript-patterns | 9 | Core TS architecture: fn(args, deps), Result types, Zod, observability |
testing-tdd | 4 | TDD workflow: red-green-refactor, test pyramid, performance testing |
communication-behavior | 6 | Claude style: critical peer, concise output, research-first |
workflow-productivity | 10 | Session management, verification, git worktrees, parallel agents |
frontend-react | 5 | React patterns, testable+storybookable components, Storybook, UI design, browser automation |
documentation-architecture | 7 | Documentation standards, ADRs, data visualization, policy explanations |
debugging-analysis | 2 | Evidence-based debugging, code flow analysis |
skill-authoring | 1 | Guide for creating custom skills |
code-review | - | Auto code review on file modifications (hooks) |
track-and-improve | - | 5 whys root cause analysis for mistakes |
# TypeScript developer wanting core patterns + TDD
/plugin install typescript-patterns@jagreehal-marketplace
/plugin install testing-tdd@jagreehal-marketplace
# Frontend developer
/plugin install frontend-react@jagreehal-marketplace
/plugin install typescript-patterns@jagreehal-marketplace
# Want Claude to be more concise and research-driven
/plugin install communication-behavior@jagreehal-marketplace
# Full productivity workflow
/plugin install workflow-productivity@jagreehal-marketplace
Add to your .claude/settings.local.json:
{
"extraKnownMarketplaces": {
"jagreehal-marketplace": {
"source": {
"source": "github",
"repo": "jagreehal/jagreehal-claude-skills"
}
}
},
"enabledPlugins": {
"typescript-patterns@jagreehal-marketplace": true,
"testing-tdd@jagreehal-marketplace": true
}
}
Core TypeScript architecture patterns for production-grade code.
| Skill | Description |
|---|---|
fn-args-deps | Core pattern: fn(args, deps) for testable functions |
validation-boundary | Zod schemas at boundaries, trust inside |
result-types | Never throw - use Result<T, E> with workflows |
strict-typescript | Beyond strict: true - advanced types, ESLint enforcement |
config-management | Validate config at startup, secrets in memory only |
api-design | Production-ready HTTP APIs with clean handlers, error envelopes |
pattern-enforcement | ESLint rules that fail the build |
resilience | Retry/timeout at workflow level, not in functions |
observability | trace() wrapper, Pino logging, OpenTelemetry |
TDD workflow and comprehensive testing strategies.
| Skill | Description |
|---|---|
tdd-workflow | Red-green-refactor with Result type testing |
testing-strategy | Test pyramid with vitest-mock-extended |
writing-tests | Test naming, assertions, edge case checklists (BugMagnet-based) |
performance-testing | Load testing, chaos engineering, trace correlation |
How Claude communicates and behaves during sessions.
| Skill | Description |
|---|---|
critical-peer | Professional skepticism, concise output, research first |
concise-output | Maximum information density, eliminate filler phrases |
confidence-levels | Express confidence as %, explain gaps, show evidence |
research-first | Validate solutions before presenting, never ask lazy questions |
literal-answers | Treat questions as literal questions, answer honestly |
answer-questions-directly | Answer questions literally, don't interpret as instructions |
Session management, task tracking, and development workflow.
npx claudepluginhub jagreehal/jagreehal-claude-skills --plugin skill-authoringCapture mistakes and improvement opportunities with 5 whys root cause analysis. Learn from patterns to prevent future issues.
Ralph Wiggum-style AI coding loop with specs, skills, and observability. Run Claude Code autonomously until all specs pass.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Verification-first engineering toolkit for Claude Code. 15 skills across a 5-phase spine (Investigate → Design → Implement → Verify → Ship), 8 specialist agents, an interactive setup wizard. Every skill has rationalizations + evidence requirements. Built for senior ICs and tech leads.
Unified Claude Code plugin merging superpowers workflows (TDD, debugging, planning) with everything-claude-code productivity (agents, learning, hooks, rules)
Development practices: TDD workflow with red-green-refactor
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
Test-Driven Development (TDD) principles and red-green-refactor cycle enforcement.