JSONbored

Generate .cursorrules files for AI-native development with project-specific patterns, coding standards, and intelligent context awareness

Advanced debugging assistant with root cause analysis, step-by-step troubleshooting, and automated fix suggestions

User-created Claude Code custom slash command recipe for drafting project documentation from source files, existing docs, and repository conventions.

Intelligent code explanation with visual diagrams, step-by-step breakdowns, and interactive examples

Slash command for auditing a remote MCP server authorization setup, including protected resource metadata, authorization server discovery, OAuth resource indicators, token audience validation, scopes, and token passthrough risk.

Advanced performance optimization with bottleneck analysis, memory profiling, and automated improvements

Intelligent code refactoring command that analyzes code structure and applies best practices for improved maintainability and performance

Custom slash command for behavior-preserving, scoped refactors of one file, function, or selection — stays inside a narrow ownership boundary for a reviewable, PR-sized change instead of a repo-wide pass

Comprehensive code review with security analysis, performance optimization, and best practices validation

Comprehensive security audit with vulnerability detection, threat analysis, and automated remediation recommendations

Deploy 100 specialized sub-agents for comprehensive enterprise-grade security, performance, and optimization audit of production codebase

User-created Claude Code custom slash command recipe for planning deeper tests around a file or function, including edge cases, property-style invariants, regression cases, and mutation-score gaps where the project already supports those tools.

Production codebase auditor specialized in Zod schema validation coverage, security vulnerability detection, and dead code elimination

Automated accessibility testing and compliance checking for web applications following WCAG 2.1 and WCAG 2.2 guidelines. This hook automatically runs accessibility scans on HTML files after they are written or edited, using axe-core for comprehensive WCAG compliance testing.

WCAG-compliant accessible statusline with screen reader announcements, high-contrast colors, semantic labels, keyboard hints, and reduced motion support.

Build repeatable eval suites that catch quality regressions in AI agent behavior before merge or release.

High-leverage collection for operators building AI-driven products: secure code review, release governance, automation orchestration, skill authoring, growth execution, and Unraid/n8n operational readiness.

An agent persona for authoring Claude Agent Skills: structured SKILL.md files with name and description frontmatter, progressively disclosed instructions, and bundled scripts the model loads on demand.

Install and manage Claude Code Agent Skills - specialized knowledge packages that extend Claude's capabilities with domain expertise and progressive disclosure

Instrument AI agent systems with high-signal telemetry and runbook-driven incident response for reliability and safety.

Expert business-validation capability pack for testing AI product ideas, market demand, pricing readiness, and launch feasibility.

AI-powered code review specialist focusing on security vulnerabilities, OWASP Top 10, static analysis, secrets detection, and automated security best practices enforcement

Multi-provider AI performance dashboard with context occupancy tracking, truncation warnings, TTFT latency, tokens/min rate, and model comparison metrics.

A CLAUDE.md rule set that turns Claude into a prompt-engineering reviewer for coding work — enforcing explicit requirements, task decomposition, example-driven prompts, and context management.

Plan SEO-forward content clusters that align search intent, topical coverage, internal links, and conversion pathways for AI tooling niches.

Official remote MCP server for querying and creating Amplitude analytics, dashboards, experiments, cohorts, session replay insights, and product data from Claude and other MCP clients.

Specialized agent for designing, building, and optimizing RESTful APIs and GraphQL services with modern best practices

Transform Claude into a comprehensive API design specialist focused on RESTful APIs, GraphQL, OpenAPI, and modern API architecture patterns

A starter kit for designing, documenting, and testing REST APIs with Claude: bundles an API-builder agent with the docs, generate-tests, and debug commands.

PostToolUse hook that extracts JSDoc and pydoc comments from modified API endpoint files and generates OpenAPI 3.1.0-compatible YAML documentation on every save.

A CLAUDE.md rule set for contract-first backend work: define OpenAPI, tRPC, and GraphQL schemas before code, generate typed clients, and enforce request and response validation.

A Claude Code statusline that reads the session JSON on stdin and splits total_duration_ms into API processing time versus network/waiting time (total minus API).

Transcribe audio files (MP3, WAV, M4A, etc.) using OpenAI Whisper AI and ffmpeg to produce structured, timestamped transcripts with automatic summarization and action item extraction. Supports multilingual transcription, speaker diarization, and meeting minutes generation.

Automatically formats code files after Claude writes or edits them using industry-standard formatters including Prettier 3.6.2+ (JavaScript/TypeScript/Web), Black or Ruff (Python), gofmt (Go), and rustfmt (Rust).

Automatically creates timestamped backups of files before modification to prevent data loss. This hook runs before file editing operations (Edit, Write, Multiedit) and creates versioned backups in a centralized .backups directory with ISO 8601-compliant timestamps including nanoseconds for collision prevention.

A Claude agent persona for building multi-agent apps with Microsoft AutoGen v0.4: the asynchronous agent runtime, message-passing between agents, the AgentChat API, cross-language (Python and .NET) support, and tool use.

Orchestrate multi-agent workflows using Microsoft AutoGen v0.4 with role-based task delegation, conversation patterns, and collaborative problem solving

Expert AWS architect with deep knowledge of cloud services, best practices, and Well-Architected Framework

Validates AWS CloudFormation templates for syntax errors and best practices using cfn-lint v1.40.4+ and AWS CLI v2.27.54+.

Complete AWS infrastructure management toolkit combining cloud architecture expertise, CloudFormation validation, and AWS services integration. Perfect for teams building and maintaining cloud-native applications on AWS.

Expert backend architect specializing in scalable system design, microservices, API development, and infrastructure planning

Full-featured backend development environment combining architecture planning, database design, and cloud services integration. Perfect for building scalable server-side applications.

Ship smart contracts on Base with secure deployment, verification, environment management, and production-readiness checklists.

Biome linting rules configuration for code quality validation. Strict enforcement, custom overrides, VCS integration, and automated fixes for TypeScript.

Claude 5-hour conversation block tracker with visual countdown, expiration warnings, and color-coded indicators to prevent unexpected session terminations.

Use the built-in /init command to generate a project CLAUDE.md from your codebase, then refine it by hand. Covers /memory, file locations, @path imports, and .claude/rules/.

Build robust browser automation workflows for AI agents with deterministic selectors, retries, and safe action boundaries.

Master MCP server development from scratch. Create custom Claude Desktop integrations with TypeScript/Python in 60 minutes using production-ready patterns.

Build JavaScript and TypeScript apps with Bun, an all-in-one toolchain that replaces Node.js, npm, a bundler, and a test runner with one fast binary that executes TypeScript directly.

Real-time burn rate monitor showing cost per minute, tokens per minute, and projected daily spend to prevent budget overruns during Claude Code sessions.

A Claude Code statusline that reads prompt-cache token metrics from session JSON and renders a color-coded hit-rate bar with an estimated token-savings readout.

Soothing Catppuccin Mocha theme statusline with 26 pastel colors, Powerline separators, and modular segments for Git, model info, and token tracking.

Build autonomous agents with the Claude Agent SDK and Claude Code subagents: the query loop, built-in tools, subagent delegation, and permission controls.

Docker statusline configuration for Claude Code CLI. Features real-time health monitoring, color-coded indicators, and container tracking. Production-ready.

How to deploy Claude Code in a security- and compliance-sensitive financial-services environment, using its documented data-handling, ZDR, network, IAM, and sandboxing controls.

Connect existing MCP servers to Claude Code with claude mcp add: stdio, HTTP, and SSE transports, local/project/user scopes, .mcp.json, and /mcp OAuth.

A practical Claude Code guide for using output styles, keeping software engineering behavior intact, choosing the right settings scope, and avoiding durable-instruction drift.

Source-backed guide for scoping MCP servers, tools, permissions, hooks, and memory when building Claude Code subagents for focused review, research, and implementation workflows.

Capability comparison of Claude Code, Amazon Q Developer (formerly CodeWhisperer), and Google Gemini Code Assist: form factor, agentic vs completion, IDE support, cloud ties, and free tiers.

Capability comparison of Claude Code, Cursor, and Windsurf (formerly Codeium): form factor, where each runs, agentic vs autocomplete, MCP extensibility, and free tiers, grounded in each tool's official docs.

Capability comparison of Claude Code, GitHub Copilot, and ChatGPT (Codex) for Python development. Form factor, where each runs, agentic vs inline, IDE integration, MCP, and free tiers, grounded in each tool's official docs.

Complete Claude Code WSL2 installation tutorial in 30 minutes. Configure Node.js, resolve PATH conflicts, and optimize Windows development performance.

Configure MCP servers in the Claude Desktop app by editing claude_desktop_config.json. Grounded walkthrough covering config file locations, the mcpServers JSON structure, the filesystem server, and how to verify and troubleshoot the connection.

How to use Claude's extended thinking: the API `thinking` config with budget_tokens, when to spend more reasoning, and the think/ultrathink prompting convention in Claude Code.

An agent pattern for routing rapid-iteration work to Claude Haiku 4.5 — more than twice Sonnet's speed at one-third the cost ($1/$5 per million tokens) — while keeping about 90% of Sonnet 4.5's agentic-coding quality.

MCP Skills integration specialist for remote server configuration, tool permissions, multi-MCP orchestration, and Claude Desktop ecosystem workflows.

A Claude Code subagent that helps you pick the right Anthropic Claude model in GitHub Copilot's model picker and decide when to switch to Claude Code instead.

Automate business and engineering processes with Claude Code: headless `claude -p` runs, GitHub Actions, scheduled routines, and in-session loops, with permission and output-format guidance.

CLAUDE.md specialist for creating, maintaining, and optimizing project-specific AI instructions that survive context compaction and guide development.

Turn CSV, JSON, or Excel data into publication-ready charts with Python: load it with pandas and render bar, line, scatter, and statistical plots in matplotlib (with seaborn styling), then export high-DPI PNG or SVG.

A Stop hook that syncs your changed files to cloud storage when a Claude Code session ends, using rclone to push to S3, Google Cloud Storage, or any of its 70+ supported backends.

An agent persona for designing multi-cloud infrastructure across AWS, GCP, and Azure using their Well-Architected frameworks: cost optimization, reliability (high availability and disaster recovery), security, and operational excellence.

Run AI inference and serverless functions on Cloudflare Workers AI: call hosted models like Llama, Whisper, and Stable Diffusion through the Workers AI binding, deploy with wrangler, and use D1/R2/KV storage plus the free daily Neuron allocation.

Expert Cloudflare capability skill for designing workers that combine D1, KV, and R2 with clear consistency, caching, and security boundaries.

A Claude Code hook that flags files exceeding complexity thresholds after you edit them — estimating cyclomatic complexity, line and function counts, and nesting depth (via ESLint's complexity rule and Radon).

A collection that bundles three Claude Code resources for code review: a code-reviewer sub-agent plus the generate-tests and explain commands.

Expert code-review capability pack for deterministic PR audits, risk-ranked findings, and low-noise fix planning without SaaS lock-in.

Comprehensive code review rules for thorough analysis and constructive feedback

Expert code reviewer that provides thorough, constructive feedback on code quality, security, performance, and best practices

A PostToolUse hook that runs the matching test runner for a changed file's language — Jest or Vitest for JS/TS, pytest for Python, go test, or Maven/Gradle for Java — scoped to the edited file.

A Claude Code agent prompt for behavior-preserving codebase migrations and refactoring. It plans framework upgrades (React, Next.js, TypeScript, ESLint), applies named refactoring patterns, modernizes legacy JavaScript, and works incrementally on a git branch with test validation between steps.

Expert automation-orchestration capability pack for designing safe, low-noise recurring Codex workflows with clear runbooks.

Expert Codex plugin capability pack for safe plugin scaffolding, manifest quality, MCP integration, and maintainable distribution.

A practical onboarding guide for developers moving to Claude Code as a coding tool. Install it, run your first session, and map everyday coding tasks to Claude Code commands and prompt recipes.

Use the built-in /hooks menu to inspect Claude Code hooks and configure them in settings.json so shell commands run deterministically at lifecycle events like PreToolUse, PostToolUse, and Stop.

Add Model Context Protocol servers to Claude Code with the claude mcp add CLI and the /mcp slash command, covering transports, scopes, and OAuth for remote servers.

Streamlined workflow for content creators and marketers. Manage projects across multiple platforms, design graphics, and automate content distribution with integrated tools.

Context window optimization specialist managing 1M+ token conversations, preventing truncation with smart summarization and session management strategies.

Create and manage specialized Claude Code subagents using the interactive /agents command or Markdown definition files in .claude/agents/, with scoped tools, model selection, and isolated context.

Detects unused CSS selectors when stylesheets are modified to keep CSS lean using PurgeCSS, PostCSS, and content analysis. This hook runs on CSS/SCSS file write/edit operations and analyzes stylesheets to identify unused selectors, generate optimized output, and report before/after size metrics.

Clean, filter, join, pivot, and export CSV/XLSX data reliably with reproducible steps. Transform messy spreadsheets into production-ready datasets with pandas. Handle encoding issues, data type conversion, missing values, duplicates, and complex merges.

Configure and optimize Cursor and Windsurf AI code editors for maximum productivity. Set up agent mode, composer features, keybindings, and AI-powered refactoring workflows. Customize with .cursorrules and .windsurfrules for project-specific guidance.

Claude Code daily usage quota tracker showing percentage of daily limit consumed with visual progress bar, time remaining, and budget pacing indicators.

A starter kit for database and data-engineering work with Claude: bundles a database-specialist agent and database-expert rules with AWS and Airtable MCP servers and optimize/debug commands.

Modern data pipeline specialist focused on real-time streaming, ETL/ELT orchestration, data quality validation, and scalable data infrastructure with Apache Airflow, dbt, and cloud-native tools

A Stop hook that terminates lingering database connections when a Claude Code session ends — via PostgreSQL pg_terminate_backend, MySQL KILL, Redis CLIENT KILL, and MongoDB connection cleanup.

Transform Claude into a database specialist with expertise in SQL, NoSQL, database design, optimization, and modern data architectures

PostToolUse hook that detects writes to migration, schema, and SQL files then runs framework-specific status checks — runs knex migrate:status for Node.js projects and python manage.py showmigrations for Django projects.

A PostToolUse hook that reminds you to enable native query logging for PostgreSQL, Prisma, Sequelize, and TypeORM, and flags possible N+1 patterns when you edit SQL or data-access files.

Expert database architect and optimizer specializing in SQL, NoSQL, performance tuning, and data modeling

Official dbt Labs MCP server that gives AI agents context from dbt Core, dbt Fusion, dbt Platform, project metadata, SQL tools, lineage, Admin API, and dbt documentation search.

A Claude Code SessionEnd hook that scans a project for dead code and writes a report to .claude/reports. It runs available tools per language: ESLint and Knip for JS/TS, autoflake or pylint for Python, Knip for unused npm dependencies, ripgrep for unreferenced src files, and jq to flag zero-coverage files.

Complete debugging toolkit for identifying, analyzing, and resolving complex software issues. Combines AI-assisted debugging with powerful diagnostic commands.

Advanced debugging agent that helps identify, analyze, and resolve software bugs with systematic troubleshooting methodologies

A Stop hook that runs npm audit, pip-audit, safety, or bundler-audit automatically at the end of every Claude Code session, detecting CVEs and outdated packages across Node.js, Python, and Ruby projects.

Automatically checks for outdated dependencies and suggests updates with security analysis. This PostToolUse hook triggers when dependency manifest files (package.json, requirements.txt, Gemfile, go.mod, Cargo.toml, pyproject.toml) are modified, providing real-time dependency health monitoring.

A Claude Code DevOps engineer persona grounded in GitHub Actions, Terraform, Docker, and Kubernetes. It writes and reviews CI/CD workflows, IaC, and deployment manifests using real tooling and documented commands.

Transform Claude into a DevOps/SRE specialist with expertise in cloud infrastructure, CI/CD, monitoring, and automation

Sends development activity updates to Discord channel for team collaboration. This Notification hook automatically sends rich embed messages to Discord webhooks when Claude Code activities occur, providing real-time team visibility into development workflows.

Automatically generates or updates project documentation when session ends.

Create production-grade Docker Compose stacks with healthchecks, secrets handling, network isolation, and safe rollout patterns.

A PostToolUse hook that watches for edits to Docker-related files (Dockerfile, docker-compose, .dockerfile, .dockerignore).

Comprehensive Docker image vulnerability scanning with layer analysis, base image recommendations, and security best practices enforcement. This PostToolUse hook automatically scans Docker images for vulnerabilities when Dockerfiles are modified, providing real-time security validation during development.

Manage Docker containers, images, and services directly through Claude with comprehensive Docker API integration

Automated documentation coverage analysis with missing docstring detection, API documentation validation, and completeness scoring. This PostToolUse hook automatically checks documentation coverage when code files are modified, providing real-time documentation quality validation during development.

Automatically generates and updates project documentation from code comments, README files, and API definitions. This PostToolUse hook provides real-time documentation generation when code files are modified, supporting multiple programming languages and documentation formats.

Fill templated DOCX with data to produce reports, invoices, and formatted documents. Generate professional Word documents programmatically with python-docx or use Jinja2 templates with docxtpl for dynamic content insertion. Support tables, images, headers, footers, and custom styling.

Industry-specific AI agents for healthcare, legal, and financial domains with specialized knowledge, compliance automation, and regulatory requirements

Cleans up temporary files, caches, and resources when Claude session ends. This Stop hook provides comprehensive environment cleanup for development projects, automatically removing temporary files, build artifacts, cache directories, and system-specific files across multiple platforms.

Validates environment variables, checks for required vars, and ensures proper configuration across environments.

Tracks error patterns and alerts when error rates spike. This Notification hook provides comprehensive error rate monitoring across log files, Docker containers, and application logs, automatically detecting error patterns and alerting when error rates exceed configurable thresholds.

Expert EVM capability skill for secure contract architecture across Ethereum and Base, including Foundry testing and operational controls.

Build and harden Ethereum smart contracts with Foundry, invariant testing, and battle-tested OpenZeppelin security patterns.

An agent that decides how much reasoning depth a task needs and prompts Claude accordingly — escalating from think to think hard to ultrathink as problem complexity rises.

Build high-performance async REST APIs with FastAPI, Python's fastest-growing web framework. Automatic OpenAPI/Swagger documentation, type-safe validation with Pydantic, native async/await support, and dependency injection for clean architecture.

Alerts when files exceed size thresholds that could impact performance. This PostToolUse hook provides comprehensive file size monitoring when files are created or modified, automatically detecting files that exceed recommended size thresholds for different file types and providing optimization suggestions.

Analyzes and reports final bundle sizes when the development session ends.

Official Firecrawl MCP server for scraping, crawling, mapping, searching, and extracting web content through Claude Code, Claude Desktop, Cursor, VS Code, Windsurf, and other MCP clients.

A Claude Code statusline script (bash) that reads cost.total_duration_ms from the statusline JSON on stdin via jq, converts it to elapsed minutes, and renders a 20-character progress bar, a percent-used figure, and a countdown against a 300-minute (5-hour) ceiling, with green/yellow/red ANSI color coding at the 50%.

Set Claude Code environment variables correctly and debug auth, model, and config issues using only documented variables and the /doctor diagnostics.

Install Claude Code correctly in 15-25 minutes. Fix npm permission errors, configure PATH, and resolve 'command not found' issues with proven solutions.

Fix Claude Code high CPU and memory usage, hangs, slow responses, and auto-compact thrashing using /context, /compact, /clear, /doctor, and documented context-management techniques.

Diagnose and fix Claude Code 429 errors, session and weekly usage limits, and high token consumption using built-in commands and documented settings.

Resolve Claude Desktop MCP server connection errors fast. Step-by-step fixes for error -32000, disconnections, and configuration issues with proven solutions.

Expert frontend developer specializing in modern JavaScript frameworks, UI/UX implementation, and performance optimization

Full-stack AI development specialist bridging frontend, backend, and AI/ML with AI-assisted coding workflows, intelligent code generation, and end-to-end type safety

A user-created custom slash command for Claude Code that turns a file or function into a test suite. You create .claude/commands/generate-tests.md and invoke it with /generate-tests; it is a prompt recipe, not a built-in command, and uses no CLI flags.

Automatically commits all changes with a summary when Claude Code session ends.

Prevents direct edits to protected branches like main or master, enforcing PR-based workflows.

Comprehensive pre-commit hook that validates code quality, runs tests, and enforces standards.

Intelligently analyzes changes and creates well-formatted git commits with conventional commit messages

Git-focused statusline showing branch, dirty status, ahead/behind indicators, and stash count alongside Claude session info

Expert release-changelog capability pack for git-cliff with conventional commits, deterministic release notes, and low-maintenance versioning.

Build intelligent CI/CD pipelines with GitHub Actions, AI-assisted workflow generation, automated testing, and deployment orchestration.

Expert GitHub Actions capability skill for secure workflow architecture, token minimization, supply-chain controls, and CI reliability.

Validates GitHub Actions workflow files for syntax errors and best practices.

Expert skill for reviewing GitHub Artifact Attestations, release artifact digests, workflow provenance, OIDC boundaries, and public release evidence before an AI agent recommends or publishes build outputs.

Gittensory MCP connects Claude and other MCP clients to private, metadata-only Gittensor contribution mining workflows for branch preflight, scoreability estimates, maintainer-fit checks, and public-safe PR packets.