.claude configuration
A comprehensive configuration framework with skills, agents, commands, and marketplace integrations that transform Claude Code into an autonomous engineering platform.
Snapshot as of 2026-11-10: selected local revisions, including pins, not latest upstream. Repo totals overlap; don't sum them.
Interactive Demo
Watch how skills, agents, and commands work together in the terminal.
Skills Library
Domain-specific knowledge loaded on demand. From debugging methodologies to full-stack design systems.
LLM app development with RAG, prompt engineering, vector databases, and AI agents
Systematic 4-phase debugging methodology for complex, intermittent, or mysterious issues. Use when investigating bugs, race conditions, or unexplained failures.
OAuth 2.0, JWT, SSO, MFA, NextAuth/Clerk/Supabase Auth implementation patterns
Stripe, RevenueCat, subscription billing, webhooks, PCI compliance, and tax. Use when integrating payments or subscriptions, handling payment webhooks, or reviewing billing and PCI scope.
Information security expertise for cybersecurity frameworks (NIST, ISO 27001), security architecture, incident response, vulnerability management, identity management, and cloud security. Use when designing security programs, responding to incidents, or assessing vulnerabilities.
REST and GraphQL API design best practices including OpenAPI specs. Use when designing APIs, documenting endpoints, or reviewing API architecture.
OpenTelemetry, structured logging, distributed tracing, alerting, and dashboards. Use when instrumenting services, designing logs/traces/metrics, defining SLOs and alerts, or debugging production behavior from telemetry.
Specialized Agents
Autonomous sub-agents that handle complex tasks. Each tuned for specific domains with curated tool access.
Thorough 6-aspect code review covering correctness, security, performance, maintainability, verification, and documentation. Use for comprehensive PR reviews or code quality audits.
Systematic 4-phase debugging for complex and intermittent issues. Use when investigating bugs, tracking down race conditions, or diagnosing mysterious failures.
Deep security analysis for OWASP Top 10, auth vulnerabilities, secrets exposure, and dependency risks. Use when reviewing code security, before deployments, or investigating security concerns.
Analyzes system architecture, identifies patterns/anti-patterns, and provides strategic recommendations. Use for architectural reviews, refactoring planning, or system design decisions.
Identifies performance bottlenecks and optimization opportunities. Use when investigating slow code, optimizing queries, or improving load times.
Marketplace
Curated from 86 open-source repositories: unique normalized skill bodies. Snapshot as of 2026-11-10at selected local revisions, including pins, not latest upstream. Repo totals overlap; don't sum them. Discover, install, and extend your capabilities.
Automation Scripts
Setup, maintenance, and repo management automation that keeps the toolkit running smoothly.
Clone the repository and start using the full configuration framework.
Already have a ~/.claude from Claude Code? Use scripts/install-in-place.sh instead; it keeps your existing files. Marketplace repos are cloned locally with push disabled by the first daily background pull (or run _pull-all-repos.sh now).