george-setup

Install George's complete Claude Code setup: orchestration engine, hooks, MCP servers, and scripts

Use when setting up PostHog analytics, feature flags, experiments, or querying PostHog data. Triggers on PostHog, PostHog event, PostHog feature flag, PostHog experiment, A/B test PostHog, HogQL, PostHog funnel, PostHog dashboard, PostHog LLM cost, posthog.capture, isFeatureEnabled, PostHog MCP, PostHog survey, PostHog error tracking.

Use when setting up Clerk authentication, configuring auth middleware, protecting routes, or handling Clerk webhooks. Triggers on Clerk, Clerk auth, ClerkProvider, auth middleware, protected routes, Clerk webhook, Svix, sign-in, sign-up, Clerk token, getToken, Clerk secret key, publishable key, Clerk setup, CAPTCHA signup, Clerk Next.js, Clerk React, Clerk Expo, user.created event, session management, Clerk identity.

Use for any server-side API or data persistence work. Triggers on REST endpoints, GraphQL resolvers, DataLoader, Node.js, Express, Fastify, API design, pagination, filtering, sorting, databases, SQL, PostgreSQL, indexes, EXPLAIN ANALYZE, query optimization, Prisma, Drizzle, TypeORM, SQLAlchemy, ORM, N+1 queries, migrations, Alembic, schema design, data modeling, normalization, JWT, OAuth, authentication, authorization, rate limiting, Redis, caching, message queues, BullMQ, Kafka, RabbitMQ, webhooks, idempotency, signatures, microservices, multi-tenant, row-level security.

Use when automating Chrome browser interactions, taking screenshots, filling forms, or verifying UI visually. Triggers on browser automation, take screenshot, screenshot page, fill form, click button, navigate to URL, Chrome DevTools, use_browser, visual verification, desktop and mobile screenshot, OAuth flow in browser, email verification flow, extract page content, DOM inspection, multi-tab browsing, form submit, CSS selector, headless Chrome, browser profile, login flow, signup flow.

Use when working with Docker, Kubernetes, Terraform, CI/CD, cloud providers (AWS/GCP/Azure), serverless, observability, bash/shell scripts (getopts, strict mode, traps), systemd, or infrastructure tooling. Also covers Helm, GitHub Actions, GitLab CI, Lambda, Cloud Run, ECS, EKS, GKE, nginx, DNS, SSL, Prometheus, Grafana, OpenTelemetry, FinOps, GitOps, ArgoCD, service mesh, Istio, BATS testing, ShellCheck, cron, awk, sed, curl, parallel execution, signal handling, process management.

Run completion council to verify work quality. Use after major implementation tasks, before declaring work done. Triggers on: verify completion, completion council, is this done, review the work, council review, check if complete, verify work, are we done, sign off, final review, acceptance review, quality gate.

Consolidate and deduplicate MEMORY.md. Use when memory file is getting large, has duplicates, or needs cleanup. Triggers on: consolidate memory, clean memory, deduplicate memory, memory cleanup.

Launch or check the Claude Code monitoring dashboard. Use when: open dashboard, show dashboard, agent dashboard, monitoring, check agent activity, session stats, telemetry viewer.

Use when creating charts, plots, graphs, dashboards, Excel reports with openpyxl, infographics, generative art, statistical plots, animations, heatmaps, treemaps, sankey diagrams, choropleth maps, geographic maps, network graphs, D3.js custom visualizations, or accessible data visualizations (WCAG, colorblind-safe palettes, alt text for charts). Tools: matplotlib, plotly, seaborn, D3, Dash, p5.js, openpyxl, Pillow, Folium, NetworkX, bokeh.

Use when writing Convex schema, queries, mutations, actions, or workflows. Triggers on Convex schema, defineTable, Convex query, Convex mutation, Convex action, httpAction, searchIndex, Convex index, identity.subject, use node, ConvexError, Convex workflow, v.string, v.object, Convex auth, Convex function, reactive query, Convex pagination, schema.ts.

Use when working with Supabase database, running SQL, applying migrations, or deploying edge functions. Triggers on Supabase, Supabase migration, Supabase SQL, Supabase edge function, Supabase RLS, row-level security, Supabase branch, Supabase table, execute_sql, apply_migration, list_tables, Supabase MCP, Supabase database.

Use when deploying Convex, pushing schema, running Convex CLI commands, or managing dev/prod Convex environments. Triggers on npx convex dev, npx convex deploy, convex dev --once, convex deploy -y, push schema, Convex deploy, Convex CLI, convex run, convex import, convex export, convex dashboard, _generated gitignore, Convex prod, Convex dev deployment.

Use when deploying Modal workers, checking Modal logs, managing Modal secrets, or configuring GPU endpoints. Triggers on modal deploy, Modal worker, Modal app, Modal logs, Modal secret, modal run, Modal endpoint, keep_warm, cold start, Modal proxy token, wk- ws- token, 8-endpoint limit, Modal GPU, memory sizing, deploy_all.py, Modal Python worker.

Use when deploying to Vercel, managing Vercel deployments, or configuring Vercel environment variables. Triggers on deploy to Vercel, Vercel deploy, vercel --prod, Vercel preview, Vercel env, Vercel logs, Vercel build, Vercel deployment, vercel ls, custom domain Vercel, 504 timeout serverless, Vercel rollback, pull env, NEXT_PUBLIC, Vercel serverless function.

Master FPGA skill covering Vivado, SystemVerilog/Verilog/VHDL, RTL design, timing closure, CDC, AXI interfaces, FSMs, pipelines, memory interfaces, HLS, verification, and hardware optimization. Uses Context7 MCP for up-to-date library docs. Use when FPGA, Verilog, VHDL, HDL, RTL, synthesis, or hardware design mentioned.

Use when committing code, creating PRs, managing branches, or resolving git conflicts. Triggers on git commit, git push, git status, git diff, git stash, git revert, cherry-pick, merge conflict, pull request, PR, create PR, squash merge, conventional commit, branch, feature branch, gh pr, git log, rebase, upstream, origin, stage files, git add.

Use for content marketing, copywriting, social media, email campaigns, launch strategy, and growth. Triggers on blog post, social media post, email campaign, newsletter, drip campaign, Product Hunt, go-to-market, GTM, launch plan, marketing copy, ad copy, content calendar, SEO content, Twitter thread, LinkedIn post, landing page copy, pSEO, programmatic SEO, content strategy, brand voice, marketing funnel, lead magnet, paid ads, Facebook ads, Google ads, campaign, retargeting, subject line, welcome sequence, content repurposing, hook formula, headline, CTA, conversion copy, growth marketing, marketing psychology, persuasion.

Use when calling Gemini AI for image analysis, image generation, grounded web search, code execution, text-to-speech, or video analysis. Triggers on Gemini, gemini_analyze, gemini_image, analyze image, generate image, Gemini search, grounded search, gemini_code_execute, run Python in sandbox, Gemini TTS, text to speech, gemini_video, video analysis, Gemini MCP, gemini_embed, embeddings, CAPTCHA solve, image edit, Gemini chat.

Use when analyzing sources with NotebookLM, creating research notebooks, or generating audio overviews and study materials. Triggers on NotebookLM, create notebook, add sources to notebook, ask NotebookLM, notebook question, synthesize sources, audio overview, podcast summary, generate infographic, mind map, study guide, FAQ generation, briefing document, NotebookLM MCP, research notebook, source analysis, multi-source synthesis, notebook deliverable.

Use when reading, writing, searching, or organizing notes in an Obsidian vault. Triggers on Obsidian, Obsidian vault, read note, write note, update note, search vault, global search, list notes, manage tags, frontmatter, wikilinks, knowledge base, save to Obsidian, Obsidian MCP, search and replace in vault, delete note, note organization, vault maintenance, atomic notes, Zettelkasten.

Use for ML model training, inference serving (vLLM, TorchServe, ONNX), data pipelines, RAG/LLM systems, and MLOps. Covers classification, regression, neural networks, ETL, feature engineering, vector databases, model deployment, experiment tracking. PyTorch, scikit-learn, HuggingFace, MLflow, W&B, FAISS, pgvector, Chroma, LoRA, QLoRA, PEFT, DVC, Delta Lake, Spark, Feast, Evidently, data drift, A/B testing.

Use when building mobile apps with Expo, React Native, iOS (Swift/SwiftUI), or Android (Kotlin/Jetpack Compose). Triggers on mobile app, native app, React Native, Expo, Expo Router, EAS Build, NativeWind, SwiftUI, Swift, UIKit, Xcode, iOS, macOS, watchOS, visionOS, SwiftData, NavigationStack, Jetpack Compose, Kotlin, Coroutines, Flow, Room, Retrofit, Hilt, Material 3, Play Store, App Store, TestFlight, mobile CI/CD, OTA updates, native UI, Reanimated, native animations, mobile performance, DOM components, native data fetching.

Switch behavior mode. Usage: /mode guided | autonomous | readonly. Updates ~/.claude/behavior.json.

Use when checking Sentry errors, investigating production issues, or triaging error spikes. Triggers on Sentry, Sentry error, Sentry issue, check Sentry, production error, error spike, crash, Sentry Seer, search_issues, get_issue_details, analyze_issue, Sentry MCP, P0, triage, error rate, unresolved issues, Sentry project.

Use when integrating Stripe payments, subscriptions, checkout, webhooks, or billing. Triggers on Stripe, Stripe checkout, Stripe subscription, Stripe webhook, invoice.paid, customer.subscription.deleted, Stripe test card, 4242, Stripe Connect, Stripe Customer Portal, Stripe pricing table, trial period, webhook signature, idempotency key, Stripe SDK, use node Stripe.

Authenticate Playwright browser sessions against Clerk-based apps using the Backend API sign-in token pattern. Bypasses password, MFA, and CAPTCHA entirely.

Use when creating presentations, slide decks, posters, or document generation. Triggers on presentation, slides, slide deck, make slides, create a deck, poster, conference talk, thesis defense, keynote, seminar, PPTX, PowerPoint, LaTeX poster, Beamer, paper to web, template, OOXML, theme, color palette, speaker notes, storyboard, narrative arc, bento grid, layout pattern, 9:16, vertical slides, mobile presentation, WCAG slides, accessible presentation, data visualization for slides, chart for slides.

Trigger for ANY task involving Python code, Python tooling, or Python-ecosystem libraries — even when 'Python' isn't explicitly mentioned. If the query references any of these, use this skill: pyproject.toml, hatchling, setuptools, ruff, pyright, mypy, pytest, FastMCP, MCP server, asyncio, TaskGroup, Typer, Click, argparse, dataclass, Pydantic, pathlib, httpx, Polars, Pandas, NumPy, FastAPI, Django, Flask, SQLAlchemy, Alembic, uv, pip, venv, cProfile, py-spy, PDF/Excel/DOCX automation, .py files. Covers writing, debugging, configuring, and reviewing Python. Includes build config, linting config, type checking config, packaging, async concurrency, CLI apps, data scripts, web frameworks, ORM, profiling, and MCP server development. Do NOT use for: ML training/fine-tuning/RAG/vector DBs (use ml-data-engineering), REST/GraphQL API design (use backend-data), test strategy/methodology (use testing-quality), React/TypeScript/frontend (use web-frontend).

Use when starting a ralph-gsd autonomous execution loop to set up a recurring monitor that watches progress, restarts if stopped, and resolves deferred items autonomously every 2 hours.

Use when the user asks to start, run, or resume ralph-gsd (the autonomous milestone execution loop). Invokes the monitor skill then launches ralph-gsd in the background.

Use when researching topics, finding YouTube videos, analyzing sources with NotebookLM, or doing requirements gathering interviews. Triggers on research, find videos, YouTube search, analyze sources, NotebookLM, research pipeline, deep interview, interview me, requirements gathering, Socratic, yt-dlp, transcript, audio overview, infographic, mind map, study guide, FAQ, briefing doc, find and analyze, research for me, analyze these videos, competitive research.

Use for scientific research, academic writing, statistical analysis, grant proposals, peer review, IRB/ethics, causal inference (DAGitty, DAGs), and PRISMA/CONSORT methodology diagrams. Covers manuscripts, LaTeX, BibTeX, p-value, ANOVA, power analysis, effect size, NSF/NIH/DOE grants, systematic reviews, meta-analysis, thematic analysis, preregistration, OSF, FAIR data, propensity scores, instrumental variables, SEM/CFA, lavaan, lme4, qualitative research, science communication.

Use for security audits, vulnerability analysis, threat modeling, compliance, and incident response. Triggers on OWASP, XSS, SQL injection, CSRF, security audit, penetration testing, pen test, CVE, vulnerability, threat model, security review, SOC2, GDPR, PCI-DSS, HIPAA, compliance audit, CSP headers, HSTS, CORS policy, RBAC, ABAC, key rotation, encryption, AES-256, TLS, mTLS, bcrypt, argon2, Semgrep, OWASP ZAP, Snyk, Trivy, SBOM, container hardening, supply chain security, Cosign, SLSA, incident response, security posture, HashiCorp Vault, key management.

Use for SEO audits, keyword research, schema markup, conversion optimization, and AI search visibility. Triggers on SEO, technical SEO, SEO audit, keyword research, schema markup, JSON-LD, structured data, meta tags, robots.txt, sitemap, Core Web Vitals, GA4, GTM, conversion tracking, CRO, landing page optimization, A/B test, AI SEO, GEO, AEO, LLMO, programmatic SEO, competitor pages, link building, backlinks, local SEO, Google Business Profile, e-commerce SEO, hreflang, international SEO, AI citation, GPTBot, PerplexityBot, ClaudeBot, content freshness, pricing page SEO, product launch SEO.

Use when running tests, writing test cases, checking coverage, or doing type-checks. Triggers on test, unit test, vitest, Playwright, E2E test, pytest, type-check, tsc --noEmit, test coverage, regression test, test suite, pnpm test, npx vitest, npx playwright test, test file, .test.ts, .spec.ts, describe, it, expect, mock.

Use for TypeScript/JavaScript LANGUAGE-LEVEL type system, compiler, build tooling, and package management — NOT for framework-specific work. Triggers on generics, conditional types, mapped types, template literal types, type guards, discriminated unions, utility types, type narrowing, infer keyword, satisfies, const assertions, recursive types, 'Type instantiation is excessively deep', advanced JS (Proxy, Reflect, Symbol, WeakMap, iterators, generators), build tools (Vite config, esbuild, Turbopack, Webpack, tree-shaking), tsconfig, strict mode, path aliases, incremental builds, ESLint flat config, typescript-eslint, Prettier, dependency injection (tsyringe, inversify), package managers (npm, pnpm, yarn workspaces, peer dependencies). NOT for React components or JSX (use web-frontend), NOT for REST/GraphQL API routes or JWT auth middleware (use backend-data), NOT for writing or running test files like .test.ts or Playwright (use testing-quality), NOT for security audits or vulnerability scanning (use security-deep). Even when a type-system question appears inside a test file context, this skill handles the TYPE question, not the test methodology.

Use for any browser-rendered UI work. Triggers on React components, hooks, state, props, JSX, Next.js pages, App Router, SSR, RSC, server actions, Tailwind CSS classes, responsive layout, dark mode, styling, CSS, accessibility, ARIA, keyboard navigation, focus management, UI design systems, color palettes, typography, component architecture, compound components, frontend performance, LCP, Lighthouse, re-renders, bundle size, Playwright browser tests, Testing Library, Remotion video compositions, captions, animations. Covers design patterns, hover states, forms, modals, navigation, grids, and any .tsx/.jsx file editing.