All Skills

Analyzes album state and recommends the optimal next action. Use when the user asks "what should I do next?" or "what's left to do?"

Guide for creating effective skills. Use when creating a new skill or updating an existing skill that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Caddy reverse proxy configuration, Caddyfile syntax, automatic HTTPS, Docker integration, and common homelab patterns

LLM observability with Langfuse — query traces, generations, costs, metrics, and debug LLM pipelines via the REST API

Guides Claude in writing idiomatic, efficient, well-structured Rust code using proper data modeling, traits, impl organization, macros, and build-speed best practices.

Implement multi-layer LLM caching with exact match, semantic similarity, and provider-side prompt caching. Reduce API costs by 30–70%, cut latency, and improve throughput using Redis, GPTCache, and provider caching APIs.

Reduce LLM API and infrastructure costs through model selection, prompt caching, batching, caching, quantization, and self-hosting strategies. Track spend by team and model, set budgets, and implement cost-aware routing.

Creates a new album with the correct directory structure and templates. Use IMMEDIATELY when the user says 'make a new album' or similar, before any discussion.

Force-fit patterns from other domains to spark novel concepts.

This skill should be used when automating browser interactions via Vercel's agent-browser CLI. It handles web page navigation, form filling, screenshots, and data scraping using Bash commands with ref-based element selection. Triggers on "browse website", "fill form", "click button", "take screenshot", "scrape page", "web automation".

Automatically validate implementations in real browsers after code is written or when user says "test this". Uses Chrome DevTools MCP to test responsive breakpoints (320px, 768px, 1024px), check accessibility compliance (WCAG AA contrast, keyboard navigation, ARIA), validate interactions, and generate detailed technical reports with file paths and specific fixes.

Create comprehensive Claude Code plugins with proper structure, commands, agents, hooks, and marketplace configuration. Use when the user wants to build a new Claude Code plugin or asks how to create/structure a plugin.

Interactive guidance on writing complete, effective BDD scenarios for story-flow.

Generate a draft story markdown by analyzing a Jira story or feature description, Figma designs, and the codebase.

Expert customer lifecycle marketing guidance for retention, expansion, and advocacy. Use when designing onboarding programs, creating upsell strategies, preventing churn, building referral programs, or writing customer success content. Use for NPS programs, win-back campaigns, customer segmentation, and lifecycle email sequences.

Setup Sentry Tracing (Performance Monitoring) in any project. Use this when asked to add performance monitoring, enable tracing, track transactions/spans, or instrument application performance. Supports JavaScript, TypeScript, Python, Ruby, React, Next.js, and Node.js.

# Vector Databases for Semantic Search ## Overview Vector databases store and query high-dimensional vector embeddings, enabling semantic search, recommendation systems, and RAG applications. ## Key Concepts ### Embeddings Vector representations of text/images that capture semantic meaning: - Tex

'Git platform detection and cross-platform command mapping for GitHub,

This skill should be used when the user asks to "use six hats", "apply six thinking hats", "think with different hats", "use De Bono's hats", "separate thinking modes", "look at this from all angles", "consider all perspectives", or wants to process input through Edward de Bono's Six Thinking Hats to systematically examine a topic from multiple cognitive perspectives.

--- name: babysit description: Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.) version: 0.1.1 --- # babysit Orchestrate `.a5c/runs/<runI

Apply behavioral science to product design and produce a Behavioral Product Design Pack (target behavior, behavioral diagnosis, intervention map, prioritized concepts, design specs, experiment + instrumentation plan, ethics/trust review). Use for retention, onboarding, habit loops, and behavior change problems.

Diagnoses and fixes Rust compile errors, borrow-checker issues, runtime panics, and logic bugs with clear explanations and idiomatic solutions.

Automatically check code against PHPCS, ESLint, WordPress Coding Standards, or Drupal Coding Standards when user asks about code style, standards compliance, or best practices. Invoke when user mentions "coding standards", "code style", "linting", "PHPCS", "ESLint", or asks if code follows conventions.

Release automation skill for version bumping and tagging. Use when creating a new release, bumping version, tagging release, pushing release tag, or synchronizing version numbers across files. Handles package.json, README.md, SKILL.md, Dockerfile, and docker-compose files.