This skill should be used when the user asks to "translate to Sindarin", "write in Elvish", "Sindarin grammar", "Elvish translation", "speak Sindarin", "Tolkien Elvish", or mentions Sindarin language, Grey-elven, or needs help with Elvish linguistics from Tolkien's legendarium.
Query Langfuse traces, prompts, and LLM metrics. Use when: - Analyzing LLM generation traces (errors, latency, tokens) - Reviewing prompt performance and versions - Debugging failed generations - Comparing model outputs across runs Keywords: langfuse, traces, observability, LLM metrics, prompt management, generations
Validates eslint.config.ts and tsconfig.json against documented architecture patterns and infrastructure requirements. Checks ESLint plugin configurations, TypeScript strict mode, FP enforcement, layer boundaries, and alignment with docs/architecture/ and docs/infrastructure/. Use when user requests "validate config", "check eslint", "verify typescript settings", or mentions config audits.
Learn Claude Code in 5 hands-on lessons. From basics to building applications. Use when: user wants to learn Claude Code, asks "how do I...", or is new. Triggers: "learn", "teach me", "how does this work", "I'm new", "course".
Logs architectural decisions to docs/DECISIONS.md in ADR format. Use when: making significant architectural or technology choices. Integrates with /craft and /why commands.
Validates code against framework-specific best practices documented in docs/infrastructure/. Checks Effect usage patterns, React 19 conventions, Drizzle ORM patterns, Hono RPC implementations, and other framework-specific guidelines. Identifies anti-patterns and suggests corrections. Use when user requests "check best practices", "validate framework usage", "review code patterns", or mentions framework compliance.
Manages course progress tracking in ~/.claude-course/progress.json. Use when: loading, saving, or displaying course progress. Internal skill - used by /ccc:course commands.
Cloudflare Workers development patterns including Workers AI, Durable Objects, KV storage, and Hono routing. Use when building serverless edge functions, AI-powered services, or stateful workflows on Cloudflare.
LLM gateway and routing configuration using OpenRouter and LiteLLM. Invoke when: - Setting up multi-model access (OpenRouter, LiteLLM) - Configuring model fallbacks and reliability - Implementing cost-based or latency-based routing - A/B testing different models - Self-hosting an LLM proxy Keywords: openrouter, litellm, llm gateway, model routing, fallback, A/B testing
Generate comprehensive tests for architectural layers with coverage-first analysis. Use when testing specific layers (core, domain, application, infrastructure, boundary). Reads testing strategy from playbook or uses interactive template selection.
Agent Factory master skill for intelligent Claude Code agent generation. Includes requirement analysis, domain detection, model selection, template system, validation framework, and advanced features. Contains algorithms, workflows, and patterns.
Tracks package.json dependencies and identifies undocumented, outdated, or misaligned tools. Compares installed packages against documented versions in docs/infrastructure/, detects unused dependencies, and flags version mismatches. Use when user requests "check dependencies", "audit package.json", "find undocumented packages", or mentions dependency alignment.
LLM prompt testing, evaluation, and CI/CD quality gates using Promptfoo. Invoke when: - Setting up prompt evaluation or regression testing - Integrating LLM testing into CI/CD pipelines - Configuring security testing (red teaming, jailbreaks) - Comparing prompt or model performance - Building evaluation suites for RAG, factuality, or safety Keywords: promptfoo, llm evaluation, prompt testing, red team, CI/CD, regression testing
Rubato Composer integration for Mazzola's mathematical music theory
Assess Claude Code knowledge and route to appropriate learning level. Use when: user wants to learn Claude Code, asks for guidance, or says "teach me". Triggers: "learn Claude Code", "teach me", "I'm new", "where do I start", "beginner".
Detects duplicate code patterns, similar functions, repeated logic, and copy-paste code across the codebase. Identifies refactoring opportunities by finding code that violates DRY principle. Reports duplication with similarity scores and refactoring suggestions. Use when user requests "find duplicates", "check for copy-paste code", "detect repeated logic", or mentions DRY violations.
Create and maintain architecture documentation following Lucid Composite Architecture (LCA) principles. INVOKE THIS SKILL when user: - Asks an "architect" to review or analyze anything - Mentions "architecture review", "structural review", or "design review" - Requests documentation of system structure or component hierarchies - Wants to create, update, or review ARCHITECTURE.md files - Discusses Atoms, Composites, Conduits, or Deployable Units - Asks about LCA principles or architectural patterns - Needs data strategy with Schema.org at boundaries Trigger keywords: architect, architecture, structural, LCA, component hierarchy, ARCHITECTURE.md
Interpret THOR scan results and explain what findings mean. Use when the user pastes THOR log lines, shares a log file, or asks how to triage Notices/Warnings/Alerts.
