NLP

Optimize and post-process GLB/glTF 3D models. Use when compressing models for web delivery, reducing file size, simplifying geometry, inspecting model stats, merging models, or converting textures. Triggers on: optimize GLB, compress model, reduce file size, simplify mesh, draco compression, meshopt, webp textures, inspect model, merge GLB, model optimization.

Discover structural and causal relationships between seemingly unrelated observations to reveal how things influence each other. Use when: (1) asked to find relationships between separate ideas or map how observations connect, (2) multiple observations seem unrelated but might share causal links or common mechanisms, (3) building system models that show interaction patterns and feedback loops, (4) seeking solutions by recognizing analogous mechanisms from different contexts.

Creates plugins (skills and MCPs) by guiding through the authoring process. Use when users want to create or update (1) skills that extend Claude's capabilities with specialized knowledge and workflows, or (2) MCPs (Model Context Protocol servers) that provide tools for Claude Desktop.

Portfolio analytics, metrics calculation, performance tracking, and dashboard data. Use when working with analytics code, files, or integration. Invoke when navigating analytics codebase, searching for analytics files, debugging analytics errors, or discussing analytics patterns. Keywords: analytics, analytics

Work with GNU recutils for plain-text record databases. Use when creating, querying, or validating .rec files, defining record schemas with %rec descriptors, converting between rec/CSV formats, or when the user mentions recutils, recsel, recins, recfmt, or record-oriented data files.

Generates implementation specifications from conversation context optionally enriched with GitHub issue data

Assists with writing and editing general prose using Strunk & White's Elements of Style and Wikipedia's AI writing detection guide. Use when composing articles, blog posts, or editing text for clarity and authenticity.

Use when analyzing markets or interpreting charts - applies technical indicators (RSI, MACD, Moving Averages), identifies support/resistance, analyzes multi-timeframe trends, checks fundamentals and sentiment. Activates when user says "analyze BTC", "what's the trend", "check this chart", mentions ticker symbols, or uses /trading:analyze command.

Native Fabric pattern execution for Claude Code. USE WHEN processing content with Fabric patterns (extract_wisdom, summarize, analyze_claims, threat modeling, etc.). Patterns run natively in Claude's context - no CLI spawning needed. Only use fabric CLI for YouTube transcripts (-y) or pattern updates (-U).

Design and evaluate context compression strategies for long-running agent sessions. Use when agents exhaust memory, need to summarize conversation history, or when optimizing tokens-per-task rather than tokens-per-request.

Lightweight playbook distilled from AI Architecture to keep dual-engine memory (.ai_context) and manifest dispatcher with minimal overhead; use when bootstrapping or porting the pattern into Claude Skills format.

Build and provision Ollama models from Modelfiles, verify health, and hot-swap personas. Use to translate Modelfile text into runnable models.

Creates expert consultation documents with code extraction, git diffs, and size tracking (125KB limit). Use when user asks to "create an expert consultation document", "prepare code for expert review", "gather architecture context", or needs comprehensive technical documentation for external analysis. Requires Node.js 18+.

Spec-driven development workflow skill. Auto-loads when working on: - Specification creation or editing - Technical planning - Task decomposition - Implementation within ClaudeCraft context

Master catchup for David. Use at SESSION START, when user says 'catchup', 'was hab ich verpasst', 'was ist los', 'check status', 'zeig blocked', or before Daily Sync. Shows Marius activity, blocked/waiting issues with context. (project)

Instantiate polymorphic analytics for multi-context analysis.

Generate structured skill specifications for independent skill creators. Use when asked to ideate, brainstorm, or specify multiple skills for a domain, workflow, or problem space. Outputs self-contained specs with list-level context so each skill can be built independently. Triggers on requests like "what skills would help with X", "generate skill ideas for Y", "specify skills to cover Z workflow".

Analyze, compare, and work with tokenizers using Unsloth tools. Compare different tokenizers, analyze token efficiency, and integrate with Unsloth models. For SuperBPE training, see the 'superbpe' skill.

This skill sets up dark mode / theme switching with persistence and system preference detection.Supports React (Context API, use-dark-mode), Vue 3 (Composition API), Tailwind CSS, CSS variables.Creates theme provider, toggle component, localStorage persistence, system preference detection (prefers-color-scheme).Activate when user says "dark mode", "theme switcher", "light/dark toggle", or needs theme switching.Output: Complete theme system with toggle, persistence, system detection, and smooth transitions.

Retrieve documentation context from local ai-docs. Check here first when implementing features, debugging errors, or needing library information. Fall back to web search if topic not found locally.