NLP

Implements TF-IDF based search engines for text datasets using vector space models and cosine similarity. Use when building search functionality, finding similar documents, ranking text by relevance, or working with text retrieval systems.

Build searchable knowledge bases from document collections (PDFs, Word, text files). Use for creating technical libraries, standards repositories, research databases, or any large document collection requiring full-text search.

CSS styling standards and best practices for responsive, accessible, and maintainable web interfaces with special considerations for multilingual content and Chuukese text display. Use when creating or modifying stylesheets and CSS components.

PROACTIVELY use when exploring unfamiliar codebases, analyzing remote repositories, generating reference skills from code, or needing AI-optimized context for code review. Triggers on "analyze repo", "explore codebase", "pack repository", "generate skill from", "understand this codebase", "code context".

Tracks complex, multi-session work with dependency graphs using bd (beads) issue tracker. Triggers on 'multi-session', 'complex dependencies', 'resume after weeks', 'project memory', 'persistent context', 'side quest tracking', 'portfolio', 'all my beads', 'cross-project beads', or when TodoWrite is insufficient for scope. For simple single-session linear tasks, TodoWrite remains appropriate. (user)

Enhanced docs generation with AI-powered features. Enhanced with Context7 MCP for up-to-date documentation.

Advanced diagnostic workflow for bug-fixer agent with mandatory Context7 MCP consultations, Chrome DevTools MCP integration, and systematic root cause analysis across all Clean Architecture layers.

Technical workflow for architect-agent - PRD creation with mandatory database context, entity design with Zod, iteration review, and agent coordination in the iterative v2.0 system

Generate AI images using GPT Image 1.5 for Hiverarchy blog posts. Use when user wants to create images, generate visuals, make illustrations, or add pictures to their posts.

This skill should be used when the user asks to "convert notebook to text", "use jupytext", "version control notebooks", "share data between kernels", "set up multi-kernel project", "pair notebooks with Python files", "sync ipynb and py files", or needs multi-kernel projects (Python/R/Stata/SAS) with version-control-friendly notebooks.

Delegates coding standards violation scanning to a lightweight agent. Use when checking files for violations without loading full source files into context.

Automatically bridge long technical sessions to keep context window small and costs low. Extracts key technical decisions, resolved bugs, active tasks, and essential code snippets from conversation history into a compact markdown summary (2,000–5,000 tokens). Use when reaching a project phase milestone, when Claude warns the context window is getting full, or to start a fresh session with minimal token cost while maintaining continuity.

Documentation and code examples research expert using Exa AI and Context7. Finds official docs, production code examples, technology comparisons, and best practices. Auto-activates when new libraries mentioned or user requests "docs", "examples", "best practices", or technology comparisons.

Implementation Agent: Full TDD workflow in a single context window. Writes tests, implements code, and iterates until all tests pass.

Runs ML models in the browser and Node.js with Transformers.js and Hugging Face Inference API. Use when adding local inference, embeddings, or calling hosted models without GPU servers.

Use when encountering errors, investigating library APIs, troubleshooting issues, or needing up-to-date documentation. Prioritizes Context7 and WebSearch over outdated training data.

Design AI-powered immersive NPC systems for escape room games using proven actor techniques from Korean immersive escape rooms (Danpyeonsun, Ledasquare). Implements adaptive dialogue, emotional simulation, player profiling, and trust dynamics using Gemini/GPT-4. Creates character profiles with lying probabilities, improvisational responses, and cost-optimized streaming. Use for murder mystery NPCs, suspect interrogation, or dynamic character interactions.

Process and analyze PDF documents including text extraction, table extraction, chart analysis, and visual content understanding. Use when working with PDFs, extracting structured data, generating summaries, or converting PDFs to other formats (markdown, JSON, CSV).

This skill should be used when the user asks about "snapshot.md", "constraints.md", "decisions.md", "debt.md", ".ctx/", "living context", "documentation freshness", "stale docs", "ADR", "architecture decision", "technical debt", "system context", "co-located documentation", "context health", "validation", or needs help managing co-located documentation that stays synchronized with code.

Unified enterprise programming language skill covering 25+ languages including Python 3.13, TypeScript 5.9, Go 1.23, Rust 1.91, Java 21, JavaScript ES2025, C++, C#, PHP, Swift, Kotlin, Scala, Elixir, Ruby, R, SQL, Shell, and more with patterns, best practices, and Context7 integration