NLP

Enhanced Just-In-Time document loading system that intelligently discovers, loads, and caches relevant documentation based on user intent and project context. Use when users need specific documentation, when working with new technologies, when answering domain-specific questions, or when context indicates documentation gaps.

Assess text readability using multiple metrics. Execute Python script for detailed readability analysis. Use when evaluating text complexity, comprehension level, or audience fit.

Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge

PCE (Process Context Engine) のメンテナンススキル。現存する Claim の品質を維持し、間違い・不要・古い・重複した Claim を整理する。pce_memory_feedback を使用して更新・削除・評価を行う。メモリの健全性を保ちたい場合、Claim の品質問題を発見した場合、定期的なメモリ整理を行いたい場合に使用する。Observation 収集、AC の構築、タスクごとのメモリ最適化は行わない。

Interactive ClaudeShack ecosystem initialization that analyzes your codebase, mines history, discusses findings with you to establish baseline understanding, and seeds Oracle with verified knowledge. Use when setting up ClaudeShack in a new project or resetting knowledge. Creates a personalized foundation that improves over use. Sets up Context7 for current library docs.

Collect and verify project information for pce-memory with multi-model validation using Codex CLI. Use when gathering project context, onboarding to a new codebase, or building a knowledge base. Triggers on "collect project info", "build knowledge base", "index this project", or "remember this codebase".

Enterprise configuration schema validation and management orchestrator with JSON Schema v2024-12, Context7 integration, semantic versioning compliance, environment variable management, secrets handling, multi-environment support, and configuration-as-code best practices; activates for config validation, schema enforcement, environment setup, secrets management, and configuration audits

Externalize detailed memory to Memory Bank before conversation summarization to prevent context loss.LOAD THIS SKILL WHEN: Conversation exceeds 10 turns | completing major features | User says "checkpoint", "存檔", "記一下", "先記著" | before leaving or pausing work.CAPABILITIES: Batch update all Memory Bank files (activeContext, progress, decisionLog, architect); preserve file paths and decisions.

Transform Gmail into a business intelligence system for MTL Craft Cocktails. Answer questions about emails, detect leads, draft responses, and track client communications with context about the cocktail catering business.

Takes a concise statement, bullet point, or short summary and expands it into a paragraph or section, enriching the content with relevant information and context.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Generate relevant memes using the memegen.link API. Use this skill when users request memes, want to add humor to content, or need visual aids for social media. Supports hundreds of popular meme templates with custom text and styling options.

Use when needing workflow job results and log commands from PR - automatically waits for workflows to complete, then returns job summaries with gh commands to retrieve logs without loading large logs into context

Generate, edit, and compose images using Google's Gemini 3 Pro Image model (Nano Banana Pro). Use this skill when the user asks to create images, generate visuals, edit photos, compose multiple images, create logos, thumbnails, infographics, product shots, or any image generation task. Supports text-to-image, image editing, multi-image composition (up to 14 images), iterative refinement, aspect ratio control, and Google Search-grounded image generation for real-time data visualization.

Write CRPO-compliant therapy copy that connects and converts without pressure tactics. Use when writing service pages, CTAs, hero sections, or any persuasive therapy content. Takes core direct-response principles and applies them to therapy context with 40% tone reduction. NO outcome guarantees, NO urgency tactics, NO testimonials. Maintains empathetic, professional tone while driving action through trust-building and value demonstration. References core direct-response-copy skill but filters all output through CRPO compliance lens.

Create and fix ASCII diagrams, tables, wireframes, box-drawings. Use when message contains Unicode box characters (┌┐└┘│─), user asks to create/fix text visualization, align borders, or fix broken ASCII art. Triggers on "поправ діаграму", "fix diagram", "create table", "вирівняй", "align boxes".

Automatically invoked when user wants to develop new features using Test-Driven Development.Trigger keywords: "new feature", "add API", "implement", "create endpoint", "TDD","test-driven", "新功能", "新增 API", "實作"This skill enforces strict TDD workflow: RED → GREEN → REFACTORUses subagents to maintain clean context and ensure quality.

Build MCP (Model Context Protocol) servers to extend Claude's capabilities with database access, API integrations, or custom tools.

Implement Lexical Editor with automatic image management using Laravel Observers. Converts base64 images to file storage, deletes unused images, and handles cleanup. Use when building WYSIWYG editors with rich content, managing media uploads in editors, implementing automatic image optimization, or setting up Observer-based storage management for rich text editors.

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.