Skills your agents can run
Plug-and-play capabilities — vetted, versioned, and runnable from any Mighty agent.
Complete Open WebUI API integration for managing LLM models, chat completions, Ollama proxy operations, file uploads, knowledge bases (RAG), image generation, audio processing, and pipelines. Use this skill when interacting with Open WebUI instances via REST API - listing models, chatting with LLMs, uploading files for RAG, managing knowledge collections, or executing Ollama commands through the Open WebUI proxy. Requires OPENWEBUI_URL and OPENWEBUI_TOKEN environment variables or explicit parameters.
AI Agent Security Suite - Real-time protection against prompt injection, command injection, SSRF, path traversal, secrets exposure, and content policy violations
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
Create and configure custom OpenCode agents (primary and subagents) with specialized prompts, tools, permissions, and models. Use when the user wants to create, modify, or configure OpenCode agents, or mentions agent modes, tool permissions, or task delegation.
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Autonomous memory system for persistent learning across sessions. Automatically saves architectural decisions, bugfixes, patterns, and insights. Use to recall context from previous work and build institutional knowledge.
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.
Anthropic Claude API 的 Python 和 TypeScript 使用模式。涵盖 Messages API、流式处理、工具使用、视觉功能、扩展思维、批量处理、提示缓存和 Claude Agent SDK。适用于使用 Claude API 或 Anthropic SDK 构建应用程序的场景。
Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5. Handles model string updates and prompt adjustments for known Opus 4.5 behavioral differences. Does NOT migrate Haiku 4.5.
Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production embedding generation.
Advanced prompt rewriting and optimization service. Analyzes prompts for clarity, specificity, structure, completeness, and usability. Identifies weaknesses, suggests improvements, and generates multiple rewrite options. Use when users need to improve an existing prompt's effectiveness, understand why a prompt isn't working well, generate variations of a prompt for A/B testing, or learn prompt engineering best practices through examples.
Adversarial brainstorming via Claude+Codex debate. Use when: exploring solutions, feasibility analysis, exhaustive enumeration. Not for: implementation (use feature-dev), architecture only (use codex-architect). Output: Nash equilibrium consensus + action items.
Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`; user asks for the Claude API, Anthropic SDK, or Managed Agents; user adds/modifies/tunes a Claude feature (caching, thinking, compaction, tool use, batch, files, citations, memory) or model (Opus/Sonnet/Haiku) in a file; questions about prompt caching / cache hit rate in an Anthropic SDK project. SKIP: file imports `openai`/other-provider SDK, filename like `*-openai.py`/`*-generic.py`, provider-neutral code, general programming/ML.
Run a quality check on your CLAUDE.md and workspace — flags what's thin, missing, outdated, or could be stronger. Use when you want to see how your system file holds up and where to improve it.
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.
Long-term memory across sessions. Always use memory_search at the start of any user request (unless the user explicitly says not to), especially for questions about the user (profile/personal info/preferences), prior constraints or decisions, and resuming ongoing work; use memory_write only when the user explicitly asks to store memory.
AI-powered diary generation for agents - creates rich, reflective journal entries (400-600 words) with Quote Hall of Fame, Curiosity Backlog, Decision Archaeology, and Relationship Evolution. Generates personal, emotional entries from the agent's perspective. Works best with Claude models (Haiku, Sonnet, Opus).
| Operation | API Cost | Frequency | Monthly Cost | |-----------|----------|-----------|--------------| | memory_search (embedding) | $0.02-0.05 | 50-200/day | $30-300 | | Context retrieval | $0.01...