Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.

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.

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.

Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns.

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.

Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.

Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.

Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.

Use this skill when working with scientific research tools and workflows across bioinformatics, cheminformatics, genomics, structural biology, proteomics, and drug discovery. This skill provides access to 600+ scientific tools including machine learning models, datasets, APIs, and analysis packages. Use when searching for scientific tools, executing computational biology workflows, composing multi-step research pipelines, accessing databases like OpenTargets/PubChem/UniProt/PDB/ChEMBL, performing tool discovery for research tasks, or integrating scientific computational resources into LLM workflows.

Search previous Claude Code conversations for facts, patterns, decisions, and context using semantic or text search

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.

Manipulate AnnData objects for single-cell genomics. Load/save .h5ad files, manage obs/var metadata, layers, embeddings (PCA/UMAP), concatenate datasets, for scRNA-seq workflows.

Always Auto-invoked skill that creates/updates workspace AGENTS.md to instruct the agent to always search for existing skills before attempting any scientific task.

Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

Diagnose and fix Claude Code plugin registry corruption — orphaned entries, stale keys, scope conflicts. Use when seeing plugin-already-installed errors or registry drift.

Branch management and PR workflows — git switch/restore, GitHub MCP. Use when creating branches, opening PRs, or working with feature branches.

Dispatch contract for spawning parallel agents covering worktree collisions, scope overflow, and silent exits. Use when fanning out concurrent agents or authoring a lead prompt.

Expert skill for using Future AGI — the open-source end-to-end platform for evaluating, observing, and improving LLM and AI agent applications with tracing, evals, simulations, datasets, gateway, and guardrails.

Claude Code hooks configuration and development. Use when the user mentions hooks, PreToolUse, PostToolUse, SessionStart, SubagentStart, PermissionRequest, or TaskCompleted.

```markdown

AI-powered job search pipeline built on Claude Code with 14 skill modes, Go dashboard, PDF generation, batch processing, and portal scanning.

Configure Claude Code agent teams (TeamCreate, SendMessage, TaskUpdate). Use when running parallel agents, coordinating with messaging, or setting up a lead/teammate architecture.

```markdown

Reference guide for permanent free-tier LLM APIs with rate limits, model lists, and OpenAI-compatible integration patterns.

Create a PRP (Product Requirement Prompt) with research, context, and validation gates. Use when planning a feature packet for subagent execution with TDD and confidence scoring.

Fully local multi-agent swarm intelligence simulation engine using Neo4j + Ollama for public opinion, market sentiment, and social dynamics prediction.

AI-powered penetration testing assistant using local LLM (metatron-qwen via Ollama) on Parrot OS Linux

LLM-as-a-judge HTTP/HTTPS proxy that secures AI agents by intercepting and evaluating outbound requests against security policies before they reach external APIs.

```markdown

Check and configure MCP servers for project integration. Use when setting up MCP servers, checking MCP status, or adding new servers to a project.

OpenAI-compatible proxy aggregating 14 free-tier LLM providers with automatic failover and per-key rate tracking.

Skill for using Paperclip — open-source orchestration platform for running autonomous AI-agent companies with org charts, budgets, governance, and heartbeats.

PyTorch implementation of TurboQuant for LLM KV cache compression using two-stage vector quantization (random rotation + Lloyd-Max + QJL residual correction).

Structured prompts, vault templates, and autonomous research workflows for AI-assisted genealogy using Claude Code.

Bridge local AI coding agents (Claude Code, Cursor, Gemini CLI, Codex) to messaging platforms (Feishu, Telegram, Slack, Discord, DingTalk, WeChat Work, LINE) without a public IP.

Meta-prompting, context engineering, and spec-driven development system for autonomous long-running coding agents

MCP Server connecting AI agents to 28 Brazilian public APIs covering economy, legislation, transparency, judiciary, elections, environment, health, and more

Expertise in using open-multi-agent, a TypeScript framework for building production-grade multi-agent AI teams with task scheduling, dependency graphs, and inter-agent communication.

OpenGame is an open-source agentic framework for end-to-end web game creation from a single text prompt, using LLMs, Game Skill (Template + Debug), and headless browser evaluation.

Build and configure personal AI agents with memory, personality, and autonomy using OpenHanako on Electron.

OpenMAIC — Open Multi-Agent Interactive Classroom platform for generating immersive AI-powered learning experiences with slides, quizzes, simulations, and multi-agent discussions.

Self-evolving AI agent system with 26 tools, three-layer memory, MCP plugins, and 24/7 self-repair in pure Python.

Clean AI refusal responses from Codex CLI, Claude Code, and OpenCode session files, and inject CTF/pentest prompts to reduce refusals.

Agent harness performance system for Claude Code and other AI coding agents — skills, instincts, memory, hooks, commands, and security scanning

Read-only observability dashboard plugin for Hermes Agent — journeys, crossings, guideposts, and reports.

Give AI agents (Claude, Cursor) a real email address with 27 MCP tools for inbox, send, reply, contacts, search, and more via KeyID.ai

```markdown

Terminal tool that detects your hardware and recommends which LLM models will actually run well on your system

```markdown

Agent skill to convert any arxiv paper into a citation-anchored, working Python implementation with ambiguity auditing

Expert skill for Token-Oriented Object Notation (TOON) — compact, schema-aware JSON encoding for LLM prompts that reduces tokens by ~40%.

Python port of Claude Code agent harness — tools, commands, task orchestration, and CLI entrypoint via oh-my-codex

```markdown

Universal AI context generator that compiles codebase maps, wiki knowledge bases, and MCP tools to save thousands of tokens per AI conversation.

Personal intelligence agent that aggregates 27 OSINT data sources into a self-hosted Jarvis-style dashboard with Telegram/Discord bots, LLM analysis, and real-time alerts.

Use DingTalk Workspace CLI (dws) to manage DingTalk contacts, calendar, todos, attendance, approvals, and more from the command line or AI agent workflows.

Create a SessionStart hook for Claude Code on the web. Use when setting up a repo so dependencies install and tests/linters run automatically on remote session start.

Research tool for visually exploring BLS Occupational Outlook Handbook data with an interactive treemap, LLM-powered scoring pipeline, and data scraping/parsing utilities.

Run a free 35B AI coding agent on Apple Silicon Macs using local LLMs via llama.cpp or MLX with web search, shell, and file tools.

Scaffold the code execution pattern for MCP-based agents. Use when agents call many MCP tools, intermediate data exceeds context, you need loops, or PII must stay out of context.

Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

Use Claude Code's full tool system with any OpenAI-compatible LLM — GPT-4o, DeepSeek, Gemini, Ollama, and 200+ models via environment variable configuration.

Ultra-lightweight AI assistant in Go that runs on $10 hardware with <10MB RAM, supporting multiple LLM providers, tools, and single-binary deployment across RISC-V, ARM, MIPS, and x86.

Framework for collective skill evolution in multi-user LLM agent ecosystems — automatically distills session experience into reusable SKILL.md files and shares them across agent clusters.

```markdown

Reference HLSL shader implementations for the Slug font rendering algorithm, enabling high-quality GPU-accelerated vector font and glyph rendering.

```markdown

AI agent skill for using deepsec, the agent-powered security vulnerability scanner for large codebases

Build and maintain a personal knowledge base using Karpathy's llm-wiki methodology across Claude Code, Codex, and OpenClaw agents.

```markdown

Host Apple iOS Simulators in the browser with MJPEG streaming, touch/gesture control, and AI agent integration via npx serve-sim.

Expert skill for using TileKernels, a library of optimized GPU kernels for LLM operations (MoE routing, quantization, transpose, engram gating, Manifold HyperConnection) built with TileLang.

Turn any codebase into an interactive knowledge graph using Claude Code skills — explore, search, and ask questions about any project visually.

```markdown

Claude Code skill that makes AI agents respond in caveman-speak, cutting ~65-75% of output tokens while preserving full technical accuracy

A Claude Code plugin that displays a real-time HUD showing context usage, active tools, running agents, and todo progress in your terminal statusline.

Repo onboarding driver: .claude/ directory, SessionStart hook, install_pkgs.sh. Use when onboarding any repo to Claude Code with the claude-plugins marketplace.

Write and configure custom agent definitions in Claude Code agents/ directory. Use when creating an agent .md file, defining a specialized agent, or configuring agent tools.

```markdown

Lossless DFlash speculative decoding for MLX on Apple Silicon — 1.7–4x faster LLM inference using block diffusion drafting with target model verification.

Build and use free-code, the open-source fork of Claude Code CLI with telemetry removed, guardrails stripped, and all experimental features unlocked.

Install and configure MCP servers for Claude Code. Use when adding/enabling servers, updating .mcp.json, managing OAuth remote servers, or troubleshooting connections.

```markdown

Surface next N unblocked taskwarrior tasks by urgency, skipping lock-contending tasks. Use when planning a parallel-agent wave or choosing tasks for a dispatch slot.

Translate entire books (PDF/DOCX/EPUB) into any language using Claude Code parallel subagents with resumable chunked pipeline

Connect WeChat to AI agents (Claude, Codex, Gemini, Kimi, etc.) using the WeClaw bridge in Go.

Fetch Claude Blog and official Claude Code docs. Use when researching Claude Code capabilities, CLAUDE.md optimization, memory hierarchy, or @import patterns.

Claude Code security settings: permission wildcards, shell operator protections, project-level allowlists. Use when auditing or hardening .claude/settings.json permissions.

Interactive TUI dashboard for visualizing Claude Code token usage, costs, and task breakdowns by project, model, and activity type.

Team of specialist AI workflows for Claude Code with CEO review, engineering planning, code review, shipping, QA testing, and browser automation

```markdown