Plugins

Prompt-engineering category of the AI Research Engineering Skills library — 4 skills covering DSPy (declarative prompt programming), Instructor (Pydantic-validated structured outputs), Guidance (regex/grammar-constrained generation), and Outlines (FSM-based structured text).

Emerging-techniques category of the AI Research Engineering Skills library — 6 skills covering Mixture-of-Experts training, Model Merging (TIES/DARE/SLERP via mergekit), Long Context (RoPE/YaRN/ALiBi), Speculative Decoding, Knowledge Distillation, and Model Pruning.

A lightweight Python framework for building modular AI agents with composable components, providing structured input/output schemas and tool integration for production-grade agent systems.

AI research skill for writing publication-ready ML papers for top conferences (NeurIPS, ICML, ICLR, ACL, AAAI, COLM) with LaTeX templates and citation verification.

A utility skills plugin from Baoyu's skills collection for Claude Code, including URL-to-markdown conversion, X post extraction, image compression, and markdown formatting tools.

A collection of 7 multimodal AI research skills covering CLIP, Whisper, LLaVA, BLIP-2, SAM, Stable Diffusion, and AudioCraft — part of Orchestra Research's 83 AI research engineering skills for coding agents.

A collection of 4 AI safety and alignment research skills covering Constitutional AI, LlamaGuard safety classifier, NeMo programmable guardrails with Colang, and Meta's Prompt Guard injection detector — part of Orchestra Research's AI research engineering skills.

Firebase CLI and official MCP Server for managing Firebase projects. Deploy code, run local hosting, interact with databases, and import/export Firebase Auth users from the command line or through AI agent integration.

Trail of Bits code-auditing plugin that detects insecure default configurations, hardcoded credentials, and fail-open security patterns during AI-assisted security review.

Trail of Bits code-auditing plugin that searches and extracts data from Burp Suite project files for AI-assisted security analysis.

Trail of Bits verification plugin that detects compiler-induced timing side-channels in cryptographic code — credited with finding a timing side-channel in ML-DSA signing (RustCrypto).

Trail of Bits code-auditing plugin that creates and refines Semgrep rules for custom vulnerability detection.

MCP server for structured spec-driven development workflows with a real-time dashboard, approval system, and VSCode extension.

Intercepts GitHub URL fetches and curl/wget commands, redirecting to the authenticated gh CLI. Includes gh CLI usage guidance.

A Python framework for building LLM-powered multi-agent systems with structured conversations, tool usage, and vector-store integration for complex AI workflows.

A tokenization skill from the AI Research Engineering Skills Library, which offers 83 skills across 20 categories covering model architecture, fine-tuning, inference, and other AI research areas.

Curated developer experience tips and productivity techniques for Claude Code.

Teaches design patterns for workflow-based Claude Code skills and provides a review agent for auditing existing skills

YARA-X detection rule authoring with linting and quality analysis

A CLI-native semantic search tool that works like grep but understands natural language, supporting multimodal content including code, images, and PDFs with built-in web search and background indexing.

Seven complementary Claude Code skills for building production-ready n8n workflows using the n8n-mcp MCP server, covering expression syntax, workflow patterns, and validation error handling.

A Claude Code plugin marketplace from Trail of Bits providing skills for AI-assisted security analysis, testing, and development workflows.

Part of a Claude Skills Library providing production-ready skill packages for Claude AI and Claude Code — reusable expertise bundles for marketing teams, executive leadership, product development, and web/mobile engineering with 65 skills and multi-agent compatibility.

A plugin marketplace and discovery platform for Claude Code with skills, agents, commands, hooks, and plugins for extending Claude Code capabilities.

A Git version control commands plugin from Build with Claude — a plugin marketplace featuring 117 agents, 175 slash commands, 28 hooks, and 26 skills for extending Claude Code workflows.

Design experience agents plugin from Build with Claude marketplace, providing 117+ specialized AI expert agents for Claude Code.

Project task management commands plugin from Build with Claude marketplace, providing 175+ slash commands for automation in Claude Code.

A plugin marketplace and discovery platform for Claude Code with skills, agents, commands, hooks, and plugins for extending Claude Code capabilities.

A minimal five-phase workflow skill (Specify→Plan→Act→Review→Vault) with a 10-point spec gate, unified journal, and 3-failure escalation protocol for structured task completion.

BMAD module of stellarlinkco/myclaude's Claude Code Multi-Agent Workflow System — runs the BMAD agile workflow with 6 specialized agents via the `/bmad-pilot` command (recommended for large enterprise projects); Claude Code orchestrates while a codeagent-wrapper executes against Codex/Claude/Gemini/OpenCode backends.