Plugins

LLM-powered knowledge graph for academic papers: tracks concepts, projects, and engagement as you read, with a local Too Many Papers web UI.

Bundles two agent skills: challenger (adversarial stress-tester for technical decisions, designs, and specs) and skill-forge (turns repeated manual workflows into reusable, validated Agent Skills).

Scaffold a new TypeScript CLI tool's documentation and configuration, or audit an existing tool against the project tool-conventions (docs/tools/<name>.md format, ~/.tool-agents/<name>/ config folder, four-tier env-var resolution chain, vendor-canonical LLM provider names, no-fallback rule). Bundles the /tool-conventions command and its tool-doc-config-architect subagent.

Automatisierte Skill- und Plugin-Verbesserung: Strukturpruefung, CLAUDE.md-Audit, A/B-Benchmark mit Varianz-Analyse und HTML-Report

基于动态 Gate、分级证据、场景权重和敏感性分析调查、比较并筛选最适合用户约束的工具

找出任務可用的工具（MCP、Skills、CLI）或搜尋更好的替代方案

Intelligent permission gate for shell, file, search, Skill, and MCP tool surfaces. AST-parses Bash commands, guards file reads/writes, and blocks configured tool invocations. Tracks manually approved commands for permanent rules.

Register the deferred tool_search MCP bridge

Personal utility commands and tools for Claude Code

from eliaslecomte/claude-plugin

Infrastructure and authoring utilities for agent workspaces, handoffs, audits, harvesting, and plugin management

Docker, Drizzle ORM, pnpm workspaces, Zod schemas, Claude Code plugin conventions, npx skills conventions

Sean O'Dell's personal Claude Code toolkit — GitHub SSH key management and more

Plugin from SergioLNeves/toolkit-agent-skills

A team of five specialist agents coordinated by one skill. Activates automatically on messages wrapped in [[ double square brackets ]]. Handles prompt engineering, guardrails, and testing/evaluation automatically; asks before taking on coding or skill-building tasks.

Codex review, media tools, and HTML presentations

tools-registry Script-Runner (stdio)

Tool operation skills for Firecrawl web search, scraping, research, and content extraction.

Daily agent tools: artifact creation, advisor review, browser automation, TUI automation, subagent orchestration, and Codex model routing.

General purpose CLI tools: fd, ripgrep, jq, yq, shell scripting, ImageMagick, Mermaid diagrams, and universal dependency installation

Utility skills — Claude Code guide, NotebookLM, Graphify, awesome lists

Aggregates your MCP servers and exposes three tools instead of hundreds, with a live token-savings receipt.

Semantic folder index for codebase navigation. Creates index.toon files with summaries ordered by priority. "Oh, I see you've discovered my meticulously organized archive."

Provider-agnostic Claude Code statusline plugin (ToPGauge) for token-plan usage and account balance. Picks the provider from ANTHROPIC_BASE_URL (currently MiniMax + DeepSeek); hides itself otherwise. Ships :install, :uninstall, :clean, and :clean-cache slash commands.

69-skill Topia Nexus for Claude Code — TDD rails, readiness/guardian/completion-gate hooks, Maestro routing, optional agora-code neural memory

Benchmark a Hugging Face model on an Intel GPU through pure PyTorch + Transformers, **single-process, no HTTP server**. Measures generate() throughput in tokens/sec, time-to-first-token, decode-step latency, and peak XPU memory. Also covers diffusion and encoder-only models via `references/non-llm-snippets.md`. Use after **model-can-it-fit** to validate predicted memory against `torch.xpu.max_memory_allocated()`.

Profile a Hugging Face model on Intel GPU at the **PyTorch level** with `torch.profiler` and Kineto. Captures CPU + XPU timeline, exports Chrome trace, identifies hottest kernels and async-overlap gaps. Use when the user asks why a model is slow, which op is the bottleneck, or where the GPU is idle. Not for profiling inside a running vLLM server (use vllm-xpu-profile) or for SYCL-kernel-level signal beneath the PyTorch op layer (use xpu-profile-unitrace).

Run an arbitrary Hugging Face safetensors model on an Intel GPU using **upstream PyTorch** (>= 2.8) with the built-in `torch.xpu` device. Covers loading from the Hub, picking the right dtype, autocast, multi-GPU with accelerate's `device_map`, and the CUDA -> XPU code translation a user has to do once. Use for the Transformers / Accelerate / Diffusers path. Not for OpenAI-compatible serving (use vllm-xpu-run); explicitly not via intel-extension-for-pytorch (ipex) or ipex-llm — those paths are end-of-life and upstream PyTorch supersedes them.

Skills for searching and downloading torrents from nyaa.si (anime), YTS (movies, ytz.mx), and managing downloads via qBittorrent.

토스증권 Open API로 국내·미국 주식 시세/종목/환율/장운영 조회와 계좌·보유주식·주문을 다루는 플러그인 (tossinvest CLI 기반)