Claude Code プラグイン
公開されている Claude Code marketplace からの 9 件のプラグインです。それぞれにスキル、スラッシュコマンド、エージェント、フック、MCP サーバーがまとめてインストールされます。
› /plugin marketplace add trailofbits/skills
› /plugin install modern-cpp@trailofbits
peepshow-marketplacet0mtaylor/peepshow1公開されている Claude Code marketplace からの 9 件のプラグインです。それぞれにスキル、スラッシュコマンド、エージェント、フック、MCP サーバーがまとめてインストールされます。
peepshow-marketplacet0mtaylor/peepshow1
rpa-skillsEvilFreelancer/rpa-skills1.claude-plugin/marketplace.json を含むリポジトリを提出すると、すべての plugin を掲載します。
marketplace を提出するModern C++ best practices (C++20/23/26). Use when writing C++ code, creating new C++ projects, or modernizing legacy C++ patterns.
10 working methods for systems languages: c-memory-safety, cpp-raii, ffi-boundaries, go-concurrency, and more
California Consumer Privacy Act (CCPA) and California Privacy Rights Act (CPRA) compliance advisor — business threshold analysis, consumer rights fulfillment (access, delete, correct, opt-out of sale/sharing, limit SPI, ADMT opt-out), privacy notice drafting, service provider vs. contractor vs. third-party classification, sensitive personal information (SPI) handling, data minimization, opt-out mechanisms (including GPC), cybersecurity audits and risk assessments (live since Jan 1, 2026), ADMT obligations (effective 2026, deadline Jan 1, 2027), CPPA enforcement (Disney $2.75M, PlayOn $1.1M, Ford $375K), penalty exposure, GDPR comparison, and gap assessments for businesses operating in or targeting California residents.
Operate, configure, secure, and troubleshoot the LiteLLM AI gateway (proxy) and Python SDK: run the proxy (litellm --config), route to 100+ providers through one OpenAI-compatible API, configure model lists and routing/reliability, virtual keys, teams, budgets, rate limits, caching, guardrails, observability, and spend, and diagnose request failures. Use when deploying or running a LiteLLM proxy or gateway (config.yaml, ghcr.io/berriai/litellm), wiring the Python SDK or OpenAI SDK through it, or hardening a public-facing deployment. Do not use for operating a single inference engine (vllm, llama-cpp), for engine-selection methodology (ml-engineering), or for building applications on top of an LLM API (backend/frontend engineering).
Operate, configure, benchmark, and troubleshoot llama.cpp across CPU, Metal, CUDA, HIP/ROCm, Vulkan, SYCL, and hybrid or multi-GPU systems. Use when installing or building llama.cpp, selecting or inspecting GGUF models, running llama-cli or bounded llama-completion, serving an OpenAI-compatible API with llama-server, tuning memory and performance, or diagnosing backend, context, template, and API failures. Do not use for model training or fine-tuning, general inference-framework selection, llama-cpp-python or other bindings, LlamaIndex, Ollama, or LM Studio operation.
Plan and execute production ML engineering work — classifier versus generative model selection, zero-shot baselines, coding specialization, model training and fine-tuning (LoRA/QLoRA), evaluation and eval-set design, quantization decisions, inference deployment, lineage, feature parity, drift response, and regression triage, experimental weight inspection and targeted editing, grounded in practical engineering patterns for production ML systems. Do not use for statistical modeling and experimental design (that's the data scientist) or for operating a specific inference engine (that's a tool skill such as llama-cpp or vllm).
Operate, configure, benchmark, and troubleshoot vLLM inference servers: Docker and Kubernetes deployment, quantization-aware model configuration (tensor parallelism, KV cache), OpenAI-compatible API serving, throughput and latency benchmarking, continuous batching tuning, GPU operation, and upgrade/rollback. Use when deploying or running a vLLM server (vllm serve, vllm/vllm-openai), sizing a model and its KV cache for GPUs, selecting quantization and parallelism, serving via /v1 endpoints, measuring serving throughput or latency, tuning batching, or diagnosing GPU, OOM, or startup failures in a vLLM deployment. Do not use for model training, fine-tuning, evaluation-set design, or engine-selection methodology (that is ml-engineering), or for operating the llama.cpp stack with GGUF models (that is llama-cpp); other inference engines (TGI, Ollama, Triton) are out of scope.
Extract relevant frames from videos and animated images (GIF/APNG/animated WebP) so LLMs can view them as a timeline. Auto-transcribes audio (whisper.cpp default) and writes a self-contained HTML report + manifest.json + ndjson run history per extract. Wraps ffmpeg with scene-change detection and fps fallback.
Prepare a Linux server with NVIDIA or Intel Arc GPUs for LLM and neural-network workloads: NVIDIA driver + CUDA from the official repo or the in-tree Intel i915/xe driver with distro firmware, Docker Engine with verified GPU access (NVIDIA Container Toolkit or /dev/dri passthrough) as the mandatory base, staged verification gates for both vendors, optional docker-compose presets for vLLM, Infinity, OpenWebUI and Ollama plus Intel Arc stacks (llama.cpp SYCL/Vulkan, Ollama, OpenVINO, vLLM), GPU power limits persisted via systemd, case fans driven by GPU temperature and Intel Arc idle-power fixes (ASPM).
ops
