Claude Code Skills · page 2

Use live BCI cognitive and mood state from NeuroSkill.

Build, test, and deploy Python MCP servers.

List, auth, and call MCP servers/tools from the terminal.

Import an OpenClaw setup (memories, skills) into Hermes.

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.

Embedding database for RAG and semantic search.

Zero-shot image classification and image-text search.

Fast vector similarity search at billion scale.

Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.

Constrain LLM output with grammars; guarantee valid JSON.

Fast BPE/WordPiece tokenization and custom vocab training.

Outlines: structured JSON/regex/Pydantic LLM generation.

Structured LLM outputs validated with Pydantic.

Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.

Vision-language chat: VQA, captioning, image dialogue.

Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.

Curate LLM training data: dedupe, filter, PII redaction.

OBLITERATUS: abliterate LLM refusals (diff-in-means).

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

Managed vector DB for production RAG and search.

Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2

High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

DSPy: declarative LM programs, auto-optimize prompts, RAG.

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.

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.

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.

Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).

TRL: SFT, DPO, PPO, GRPO, reward modeling for LLM RLHF.

Unsloth: 2-5x faster LoRA/QLoRA fine-tuning, less VRAM.

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.

Canvas LMS integration — fetch enrolled courses and assignments using API token authentication.

Publish static sites to {slug}.here.now and store private files in cloud Drives for agent-to-agent handoff.

>-

Shop.app: product search, order tracking, returns, reorder.

Shopify Admin & Storefront GraphQL APIs via curl. Products, orders, customers, inventory, metafields.

SiYuan Note API for searching, reading, creating, and managing blocks and documents in a self-hosted knowledge base via curl.

Give Hermes phone capabilities without core tool changes. Provision and persist a Twilio number, send and receive SMS/MMS, make direct calls, and place AI-driven outbound calls through Bland.ai or Vapi.

Gateway to 400+ bioinformatics skills from bioSkills and ClawBio. Covers genomics, transcriptomics, single-cell, variant calling, pharmacogenomics, metagenomics, structural biology, and more. Fetches domain-specific reference material on demand.

Evolve prompts/regex/SQL/code with Imbue's evolution loop.

Passive domain reconnaissance using Python stdlib. Subdomain discovery, SSL certificate inspection, WHOIS lookups, DNS records, domain availability checks, and bulk multi-domain analysis. No API keys required.

>

Pay HTTP 402 APIs via Machine Payments Protocol (MPP).

Agent payments via Stripe Link — cards, SPT, approvals.

Provision SaaS services + sync creds via Stripe Projects.

Shop catalog search, checkout, order tracking, returns.

Generate ideas via named methods from creative practice.

Neutral arbiter for merge conflicts between two agents.

ASCII art: pyfiglet, cowsay, boxes, image-to-ascii.

AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.

Generate images, video, and audio via diffusion workflows.

Turn a handwriting photo into an installable TTF font.

Hand-drawn Excalidraw JSON diagrams (arch, flow, seq).

HeartMuLa: Suno-like song generation from lyrics + tags.

Frontend design guidance, upstream-maintained (impeccable).

Build creative browser demos with DOM-free text layout.

Rewrite text to ASD-STE100 Simplified Technical English.

Throwaway HTML mockups: 2-3 design variants to compare.

Plan multi-platform social campaigns: briefs to posting.

Drive and script tldraw offline canvases with an agent.

Control TouchDesigner via twozero MCP.

Automate Unreal Engine editor scenes, actors, and renders.

Iterative Python via live Jupyter kernel (hamelnb).

Set up Actual Computer (actual.inc) inference in Hermes.

Generate a bash wizard guiding a human through manual setup.

Query Polymarket: markets, prices, orderbooks, history.

Manual OAuth for remote MCP servers on headless gateways.

Run PyTorch training across GPUs with minimal changes.

lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).

W&B: log ML experiments, sweeps, model registry, dashboards.

Speed up long-sequence transformer training and inference.

llama.cpp local GGUF inference + HF Hub model discovery.

vLLM: high-throughput LLM serving, OpenAI API, quantization.

On-demand GPU cloud instances for ML training.

Serverless GPU cloud for ML jobs and model APIs.

HuggingFace hf CLI: search/download/upload models, datasets.

SAM: zero-shot image segmentation via points, boxes, masks.

Fine-tune large LLMs with LoRA on limited GPU memory.

分享 drawio-chart Skill 的设计思路、安装方式和使用流程，说明为什么技术文章配图更适合保留 draw.io 源文件，以及如何让 Agent 生成可维护的流程图、架构图和模块关系图。

Use only when the user explicitly requests a review or audit of backend code under `api/`. Supports pending-change, file-focused, and pasted-diff reviews. Do not use for implementation-only requests, diagnosis without review intent, frontend code, or backend code outside `api/`.

Refactor high-complexity React components in Dify frontend. Use when `pnpm analyze-component --json` shows complexity > 50 or lineCount > 300, when the user asks for code splitting, hook extraction, or complexity reduction, or when `pnpm analyze-component` warns to refactor before testing; avoid for simple/well-structured components, third-party wrappers, or when the user explicitly wants testing without refactoring.

Use when writing, changing, or reviewing Cucumber and Playwright tests under `e2e/`, including feature files, step definitions, support code, scenario tags, locators, and assertions. Do not use for Vitest, React Testing Library, backend tests, or generic browser automation outside the E2E suite.

Use only when the user explicitly requests a review or audit of frontend code under `web/` or `packages/dify-ui/`. Supports pending-change, file-focused, and pasted-diff reviews. Do not use for implementation-only requests, diagnosis without review intent, or backend-only code.

Use when writing or changing Vitest or React Testing Library tests under `web/` or `packages/dify-ui/`, or when the user explicitly requests frontend test strategy, including evaluation of an existing strategy. Do not use for frontend code-review-only requests, general testability discussion, Python tests, or Cucumber/Playwright E2E.

Use when implementing or refactoring React/TypeScript components and the task requires decisions about component ownership, feature boundaries, state, data flow, effects, or interaction ownership. Do not use for review-only requests, test-only work, copy-only edits, or styling-only changes.

Lightweight coding guardrails for making focused, simple, and verifiable changes in this repo. Use for all coding work.

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.

Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.

This skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs guidance on hookify rule syntax and patterns.

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.

This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.

This skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin state files", "read YAML frontmatter", "per-project plugin settings", or wants to make plugin behavior configurable. Documents the .claude/plugin-name.local.md pattern for storing plugin-specific configuration with YAML frontmatter and markdown content.

This skill should be used when the user asks to "create a plugin", "scaffold a plugin", "understand plugin structure", "organize plugin components", "set up plugin.json", "use ${CLAUDE_PLUGIN_ROOT}", "add commands/agents/skills/hooks", "configure auto-discovery", or needs guidance on plugin directory layout, manifest configuration, component organization, file naming conventions, or Claude Code plugin architecture best practices.

This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.

>