Claude Code Skills · page 2

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

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.

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.

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework

Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.

Outlines: structured JSON/regex/Pydantic LLM generation.

Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library

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.

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.

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.

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.

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 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.

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.

>

Review backend code for quality, security, maintainability, and best practices based on established checklist rules. Use when the user requests a review, analysis, or improvement of backend files (e.g., `.py`) under the `api/` directory. Do NOT use for frontend files (e.g., `.tsx`, `.ts`, `.js`). Supports pending-change review, code snippets review, and file-focused review.

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.

Write, update, or review Dify end-to-end tests under `e2e/` that use Cucumber, Gherkin, and Playwright. Use when the task involves `.feature` files, `features/step-definitions/`, `features/support/`, `DifyWorld`, scenario tags, locator/assertion choices, or E2E testing best practices for this repository.

Review Dify frontend code for correctness, accessibility, component design, dify-ui usage, data/query boundaries, performance, and tests. Trigger for `.tsx`, `.ts`, `.js`, UI, React, Next.js, pending-change, or focused frontend review requests.

Generate Vitest + React Testing Library tests for Dify frontend components, hooks, and utilities. Triggers on testing, spec files, coverage, Vitest, RTL, unit tests, integration tests, or write/review test requests.

React/TypeScript component style guide. Use when writing, refactoring, or reviewing React components, especially around props typing, state boundaries, shared local state with Jotai atoms, API types, query/mutation contracts, navigation, memoization, wrappers, and empty-state handling.

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.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

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.

Add documentation for a new AI provider — usage docs, env vars, Docker config, image resources.

Add server-side environment variables that control default values for user settings.

Agent runtime lifecycle hooks. Use for before/after tool or step hooks, tool mocks, human intervention, sub-agent calls, context compression, evals, tracing, callAgent, or lifecycle events.

Build or extend LobeHub Agent Signal pipelines. Use for signal sources, signal/action types, policies, middleware, workflow handoff, dedupe, scope behavior, or observability.

Agent tracing CLI for execution snapshots. Use for agent-tracing, traces, snapshots, LLM call inspection, context engine data, agent step analysis, or execution debugging.

Build LobeHub builtin tool packages. Use when adding agent-callable tools, manifests, executors, runtimes, inspectors, renders, placeholders, streaming, interventions, portals, or tool registries.

Build multi-platform chat bots with the chat SDK. Use for Slack, Teams, Google Chat, Discord, GitHub, Linear bots, webhooks, mentions, slash commands, cards, modals, or streaming responses.

>

LobeHub CLI (@lobehub/cli) development guide — commands, subcommands, architecture.

LobeHub data-fetching pipeline guide. Use for service layer, Zustand store, SWR, lambdaClient, useClientDataSWR, useFetchXxx hooks, or migrating useEffect fetches.

Use for Drizzle migrations: schema/table/column changes, migration generation or regeneration, sequence conflicts after rebase, idempotent SQL review, or migration renames.

LobeHub debug package and log namespace guide. Use when adding debug() logging, choosing lobe-* namespaces, troubleshooting DEBUG output, localStorage.debug, or log format specifiers.

Electron desktop development guide — IPC handlers, controllers, preload scripts, window/menu management.

Write website changelog pages under docs/changelog/*.mdx. Use for EN/ZH product update posts, changelog posts, update-log copy, or docs changelog edits; not GitHub Release notes.

LobeHub Drizzle ORM schema and query style. Use for pgTable schemas, indexes, joins, inferred types, db.select/db.query, schema fields, foreign keys, junction tables, or postgres query patterns.

Implement or debug LobeHub heterogeneous agents. Use for Claude Code/Codex adapters, external CLI agents, event mapping, IPC, persistence, tool-call chains, sessions, traces, or adapter bugs.

Add or edit LobeHub keyboard shortcuts. Use for HotkeyEnum, HOTKEYS_REGISTRATION, combineKeys, useHotkeyById, tooltip hotkeys, shortcut scope, conflicts, or Cmd/Ctrl key combos.

LobeHub i18n with react-i18next. Use for user-facing strings, locale keys, namespaces, useTranslation, t(), interpolation, zh-CN/en-US previews, hardcoded UI copy, or pnpm i18n.

Linear issue management. Use for LOBE-xxx issues, Linear links, PRs referencing Linear, retrieving issues, updating status, completion comments, or sub-issue trees.

>

UI copy and microcopy guidelines. Use for user-facing copy, buttons, errors, empty states, onboarding, i18n wording, translation, or copy improvements in Chinese or English.

LobeHub imperative modal conventions. Use when creating or migrating modals, dialogs, popups, confirm flows, ModalHost wiring, createModal, confirmModal, useModalContext, or base-ui modal APIs.

Create a PR for the current branch (targets `canary` by default), including splitting one cross-layer branch into ordered stacked PRs so a lower layer (db / shared package / server TRPC) merges before its callers (desktop / CLI / UI). Use when the user asks to create / submit a PR, or to split a branch because clients call a server contract that isn't on the trunk yet. Triggers on 'pr', 'create pr', 'submit pr', 'open a PR', 'pull request', 'split this PR', 'stacked PR', 'backend should merge first', '提 PR', '提个 PR', '新建 PR', '拆 PR', '后端先合', '分层合并'.

LobeHub open-source monorepo architecture map. Use when locating code layers, understanding apps/packages/src layout, business stubs, project structure, or onboarding to the repository.

LobeHub React component conventions. Use when editing TSX UI, choosing base-ui vs @lobehub/ui vs antd, styling with antd-style, routing, desktop variants, layouts, or component state.

OpenResponses API compliance testing. Use for Response API endpoint tests, compliance runs, schema debugging, response api test, or openresponses test tasks.

LobeHub code review checklist. Use when reviewing a PR, diff, or branch for console leftovers, return await, secrets, i18n, desktop router drift, UI imports, migrations, or cloud impact.

Audit .agents/skills SKILL.md files. Use for recurring checks of duplicate, overlapping, stale, inconsistent, or broken skills and merge/delete candidates.

LobeHub SPA route architecture. Use when editing src/routes, src/features delegation, desktop/mobile/popup router configs, .desktop variants, route segments, redirects, or new pages.

LobeHub Zustand store data-shape patterns. Use when designing store state, list/detail splits, normalized maps, reducers, messagesMap, topicsMap, or choosing shared type sources.

Vitest testing guide. Use when writing or updating tests, fixing failing tests, improving coverage, debugging test issues, or setting up mocks.

TRPC router development guide. Use when creating or modifying apps/server/src/routers, adding procedures, or implementing server-side API endpoints.

LobeHub TypeScript style and type-safety guide. Use when editing TS/TSX/MTS, fixing types, choosing interface vs type, avoiding any/object, import type, async flow, or ts-expect-error.

LobeHub Upstash Workflow and QStash guide. Use for async workflows, process/paginate/execute fan-out, serve handlers, context.run/call/sleep, or workflow triggers.

Version release workflow — release process and GitHub Release notes (not docs/changelog pages).

LobeHub Zustand store conventions. Use when editing src/store, store slices, public/internal actions, dispatch actions, flattenActions, optimistic updates, selectors, maps, or class action migration.

Backfill and maintain model-bank metadata (knowledgeCutoff, family, generation). Use when adding models, fixing cutoff/family data, running a metadata sweep across aiModels providers, or researching official knowledge cutoffs.

>

This skill should be used when the user asks to "test a cross-repo feature", "deploy a feature branch to staging", "test SDK against OH Cloud", "e2e test a cloud workspace feature", "test provider tokens", "test secrets inheritance", or when changes span the SDK and OpenHands server repos and need end-to-end validation against a staging deployment.

This skill should be used when the user asks to "generate release notes", "list upcoming release PRs", "summarize upcoming release", "/upcoming-release", or needs to know what changes are part of an upcoming release.

This skill should be used when the user asks to "update SDK", "bump SDK version", "pin SDK to a commit", "test unreleased SDK", "update agent-server image", "bump the version", "prepare a release", "what files change for a release", or needs to know how SDK packages are managed in the OpenHands repository. For detailed reference material, see references/docker-image-locations.md and references/sdk-pinning-examples.md in this skill directory.

|

Perform thorough code reviews with security, performance, and maintainability analysis. Use when user asks to review code, check for bugs, or audit a codebase.