Browse Skills

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.

OpenAI Codex CLI wrapper — three modes. (gstack)

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

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.

Produce a world-class single-page editorial landing site in the Atelier Zero visual language (Monocle / Apartamento / Études editorial collage) — the same aesthetic Open Design uses for its own marketing surface. The agent fills a typed `inputs.json` from a brand brief, optionally generates 16 collage assets via gpt-image-2, then runs a pure-function composer that emits a self-contained HTML file; a separate path can mirror the Astro marketing site in `apps/landing-page/`. Drop-in scroll-reveal motion and a Headroom-style sticky nav are wired automatically.

Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/mask, background removal or replacement, transparent background, product shots, concept art, covers, or batch variants); run the bundled CLI (`scripts/image_gen.py`) and require `OPENAI_API_KEY` for live calls.

PostgreSQL-based semantic and hybrid search with pgvector and ParadeDB. Use when implementing vector search, semantic search, hybrid search, or full-text search in PostgreSQL. Covers pgvector setup, indexing (HNSW, IVFFlat), hybrid search (FTS + BM25 + RRF), ParadeDB as Elasticsearch alternative, and re-ranking with Cohere/cross-encoders. Supports vector(1536) and halfvec(3072) types for OpenAI embeddings. Triggers: pgvector, vector search, semantic search, hybrid search, embedding search, PostgreSQL RAG, BM25, RRF, HNSW index, similarity search, ParadeDB, pg_search, reranking, Cohere rerank, pg_trgm, trigram, fuzzy search, LIKE, ILIKE, autocomplete, typo tolerance, fuzzystrmatch

Expert PR and media relations guidance for earned media, press coverage, and reputation building. Use when writing press releases, crafting media pitches, developing journalist relationships, planning embargo strategies, managing crisis communication, placing thought leadership, building analyst relations, submitting award applications, or measuring PR coverage. Use for media outreach, press kits, speaking opportunities, and earned media strategy.

Karpathy's LLM Wiki: build/query interlinked markdown KB.

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

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

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

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

Build, test, inspect, install, and deploy MCP servers with FastMCP in Python. Use when creating a new MCP server, wrapping an API or database as MCP tools, exposing resources or prompts, or preparing a FastMCP server for Claude Code, Cursor, or HTTP deployment.

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

Create pull requests for ant-design using the repository's official PR templates. Use this skill when the user asks to create/open a PR, draft PR title/body, summarize branch changes for a PR, or otherwise prepare PR content. Judge by intent rather than fixed phrases; short colloquial requests still count if they are about creating a PR rather than discussing PR concepts.

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

Real-time communication patterns for live updates, collaboration, and presence. Use when building chat applications, collaborative tools, live dashboards, or streaming interfaces (LLM responses, metrics). Covers SSE (server-sent events for one-way streams), WebSocket (bidirectional communication), WebRTC (peer-to-peer video/audio), CRDTs (Yjs, Automerge for conflict-free collaboration), presence patterns, offline sync, and scaling strategies. Supports Python, Rust, Go, and TypeScript.

Transform Claude Code into an AI Scientist that orchestrates research workflows using tree-based hypothesis exploration. Triggers on "research project", "scientific experiment", "run experiments", "AI scientist", "tree search experimentation", "systematic study".

Implement cost-optimized LLM routing with NO OpenAI. Use tiered model selection (DeepSeek, Haiku, Sonnet) to achieve 70-90% cost savings. Triggers on "LLM costs", "model selection", "cost optimization", "which model", "DeepSeek", "Claude pricing", "reduce AI costs".