14,252 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
Skill Claude CodeCodex
You are an expert at building applications with the Anthropic Claude API. Help the user write correct, idiomatic code using the latest API patterns and SDK conventions.
Skill Claude CodeCodex
Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports anthropic/@anthropic-ai/sdk; user asks for…
orlando-japan/claude-code-setting
Skill Claude CodeCodex
Maximize cache hit rate on Claude API calls to cut latency and cost. Invoke when building or optimizing a production Claude-powered feature.
Skill Claude CodeCodex
Compile a natural-language spec into a tiny neural function that runs locally with ProgramAsWeights (PAW). Use it for fuzzy text-in / text-out tasks that a regex can't handle but that are too slow, costly, or overkill to send to a full LLM on every item - classify, categorize, label, or tag text (sentiment, urgency…
Plugin Claude Code
Bundles 2 skills, 2 hooks · 55 tokens together
GEOS-authoring plugin: geos-rag MCP + XML self-verification Stop hook.
Skill Claude CodeCodex
Engineers LLM applications: fixing bad output (prompting, RAG, finetuning), evals and LLM judges, agents and tools, guardrails, and production monitoring. Use when building or debugging an app on top of an LLM.
Skill Claude CodeCodex
Build and deploy methodology-aware data agents on Trino/Iceberg with structured reasoning, MLflow tracing, and 7-dimension evaluation — guided by settled decisions and requirements recorded in the RAC corpus.
Agent Claude Code
Use when selecting, benchmarking, or tuning Ollama models on constrained edge hardware; analysing LLM inference performance and context window behaviour; designing or evaluating prompt injection detection approaches; or producing model research documentation. Produces research notes, configuration recommendations, and…
Skill Claude CodeCodex
Use when a RAG request needs bounded multi-round evidence gathering with Critic-based sufficiency checks before returning an answer.
Skill Claude CodeCodex
Offload data transformation, parsing, validation, encoding, and formatting tasks to pre-built tools. One call with a task description and your data, get the result back. No search step, no reasoning about which tool to use. Covers data normalization, format conversion, parsing, validation, batch processing, mock data…
Skill Claude CodeCodex
Checks a prompt before running it: scores prompt quality and suggests an improved version, then recommends the ideal Claude model, /effort level, and which skills/tools will be used. Use when you want to improve your prompt and plan the run configuration — type /prompt-check followed by your prompt.
Skill Claude CodeCodex
Prompt builder and improver: turns a short request (2-3 words) or a fully spelled-out request into a ready-to-use prompt — for LLM tasks (analysis, writing), for image/video generation (Midjourney, DALL-E, Stable Diffusion, Sora, Runway), or for agentic/coding tasks (Claude Code, Cursor). Automatically detects the…
openvino-dev-samples/local-ai-skill-authoring
Skill Claude CodeCodex
Author, scaffold, review, or debug a "local AI skill" — a self-contained package that runs an AI model locally (on Windows via OpenVINO, or any local runtime) and exposes it to a Host application (Marvis, WorkBuddy, or any custom host) through a single entry script. Use this skill when the user, in Chinese or English…
Skill Claude CodeCodex
Deep learning and algorithm tutor that generates rigorous, structured tutorials combining mathematical theory with hands-on Python implementation. Use this skill whenever the user asks to learn, study, or get a tutorial on ANY technical topic — algorithms (PPO, DDPM, Transformer, DQN, SAC, etc.), ML/DL concepts…
mikel063093/kmp-quality-skills
Skill Claude CodeCodex
Guides implementation of on-device AI inference using Gemini Nano (Android), ONNX Runtime (Android/KMP), CoreML and Vision framework (iOS). Covers model management, execution provider selection, INT4 quantization, 3-tier fallback strategy (device → on-device model → cloud), model warm-up, and inference profiling.
Plugin Claude Code
Bundles 7 skills · 124 tokens together
Agentic data analysis swarm — ingest, clean, profile, analyze, visualize, report, and build interactive dashboards from CSV/Excel/JSON data. A multi-agent pipeline with specialized data-engineer, statistician, visualizer, reporter, and strategist agents coordinated by an orchestrator.
DongYang26/cc-academic-style-coding
Skill Claude Code
Implement, debug, run, and reproduce ML/AI paper experiments in research repositories. Use when working on PyTorch training or evaluation pipelines, baselines, ablations, dataset pipelines, environment or GPU setup, tensor-shape debugging, result export, or experiment cleanup.
Plugin Claude Code
Bundles 9 skills, 5 hooks, 1 MCP server · 1,459 tokens together
Prompt-engineering toolkit. Discover evidence, critique and visually validate plans, compile finite project graphs, run bounded goal-directed graph execution to evidence-backed convergence, and review results.
Plugin Claude Code
Bundles 2 skills, 2 commands, 2 agents · 147 tokens together
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
chang9852/role-prompt-designer
Skill Claude CodeCodex
Design and generate AI Agent role/personality definitions using the SOUL/IDENTITY/AGENTS three-layer prompt architecture. Use when: (1) Creating a new AI Agent persona from scratch, (2) Writing or editing SOUL.md, IDENTITY.md, or AGENTS.md files, (3) Designing role prompts for AI assistants, chatbots, or autonomous…
Skill Claude Code
Use when writing code in an app that does semantic search, RAG, or ingests documents into a vector database on the platform — running nearest-neighbor queries, listing/adding/removing documents, or feeding retrieved chunks into an LLM. Covers VectorDatabaseQuery(), ListDocumentsInVectorDatabase()…
Cursor rule Cursor
Details Flax NNX lifted transforms (nnx.jit, nnx.grad, nnx.vmap, nnx.scan) for applying JAX transformations directly to nnx.Module methods.
Cursor rule Cursor needs its repo
Semantic search over the project knowledge base via the zvec CLI.
jxjwilliam/jinyong-finetune-qlora
Cursor rule Cursor
AutoDL (autodl.com) cloud GPU workflow for QLoRA fine-tuning Jin Yong style.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: