Каталог навыков агентов

Soul-Bound Keys and Soulchain for persistent agent identity, reputation, and messaging. The identity primitive for the a...

Mine Sponsored Products search terms end-to-end via the Amazon Ads MCP: generate the SP Search Term report via allv1_Ads...

Builds generative AI applications on Amazon Bedrock. Covers model invocation (Converse API, InvokeModel), RAG with Knowl...

按关键词批量下载 Amazon 搜索结果页产品图，多关键词自动分文件夹存储

Reference system prompt and tool schemas for Amp. Use when imitating, comparing, or analyzing Amp's prompting style; des...

Collaborative spec workflow between two agents. Use when the user says "spec", "design with", "collaborative spec", "spe...

Operate and troubleshoot the AMS unified MCP server for roadmap learning, GSD project orchestration, task management, AC...

Compara densidade de tropos do romance com benchmarks de genero e sugere rotas de subversao criativa preservando a agenc...

Analyze a reference video and reverse-engineer its style into a reusable Seedance 2.0 prompting template for the Novoads...

競合分析パイプラインのオーケストレーター。competitive-tracker → market-intelligence-scanner → priority-analyzer を 順次呼び出して「次に何を作るべきか?」に対するデータ駆...

Use to explain a codegen eval result under evals/codegen/.runs/: why an attempt lost points, the root cause, and what to...

Andrej Karpathy的思维框架与表达方式。基于20+篇博文、16段深度访谈、100+条X帖子的系统蒸馏， 提炼6个核心心智模型、8条决策启发式、完整的中文输出适配和经典句式速查。 用途：作为思维顾问，用Karpathy的视角分析A...

Embody Andrew Ng - AI persona expert with integrated methodology skills

Anfechtungsklage gegen rechtswidrige belastende Verwaltungsakte. Klagebefugnis § 42 VwGO, Vorverfahren § 68 VwGO, Klagef...

Animate one supplied still into a short video with bounded subject and camera motion while preserving identity and compo...

Drive Animato (github.com/otdnnc/Animato) as an API-key agent loop that turns a rigged .fbx/.gltf model plus a plain-tex...

Use this agent when you need to systematically review existing GO annotations for a gene and make curation decisions bas...

Draft, preview, and explicitly send an Egregore group announcement. Use for /announce, telling the team something, or no...

Anomaly and outlier detection using Isolation Forest, One-Class SVM, autoencoders, and statistical methods. Activates fo...

Multi-perspective reasoning through cognitive voices

Reference system prompt and tool schemas for Anthropic. Use when imitating, comparing, or analyzing Anthropic's promptin...

Optimization guidelines for Claude 3.5 Sonnet, Claude 3.5 Haiku, and Opus.

Anthropic Claude API for AI models with tool use and extended context.

Call Anthropic Messages API (Claude) with a prompt

Master Anthropic's prompt engineering techniques to generate new prompts or improve existing ones using best practices f...

Guide for Anthropic Python/TypeScript SDK usage including messages API, streaming, prompt caching, batches, token counti...

All official Claude skills from anthropics/skills.

Prevents order-gap hallucination — where the model detects a false premise when asked directly but misses it when embedd...

Hierarchical coordination and drift detection with frequent checkpoints, shared memory coherence validation, role specia...

Complete methodology for preventing AI hallucinations. Use when accuracy is critical and you need Claude to verify befor...

Prevents suggesting non-existent packages, fabricated library names, and invalid version pins. Also guards against typos...

Edit formulaic or AI-sounding prose while preserving the author's voice. Use for an anti-slop pass, editorial review, or...

---name: antibody-design-agent

A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns,...

Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and...

Build container-based Foundry Agents with Azure AI Projects SDK (ImageBasedHostedAgentDefinition). Use when creating hos...

Autonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct w...

X-ray any AI model's behavioral patterns — refusal boundaries, hallucination tendencies, reasoning style, formatting def...

Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywor...

Design and evaluate compression strategies for long-running sessions

Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and in...

Expert data scientist for advanced analytics, machine learning, and statistical modeling. Handles complex data analysis,...

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

AI-powered image editing with style transfer and object removal

Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, impo...

Generate images using Antigravity AI image generation models.

This skill generates images using Google Gemini's image generation model (gemini-3-pro-image-preview). It enables seamle...

Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLM...

Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmar...

Design short-term, long-term, and graph-based memory architectures

Build comprehensive ML pipelines, experiment tracking, and model registries with MLflow, Kubeflow, and modern MLOps tool...

Conselho de especialistas — consulta multiplos agentes do ecossistema em paralelo para analise multi-perspectiva de qual...

Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Genera...

Expert prompt engineer specializing in advanced prompting techniques, LLM optimization, and AI system design. Masters ch...

Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates,...

Scanpy is a scalable Python toolkit for analyzing single-cell RNA-seq data, built on AnnData. Apply this skill for compl...

A meta-skill that understands task requirements, dynamically selects appropriate skills, tracks successful skill combina...

Use when executing implementation plans with independent tasks in the current session

Protocolo de Inteligência Pré-Tarefa — ativa TODOS os agentes relevantes do ecossistema ANTES de executar qualquer taref...

Build tools that agents can use effectively, including architectural reduction patterns

FREE — Intelligent tool-call reliability wrapper. Monitors, retries, fixes, and learns from tool failures. Auto-recovers...

Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't j...

Sub-skill técnica de Yann LeCun. Cobre CNNs, LeNet, backpropagation, JEPA (I-JEPA, V-JEPA, MC-JEPA), AMI (Advanced Machi...

Mobile layout skill for antislop. Use for layouts that reflow on small screens: grids, overflow, tap targets. Load with...

Mobile layout skill for antislop. Use for layouts that reflow across screen sizes, phone to desktop: grids, overflow, ta...

Motion capture for any creature from one AI video, with the anymove repo. A video model films a rigged 3D creature from...

Turn a two-camera AI clip into a game-ready animation with anymove - read every joint with the creature's trained reader...

Make the two-camera AI clip for an anymove creature - write the move's prompt from creature.json, send the reference fra...

Train and use a MiniMax H3 image-to-video LoRA on fal that keeps anymove's two-camera layout - split screen held, limb c...

Train the joint reader for one anymove creature - render about 2,200 random poses from both layout cameras with every jo...

Set up a new creature for anymove - get a textured mesh, scale and face it, place its skeleton in rig.json with grid vie...

Aphorism management. USE WHEN aphorism, quote, saying. SkillSearch('aphorisms') for docs.

API SPEC

CRITICAL: API agents wrap external HTTP services. They use request/response transforms to adapt between Orchestrator AI'...

Official Anthropic SDK patterns for TypeScript/Node.js — client setup, Messages API, streaming, tool use, vision, extend...

Image understanding and document analysis with Claude's multimodal capabilities -- image input formats, PDF processing,...

Official Cohere TypeScript SDK patterns -- CohereClientV2, chat, embeddings, rerank, RAG with citations, tool use, strea...

ElevenLabs voice AI SDK patterns for TypeScript/Node.js -- text-to-speech, streaming, voice cloning, speech-to-speech, p...

LangChain.js patterns for building LLM applications — chat models, LCEL chains, prompt templates, structured output, age...

LLM observability with Langfuse — OpenTelemetry-based tracing, evaluations, prompt management, datasets, and production...

LiteLLM proxy server setup, TypeScript client patterns via OpenAI SDK, model routing, fallbacks, load balancing, spend t...

LlamaIndex.TS data framework for RAG, indexing, retrieval, query engines, chat engines, and agentic workflows in TypeScr...

Official Mistral AI TypeScript SDK patterns — client setup, chat completions, streaming, function calling, structured ou...

Serverless GPU compute platform for AI model deployment — web endpoints, GPU functions, model serving, and TypeScript cl...

Local LLM inference with the Ollama JavaScript client -- chat, streaming, tool calling, vision, embeddings, structured o...

Official OpenAI SDK patterns for TypeScript/Node.js — client setup, Chat Completions, Responses API, streaming, structur...

Speech-to-text transcription and translation via OpenAI Audio API -- models, response formats, timestamps, prompting, st...

Testing and evaluation framework for LLM prompts and applications -- promptfooconfig.yaml, assertions, model-graded eval...

Replicate SDK patterns for TypeScript/Node.js -- client setup, predictions, streaming, webhooks, file handling, model ve...

Together AI SDK patterns for TypeScript — client setup, chat completions, streaming, structured output, function calling...

Vercel AI SDK patterns - providers, text generation, streaming, structured output, tool calling, chat UI hooks, embeddin...

Use when the owner asks what their Claude Code use would cost on the API, wants an API shadow bill or cost card for a ti...

How OpenAPI specs are linted in this repo. Use when diagnosing a `bundleSpec` failure or understanding what rules the to...

Use this before implementing features involving third-party platforms, APIs, comments, account login, posting, scraping,...

Wire an AI agent to live e-commerce product data using Apify's E-commerce Scraping Tool over MCP, either as runtime tool...

Main application building orchestrator. Creates full-stack applications from natural language requests. Determines proje...