majiayu000/claude-skill-registry - Seite 18

dspy-rag-pipeline

This skill should be used when the user asks to "build a RAG pipeline", "create retrieval augmented generation", "use ColBERTv2 in DSPy", "set up a retriever in DSPy", mentions "RAG with DSPy", "context retrieval", "multi-hop RAG", or needs to build a DSPy…

Quellsprache: Englisch

dspy-signature-designer

This skill should be used when the user asks to "create a DSPy signature", "define inputs and outputs", "design a signature", "use InputField or OutputField", "add type hints to DSPy", mentions "signature class", "type-safe DSPy", "Pydantic models in DSPy",…

Quellsprache: Englisch

dspy-simba-optimizer

This skill should be used when the user asks to "optimize with SIMBA", "use Bayesian optimization", "optimize agents with custom feedback", mentions "SIMBA optimizer", "mini-batch optimization", "statistical optimization", "lightweight optimizer", or needs an…

Quellsprache: Englisch

dspy

Compile prompts into self-improving pipelines with signatures, modules, optimizers, and programmatic prompt engineering

Quellsprache: Englisch

effect-ai

This skill should be used when the user asks about "Effect AI", "@effect/ai", "LLM integration", "AI tool use", "AI execution planning", "building AI agents", "AI providers", "structured AI output", "AI completions", "Effect OpenAI", "Effect Anthropic", or…

Quellsprache: Englisch

effect-ts-ai

@effect/ai integration patterns for categorical AI composition, typed error handling, and production prompt pipelines. Use when building AI applications with Effect-TS, composing LLM calls with typed errors, creating tool-augmented AI systems, or integrating…

Quellsprache: Englisch

effective-prompting

Master effective prompting techniques for Claude Code. Use when learning prompt patterns, improving task descriptions, optimizing Claude interactions, or troubleshooting why Claude misunderstood a request. Covers @ mentions, thinking keywords, task framing,…

Quellsprache: Englisch

elevenlabs-agents

ElevenLabs Agents Platform for AI voice agents (React/JS/Native/Swift). Use for voice AI, RAG, tools, or encountering package deprecation, audio cutoff, CSP violations, webhook auth failures.

Quellsprache: Englisch

elevenlabs-remotion

Generate professional voiceovers using ElevenLabs AI. Use when the user needs to create voiceovers for videos, audio narration, or text-to-speech content. Supports multiple voices with character presets (narrator, salesperson, expert) for natural delivery.…

Quellsprache: Englisch

emotional-stakes

Use when writing subagent prompts, skill instructions, or any high-stakes task requiring accuracy and truthfulness

Quellsprache: Englisch

engine-superpower-profiling

Profile AI engine superpowers and capability boundaries.

Quellsprache: Englisch

enhancer

Transform simple prompts into comprehensive, context-aware prompts. Use for prompt enhancement, requirements analysis, and implementation strategy. Includes Context7 prompt engineering guides lookup.

Quellsprache: Englisch

eureka-context-engineering-v6-1

Complete Eureka V6.1 Context Engineering suite with observability, structured output, and hybrid memory

Quellsprache: Englisch

eval-frameworks

Evaluation framework patterns for RAG and LLMs, including faithfulness metrics, synthetic dataset generation, and LLM-as-a-judge patterns. Triggers: ragas, deepeval, llm-eval, faithfulness, hallucination-check, synthetic-data.

Quellsprache: Englisch

eval-gap-finder

Find AILANG vs Python eval gaps and improve prompts/language. Use when user says 'find eval gaps', 'analyze benchmark failures', 'close Python-AILANG gap', or after running evals.

Quellsprache: Englisch

eval-runner

Run eval scenarios to benchmark Mycelium effectiveness. Execute tasks using reflexion loop, validate against success criteria, record metrics.

Quellsprache: Englisch

exa-research

Use Exa AI for neural search, content retrieval, and automated deep research. Requires EXA_API_KEY.

Quellsprache: Englisch

prompt-exec

Execute the forged prompt exactly as written, with no reinterpretation. Requires explicit user consent and a ready prompt artifact on disk. Deletes the canonical prompt after successful execution.

Quellsprache: Englisch

experience-library

Capture task outcomes, score performance, and derive rules as token priors for continual learning without model weight changes. Use for post-task feedback, experience capture, pattern extraction, and learning from mistakes. Achieves continual learning for $18…

Quellsprache: Englisch

extended-thinking

Extended thinking (ultrathink) configuration for Claude API. Activate for complex reasoning tasks, deep analysis, multi-step problem solving, and tasks requiring careful deliberation. Enables Claude's internal reasoning with configurable thinking budgets.

Quellsprache: Englisch

faion-audio-skill

""

Quellsprache: Englisch

faion-claude-api-skill

""

Quellsprache: Englisch

faion-gemini-api-skill

""

Quellsprache: Englisch

faion-image-gen-skill

""

Quellsprache: Englisch

faion-langchain-skill

""

Quellsprache: Englisch

faion-llamaindex-skill

""

Quellsprache: Englisch

faion-llm-integration

LLM APIs: OpenAI, Claude, Gemini, local LLMs, prompt engineering, function calling.

Quellsprache: Englisch

faion-openai-api-skill

""

Quellsprache: Englisch

fastmcp-creator

Build Model Context Protocol (MCP) servers - comprehensive coverage of generic MCP protocol AND FastMCP framework specialization. Use when creating any MCP server (Python FastMCP preferred, TypeScript/Node also covered). Includes agent-centric design…

Quellsprache: Englisch

fastmcp-patterns

FastMCP server patterns for building MCP servers. Use when implementing MCP tools, resources, or server configuration.

Quellsprache: Englisch

fastmcp

FastMCP Python framework for MCP servers with tools, resources, storage backends (memory/disk/Redis/DynamoDB). Use for Claude tool exposure, OAuth Proxy, cloud deployment, or encountering storage, lifespan, middleware, circular import, async errors.

Quellsprache: Englisch

few-shot-examples

Curated few-shot examples for construction AI tasks: classification, extraction, analysis. Domain-specific examples for improved LLM performance.

Quellsprache: Englisch

few-shot-learning-patterns

Few-Shot Learning（少数例示学習）のパターンとベストプラクティスを提供するスキル。効果的な例示の設計、構造化、配置により、AIの出力品質を大幅に向上させます。 • The Pragmatic Programmer / 適用: 例示パターン設計の品質基準 / 目的: 実践的改善と一貫性維持 • Few-Shot戦略 / 適用: 段階的複雑度設計と最適shot数決定 / 目的: AIの学習効率最大化 Trigger: Use when you need to design effective…

Quellsprache: Japanisch

fine-tuning-customization

LLM fine-tuning with LoRA, QLoRA, DPO alignment, and synthetic data generation. Efficient training, preference learning, data creation. Use when customizing models for specific domains.

Quellsprache: Englisch

fluff-detector

Detect human-oriented content in LLM artifacts. Flags attribution, personas, redundant explanations, marketing language, and decorative elements that waste tokens without improving LLM behavior.

Quellsprache: Englisch

prompt-forge

Shape, refine, and stabilize human intent into a canonical prompt artifact without executing anything. Iteratively clarifies ambiguity and contradictions until the user explicitly confirms readiness.

Quellsprache: Englisch

foundation-models

Apple Foundation Models framework for on-device AI, @Generable macro, guided generation, tool calling, and streaming. Use when user asks about on-device AI, Apple Intelligence, Foundation Models, @Generable, LLM, or local machine learning.

Quellsprache: Englisch

friction-detector

Detect friction signals; graduate patterns into rules. Use for session retrospectives.

Quellsprache: Englisch

full-interview

Force full interview depth for this session. Use when user says '/full-interview' or 'full interview mode'.

Quellsprache: Englisch

function-calling

LLM function calling and tool use patterns. Use when enabling LLMs to call external tools, defining tool schemas, implementing tool execution loops, or getting structured output from LLMs.

Quellsprache: Englisch