home/categories/llm-ai

category focus

LLM & AI

Large Language Models and AI agents.

4725 skillsall categories

sorting

stars

current ordering strategy

query

all entries

refine the visible subset

llm-ai

prompt-engineering

Techniques for writing effective LLM prompts. Use when crafting system prompts, optimizing agent instructions, or improving model outputs.

lbussell

data-ai

open

llm-ai

wandb-plot

Shared skill entrypoint for Claude Code. See the canonical skill file at: wandb-plot/SKILL.md

RubenBranco

data-ai

open

llm-ai

multi-ai-orchestrator

Ollama-based multi-AI model orchestration with auto-profiling, smart routing, and ensemble execution

ljchg12-hue

data-ai

open

llm-ai

performance-analysis

Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms

adebold

data-ai

open

llm-ai

For complex problems where user context is insufficient, systematically elicit information through adaptive prompt patterns. Combines five complementary patterns (Flipped Interaction, Cognitive Verifier, Question Refinement, Reflection, Context Manager) to clarify requirements, verify understanding, and manage context dynamically.

t-chito

data-ai

open

llm-ai

llamaindex-patterns

LlamaIndex implementation patterns with templates, scripts, and examples for building RAG applications. Use when implementing LlamaIndex, building RAG pipelines, creating vector indices, setting up query engines, implementing chat engines, integrating LlamaCloud, or when user mentions LlamaIndex, RAG, VectorStoreIndex, document indexing, semantic search, or question answering systems.

vanman2024

data-ai

open

llm-ai

multi-ai

Start the multi-AI pipeline with a given request. Cleans up old task files and guides through plan → review → implement → review workflow.

cskwork

data-ai

open

llm-ai

lets-wrap

End-of-session orchestrator that closes the learning loop. Extracts learnings and encodes them back into CLAUDE.md, mission-context, and skills. Use when "lets wrap", "wrapping up", "end of session", "syncing".

Eddale

data-ai

open

llm-ai

ac-context-optimizer

Optimize context usage for autonomous coding. Use when managing context window, prioritizing information, reducing token usage, or improving efficiency.

adaptationio

data-ai

open

llm-ai

ds-delegate

Subagent delegation for data analysis. Dispatches fresh Task agents with output-first verification.

edwinhu

data-ai

open

llm-ai

writing-eval-sloptastic

Quantitative framework for detecting AI-generated "slop" in prose through systematic analysis of structural, lexical, rhetorical, and logical patterns. Use when analyzing text authenticity, evaluating writing quality, detecting AI-generated content, or assessing whether prose has characteristic AI patterns like excessive parallelism, abstraction laddering, chiasmus abuse, platitudes, tautologies, or rhetorical overengineering.

m31uk3

data-ai

open

llm-ai

rag-evaluation

Comprehensive guide to evaluating Retrieval-Augmented Generation systems including retrieval metrics, generation quality, faithfulness, and end-to-end evaluation frameworks

AmnadTaowsoam

data-ai

open

llm-ai

skill-architect

Creates, refines, ingests, and evaluates agent skills using archetype-driven design. Use when building skills from scratch, extracting knowledge from documentation, or auditing skill quality. Do not use for non-skill related tasks or when other specialized skills are more appropriate.

Git-Fg

data-ai

open

llm-ai

save-context

Save session context for agent handoffs. Use when ending work, switching agents, or when user says "save context", "handoff", "wrap up", or "save session".

dparedesi

data-ai

open

llm-ai

rag-implementation

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

ccf

data-ai

open

llm-ai

foundry

Three-stage code implementation with planning. Gemini (Engineer) plans, Claude (Caster) implements, Gemini (Inspector) verifies. ~3x token cost for complex, multi-file changes.

stephenwinters81

data-ai

open

llm-ai

claude-typescript-sdk

Build AI applications with the Anthropic TypeScript SDK. Use when creating Claude integrations, building agents, implementing tool use, streaming responses, or working with the @anthropic-ai/sdk package.

Anveio

data-ai

open

llm-ai

session

Use when work spans multiple phases, requires context handoff, or exceeds single conversation scope. Triggers - session, multi-phase, handoff, continue, resume, checkpoint, long-running.

erikpr1994

data-ai

open

llm-aimarketplace

ms-agent-patterns

Use when building multi-agent systems with Microsoft Agent Framework. Triggers: "microsoft agents", "agent framework", "semantic kernel", "autogen", "agent graph". NOT for: Simple single-agent scenarios or non-Microsoft frameworks.

pagerguild

data-ai

open

llm-ai

prompt-engineering

Comprehensive prompt engineering techniques for Claude models. Use this skill when crafting, optimizing, or debugging prompts for Claude API, Claude Code, or any Claude-powered application. Covers system prompts, role prompting, multishot examples, chain of thought, XML structuring, long context handling, extended thinking, prompt chaining, Claude 4.x-specific best practices, and agentic orchestration including subagents, agent loops, skills, MCP integration, and multi-agent workflows.

cuba6112

data-ai

open

llm-ai

using-superpowers

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions