llm-ai
1
image-generation
AI图像生成与编辑能力，基于 Nano Banana (Gemini Image) 实现文生图、图生图、图像编辑。适用于创意设计、营销素材、社交媒体内容、演示文稿配图等场景。支持多种风格、高分辨率输出（最高4K）、文字渲染、角色一致性保持。
hxk622
data-ai
sorting
stars
current ordering strategy
query
all entries
refine the visible subset
llm-ai
1
code-reviewer
Atlas skill for converting Claude Code Subagents to OpenCode Agents format. USE WHEN migrating from Claude Code to OpenCode or when you have existing subagent definitions to port.
edheltzel
data-ai
llm-ai
1
multi-agent-orchestration
Comprehensive guide to building multi-agent systems, agent collaboration patterns, and orchestration strategies (2025-2026 standards)
mdaashir
data-ai
llm-ai
1
few-shot-prompting
Example-based prompting techniques for in-context learning
pluginagentmarketplace
data-ai
machine-learning
1
optimizing-rag
Optimize RAG performance with reranking, caching, parallel processing, and production deployment patterns. Use when improving retrieval quality, adding rerankers, deploying to production, implementing caching strategies, or optimizing for scale and latency.
tkhongsap
data-ai
llm-ai
1
agentuity-cli-cloud-vector-search
Search for vectors using semantic similarity. Requires authentication. Use for Agentuity cloud platform operations
agentuity
data-ai
llm-ai
1
rag-expert
Expert in Retrieval-Augmented Generation systems - knowledge bases, chunking strategies, embedding optimization, and production RAG architectures
frankxai
data-ai
llm-ai
1
doc-review
Review a single file or all files in a folder for data inconsistencies, reference errors, typos, and unclear terminology using parallel sub-agents
vladm3105
data-ai
llm-ai
1
remembering-conversations
ALWAYS USE THIS SKILL WHEN STARTING ANY KIND OF WORK, NO MATTER HOW TRIVIAL. You have no memory between sessions and will reinvent solutions or repeat past mistakes UNLESS YOU USE THIS SKILL. Gives you perfect recall of all your past conversations and projects.
Krosebrook
data-ai
llm-ai
1
consulting-agents
Use when you need information you don't have, expertise outside your comfort zone, or fresh eyes on code - dispatches agents to research, advise, or review. NOT for implementation delegation (see subagent-driven-development).
snits
data-ai
llm-ai
1
rag-exploitation
Attack techniques for Retrieval-Augmented Generation systems including knowledge base poisoning
pluginagentmarketplace
data-ai
machine-learning
1
hugging-face-evaluation-manager
Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.
Nymbo
data-ai
machine-learning
1
multi-model-validation
Run multiple AI models in parallel for 3-5x speedup with ENFORCED performance statistics tracking. Use when validating with Grok, Gemini, GPT-5, DeepSeek, or Claudish proxy for code review, consensus analysis, or multi-expert validation. NEW in v3.1.0 - SubagentStop hook enforces statistics collection, MANDATORY checklist prevents incomplete reviews, timing instrumentation examples. Includes dynamic model discovery via `claudish --top-models` and `claudish --free`, session-based workspaces, and Pattern 7-8 for tracking model performance. Trigger keywords - "grok", "gemini", "gpt-5", "deepseek", "claudish", "multiple models", "parallel review", "external AI", "consensus", "multi-model", "model performance", "statistics", "free models".
involvex
data-ai
llm-ai
1
context-optimization
Apply optimization techniques to extend effective context capacity. Use when context limits constrain agent performance, when optimizing for cost or latency, or when implementing long-running agent systems.
SyntaxAsSpiral
data-ai
llm-ai
1
outsourcing-core
로컬 AI CLI에 작업을 아웃소싱할 때 자동 활성화. Use when the task is complex, requires specialized AI capabilities, or benefits from distributing work to different AI models
inchan
data-ai
llm-ai
1
rlm-process
Process large contexts using RLM (Recursive Language Model) patterns - chunking, filtering, recursive sub-calls
namesreallyblank
data-ai
llm-ai
1
writing-claude-skills
Create effective Agent Skills following the agentskills.io specification. Use when creating new skills, reviewing existing skills, or improving skill descriptions.
stephendolan
data-ai
machine-learning
1
training-hub
Fine-tune LLMs using Red Hat training-hub library with SFT, LoRA, and OSFT algorithms. Use when preparing JSONL datasets, running training jobs, configuring hardware, scaling to clusters, evaluating models, or deploying with vLLM.
RobbieJ
data-ai
llm-ai
1
claude4-prompt-engineer
Expert prompt engineering for Claude 4.x models (Sonnet 4.5, Opus 4.5, Haiku 4.5). Use when creating system prompts, optimizing existing prompts, designing agentic workflows, or improving prompt effectiveness. Triggers on requests like "optimize this prompt", "write a system prompt", "improve these instructions", "create an agent prompt", or any task involving prompt design for Claude.
pkarpovich
data-ai
llm-ai
1
hf-jobs
This skill should be used when users want to run any workload on Hugging Face Jobs infrastructure. Covers UV scripts, Docker-based jobs, hardware selection, cost estimation, authentication with tokens, secrets management, timeout configuration, and result persistence. Designed for general-purpose compute workloads including data processing, inference, experiments, batch jobs, and any Python-based tasks. Should be invoked for tasks involving cloud compute, GPU workloads, or when users mention running jobs on Hugging Face infrastructure without local setup.
Nymbo
data-ai
llm-ai
1
architecting-memory
Implements progression from Vector RAG → GraphRAG → Temporal Knowledge Graphs. Use when designing persistent memory architectures for AI agent systems.
Git-Fg
data-ai