llm-ai
1
multi-agent-patterns
Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.
SyntaxAsSpiral
data-ai
sorting
stars
current ordering strategy
query
all entries
refine the visible subset
llm-ai
1
project-development
Methodology for identifying LLM-suited tasks, designing pipelines, and iterating with agent-assisted development.
5dlabs
data-ai
llm-ai
1
skill-review
Review and propose improvements for Claude skills based on usage patterns.
Xantibody
data-ai
llm-ai
1
agent-communication
Use when user explicitly requests to coordinate with other Claude Code agents, join an agent chat, or communicate across multiple repositories/projects
asermax
data-ai
llm-ai
1
using-superpowers
开始任何对话时使用 - 确立如何查找和使用技能。在任何响应之前（包括澄清问题）都需要调用 Skill 工具。Use when starting any conversation - establishes how to find and use skills. If a skill might apply (even 1% chance), you MUST invoke it.
hxk622
data-ai
llm-ai
1
skill-creation-guide
Guide for creating Agent Skills: structure, best practices, and SKILL.md format for Claude Code, Codex, Gemini CLI, and other AI agents.
gmh5225
data-ai
llm-ai
1
faf-platforms
Understand where FAF works - Claude Code (CLI + Skills), claude-faf-mcp (Desktop + MCP), vs claude.ai (web - file upload only). Explains faf-cli vs MCP differences, when to use each platform. Use when user asks "does FAF work with", "CLI vs MCP", "Claude Desktop vs claude.ai", or platform compatibility questions.
Wolfe-Jam
data-ai
llm-ai
1
safety-filter-bypass
Techniques to test and bypass AI safety filters, content moderation systems, and guardrails for security assessment
pluginagentmarketplace
data-ai
llm-ai
1
julien-maintenance-claude-json
Clean ~/.claude.json when it becomes too large (>25K tokens). Use when Claude cannot read the file, user mentions "claude.json trop gros", "nettoyer claude.json", or "cleanup claude.json".
theflysurfer
data-ai
llm-ai
1
prompt-hacking
Advanced prompt manipulation including direct attacks, indirect injection, and multi-turn exploitation
pluginagentmarketplace
data-ai
llm-ai
1
prompt-analyzer
ユーザープロンプトを分析し、topic_type（instruction/question/context）を判定する。
M2AI-jp
data-ai
machine-learning
1
mlops-engineer
Build ML pipelines, experiment tracking, and model registries. Implements MLflow, Kubeflow, and automated retraining. Handles data versioning and reproducibility. Use PROACTIVELY for ML infrastructure, experiment management, or pipeline automation.
sidetoolco
data-ai
llm-ai
1
subagent-orchestration
Esta skill debe usarse cuando el usuario pide "orquestar agentes", "coordinar subagentes", "agentes en paralelo", "flujo multi-agente", "delegar a agentes", "lanzar agentes en paralelo", o necesita ejecutar múltiples tareas independientes con subagentes simultáneos.
DieGopherLT
data-ai
llm-ai
1
skill-creator
Skill 與 Agent 建立指導專家，協助開發者依據 GitHub Copilot 最佳實踐建立高品質的 custom agent 和 skill 定義檔案，包含 YAML frontmatter、MCP 整合與互動式工作流程設計。
yaochangyu
data-ai
machine-learning
1
prompt-engineer
Optimizes prompts for LLMs and AI systems. Use when building AI features, improving agent performance, or crafting system prompts. Expert in prompt patterns and techniques.
sidetoolco
data-ai
llm-ai
1
anthropic-prompt-engineer
Master Anthropic's prompt engineering techniques to generate new prompts or improve existing ones using best practices for Claude AI models.
zircote
data-ai
machine-learning
1
ai-system-evaluation
End-to-end AI system evaluation - model selection, benchmarks, cost/latency analysis, build vs buy decisions. Use when selecting models, designing eval pipelines, or making architecture decisions.
doanchienthangdev
data-ai
llm-ai
1
agent-native-architecture
This skill should be used when building AI agents using prompt-native architecture where features are defined in prompts, not code. Use it when creating autonomous agents, designing MCP servers, implementing self-modifying systems, or adopting the "trust the agent's intelligence" philosophy.
SiTaggart
data-ai
machine-learning
1
senior-prompt-engineer
World-class prompt engineering skill for LLM optimization, prompt patterns, structured outputs, and AI product development. Expertise in Claude, GPT-4, prompt design patterns, few-shot learning, chain-of-thought, and AI evaluation. Includes RAG optimization, agent design, and LLM system architecture. Use when building AI products, optimizing LLM performance, designing agentic systems, or implementing advanced prompting techniques.
drgaciw
data-ai
machine-learning
1
genai-dac-specialist
Expert in OCI Generative AI Dedicated AI Clusters - deployment, fine-tuning, optimization, and production operations
frankxai
data-ai
llm-ai
1
student-language-guide
Provide student-facing language rules for educational content. Use when writing lessons, checking language appropriateness, or validating content for students.
zeeshan080
data-ai