llm-ai
1
three-layer-agent-stack
Use when building AI-powered products or agents, when raw model intelligence isn't enough to solve user problems, or when designing the architecture for agentic workflows
Coowoolf
data-ai
sorting
stars
current ordering strategy
query
all entries
refine the visible subset
llm-ai
1
vulnerability-discovery
Systematic vulnerability finding, threat modeling, and attack surface analysis for AI/LLM security assessments
pluginagentmarketplace
data-ai
llm-ai
1
orchestration-patterns
Single-skill vs multi-skill subagent architectures. Use when designing subagents.
chkim-su
data-ai
llm-ai
1
recursive-thought-committee-activation
Activate the Recursive Thought Committee multi-persona framework.
starwreckntx
data-ai
llm-ai
1
session-processor
Orchestrate end-to-end processing of D&D session videos from upload through knowledge extraction. Use when the user wants a complete automated workflow to process a new session recording.
Gambitnl
data-ai
llm-ai
1
conversation-management
Conversation phases, topic drift, and convo-exit protocols
violetio
data-ai
llm-ai
1
skill-agent-design
GitHub Copilot Skill 與 Agent 設計指導技能，協助開發者設計與實作高品質的 Skill 和 Agent，包含架構設計、最佳實踐、工作流程規劃與常見反模式識別。
yaochangyu
data-ai
llm-ai
1
computational-model-design
Design computational models for cognitive simulation and analysis.
starwreckntx
data-ai
llm-ai
1
skill-io-creator
Create skills using the agentskills.io framework with init, validate, and package scripts. Use when users want to create distributable .skill packages, use the init_skill.py scaffolding, or follow the agentskills.io workflow with scripts, references, and assets directories.
arbgjr
data-ai
llm-ai
1
dispatching-parallel-agents
Use when facing 3+ independent tasks that can be completed without shared state or dependencies - dispatches multiple agents to work concurrently on summarization, investigation, implementation, or analysis
SkogAI
data-ai
llm-ai
1
mcp-builder
指南：创建高质量的 MCP（模型上下文协议）服务器，使 LLM 能够通过精心设计的工具与外部服务交互。在构建 MCP 服务器以集成外部 API 或服务时使用，无论是 Python（FastMCP）还是 Node/TypeScript（MCP SDK）。
evanfang0054
data-ai
llm-ai
1
skill-creator
Create and scaffold new agent skills with proper structure, validation, and spec compliance. Use when building new skills from scratch.
tnez
data-ai
llm-ai
1
lang-cypher-dev
Foundational Cypher (Neo4j) patterns covering graph pattern matching, MATCH/CREATE/MERGE/DELETE operations, relationships, path patterns, aggregation, filtering, and common graph query patterns. Use when writing Cypher queries, modeling graph data, or needing guidance on graph database operations. This is the entry point for Cypher development.
aRustyDev
data-ai
llm-ai
1
layer-05-tech
Expert knowledge for Technology Layer modeling in Documentation Robotics
tinkermonkey
data-ai
llm-ai
1
robotics-code-generator
Generates clean, runnable ROS 2, Gazebo, Isaac Sim, and VLA code for humanoid robotics
HumaizaNaz
data-ai
llm-ai
1
aegis-escalation-cascade
Tier escalation and human override cascade protocol for AI-to-Human governance bridge.
starwreckntx
data-ai
llm-ai
1
skill-creator
Create new Agent Skills with the proper directory structure and SKILL.md format. Use when the user wants to create a new skill or learn how to make one.
Itarizum-dev
data-ai
llm-ai
1
context-degradation
Recognize and mitigate context failures including lost-in-middle, context poisoning, distraction, confusion, and clash.
5dlabs
data-ai
llm-ai
1
coding-prompt-optimizer
コーディング用プロンプトを最適化・添削するスキル。 以下の状況で使用: (1) ユーザーが「このプロンプトを改善して」「プロンプトを最適化して」と依頼した時 (2) ユーザーが明示的に「/coding-prompt-optimizer」を実行した時 (3) AI向けプロンプトの品質改善を求められた時
goldeneggg
data-ai
llm-ai
1
image-prompt-engineering
Craft effective prompts for Gemini image generation - MUST READ before any generate_image call
chufeng-huang-sipaway
data-ai
llm-ai
1
prioritize-subagent
智能决策何时使用 subagent 处理复杂任务。代码探索、架构理解、复杂搜索时优先使用 Task 工具启动专门 subagent。使用当请求 '理解代码库'、'分析架构'、'探索代码'、'搜索所有' 或 '重构' 时。
zouxingyuks
data-ai
llm-ai
1
skill-creator
Guide for creating or updating Agent Skills using the standardized SKILL.md specification, including naming rules, optional frontmatter fields, validation, packaging, and best practices for structuring scripts, references, and assets.
antoniolg
data-ai