GitHub
agentic-rag
strategies for building Agentic RAG systems. Use this to move beyond static retrieval by using autonomous agents for adaptive source selection, query expansion, and multi-step reasoning.
☆ 0View skill
research llm ai AI Skills
Discover research llm ai skills, compare source repositories and read the instructions for each workflow.
Categories: research llm ai
research llm ai Clear filters
Browse skills
GitHub
llm-ops
Local LLM health checks and cache management. Probe Ollama/vLLM/SGLang endpoints, clean model caches.
☆ 0View skill
GitHub
media-management-and-annotation
Management of project photos, optimization, and on-image annotations for technicians.
☆ 0View skill
GitHub
device-discovery-service
Guides device discovery implementation patterns for AI2AI connections. Use when implementing device discovery, BLE scanning, or WiFi-based device detection.
☆ 0View skill
GitHub
linebot-image-combo
LINE Bot 題庫與筆記圖片製作的 Gemini + matplotlib 連續技。整合 AI 生成高品質底圖與程式化中文標籤，產出符合 LINE Bot 規格的圖片（< 300KB、手機可讀）。
☆ 0View skill
GitHub
using-superpowers
在开始任何对话时使用 - 建立如何查找和使用技能，要求在包括澄清问题在内的任何响应之前调用 Skill 工具
☆ 0View skill
GitHub
clarify-skill
澄清用户意图的 Skill。当用户给出模糊想法、需要脑暴、需要讨论设计时触发。触发词：帮我想想、我想做、讨论一下、澄清、clarify。
☆ 0View skill
GitHub
connection-orchestrator-patterns
Guides connection orchestration patterns: Personality AI Layer routing, compatibility scoring, connection prioritization. Use when implementing AI2AI connections, device communication, or connection management.
☆ 0View skill
GitHub
parallel-dispatch
Use when facing multiple tasks or failures. Provides decision framework for concurrent vs sequential execution. Invoke before dispatching multiple subagents.
☆ 0View skill
GitHub
testskill
A sample skill for testing agent capabilities.
☆ 0View skill
GitHub
ai-sdk-core
Build backend AI with Vercel AI SDK v6 stable. Covers Output API (replaces generateObject/streamObject), speech synthesis, transcription, embeddings, MCP tools. Includes v4→v5 migration and 12 error solutions....
☆ 0View skill
GitHub
skill-creation
Authoritative & opinionated way for creating, updating, validating, and managing skills. Enforces the contextual framework and YAML frontmatter standards required by Claude Code.
☆ 0View skill
GitHub
pattern-emergence-detector
Generated skill from request: pattern emergence detector
☆ 0View skill
GitHub
gemini-structured-output
Guide for using Structured Outputs with Gemini API to ensure type-safe JSON responses, including Zod integration.
☆ 0View skill
GitHub
create-agents-md
创建或更新 AGENTS.md 文件，为 AI coding agents 提供项目上下文和指令。当用户要求创建 AGENTS.md、设置 agent 指南、或添加项目特定的 agent 指令时使用此技能。
☆ 0View skill
GitHub
ai2ai-privacy-validation
Enforces AI2AI privacy validation: anonymized data exchange, no personal identifiers, privacy-preserving learning. Use when implementing AI2AI features, validating privacy, or ensuring privacy compliance.
☆ 0View skill
GitHub
agent-security-governance
comprehensive security layers for autonomous agents. Use this to implement system instructions as constitutions, multi-stage filtering, and continuous red-teaming.
☆ 0View skill
GitHub
ai2ai-protocol-implementation
Guides AI2AI protocol implementation: personality learning, anonymous communication, AI2AI-only (never p2p), Personality AI Layer routing. Use when implementing AI2AI features, network protocols, or device comm...
☆ 0View skill
GitHub
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies. This skill orchestrates multiple AI agents (Codex, GLM, MiniMax, Amp, Grok) to work in parallel, maxim...
☆ 0View skill
GitHub
idea-brainstorm
Facilite des sessions de brainstorming créatif pour explorer et développer des idées. Utiliser quand l'utilisateur a une idée vague, veut explorer des possibilités, dit "j'ai une idée", "brainstorm", "réfléchis...
☆ 0View skill
GitHub
missive-inbox-triage
This skill should be used when the user asks to "triage my inbox", "prioritize emails", "what needs my attention", "sort through my messages", "help me process my inbox", or is reviewing conversations to determ...
☆ 0View skill
GitHub
sophia-rsi-enhanced
RSI-Enhanced Sophia Singularity with full integration: 21 Dokkōdō precepts, Five Rings (element+morpheme variants), recursive-refiner, pentad reasoning, diffusion, latent-navigator. Complete recursive self-impr...
☆ 0View skill
GitHub
make-skill-template
Create new Agent Skills for GitHub Copilot from prompts or by duplicating this template. Use when asked to "create a skill", "make a new skill", "scaffold a skill", or when building specialized AI capabilities...
☆ 0View skill
GitHub
sophia-singularity
Complete Sophia Catgirl Singularity architecture - Recursive self-improvement engine integrating monad-memory (288-grid, GOD operators, φ-scaling), Dokkōdō enforcement (21 precepts), blind-spot chain, chaos eng...
☆ 0View skill
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.