MCP App StoreMCP App Store
from awesome-omni-skills54
Guides building and operating agent memory systems (semantic, episodic, procedural) with practical patterns for chunking, embeddings, retrieval, and decay.
This skill packages best-practice guidance and operational patterns for agent memory systems. It explains architecture choices (short-term context vs long-term vector stores), chunking strategies, embedding/model trade-offs, vector store selection, and practical runtime patterns for retrieval, conflict resolution, and memory decay. The content is aimed at engineers and architects building RAG pipelines, personalization layers, or multi-agent shared memory.
Use this skill when designing or troubleshooting memory for conversational agents: selecting a vector store, choosing embedding models, defining chunking strategies, implementing temporal decay, or creating background memory formation pipelines. Trigger when requests mention "agent memory", "long-term memory", "memory retrieval", or "episodic memory".
Tools implied by the content: codex-cli, claude-code, cursor, gemini-cli, opencode (examples reference common agent tooling).
This skill has not been reviewed by our automated audit pipeline yet.
Azure Identity SDK (TypeScript) v2
Authenticate to Azure services from TypeScript using DefaultAzureCredential, Managed Identity, service principals, and credential chains with provenance-preserv
Conductor Revert (Git-aware Revert Track)
Git-aware revert workflow for reverting tracks, phases, or tasks while preserving provenance and upstream workflow; includes safety checks and an execution plan
Security Threat Model (Repository-grounded)
Generate an evidence-backed, repository-specific threat model that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and prioritized miti
Context Restoration — Code Refactoring
Workflow and best practices for restoring and preserving project context during code refactoring, with provenance and selective file restoration.
HelpDesk Automation (Rube MCP)
Automate HelpDesk workflows via Rube MCP (Composio): list and paginate tickets, manage views, use canned responses, and inspect custom fields while preserving u
Azure Event Hubs (Rust) — Workflow
Run and review Azure Event Hubs workflows in Rust: send/receive events, batch sends, partitioned consumption and checkpointing with preserved provenance.
Azure.Messaging.EventGrid (.NET) v2
Workflow skill for Azure Event Grid (.NET): publish and consume EventGrid and CloudEvents, with examples for publishing, pull delivery, and Azure Functions trig
AgentPhone (Telephony)
Manage AgentPhone telephony workflows: create agents, buy/release numbers, make calls, send/receive SMS, configure webhooks, and inspect transcripts/usage.
Node.js Best Practices (v3)
Decision-focused Node.js guidance for framework choice, async patterns, security, testing, and architecture — teaches how to think about Node.js projects rather
Learning Opportunities
Adds short interactive learning exercises during AI-assisted coding to help developers understand design decisions and new code before merging.
Caveman Compress
Compress natural-language memory files into a compact 'caveman' format to save LLM tokens while preserving code, links, and structure.
Go Data Structures
Authoritative guidance on choosing and using Go built-in and standard-library data structures, with practical best practices for slices, maps, arrays, container
Memory Search
Search past coding sessions and observations using natural-language queries to retrieve decisions, notes, and context.
DSPy — Declarative LM Programming
Use DSPy to build declarative, modular LM pipelines, optimize prompts automatically, and assemble reliable RAG/agent systems with structured signatures and opti
Microsoft Foundry Classic — Expert Guidance
Comprehensive guidance for building, configuring, troubleshooting, and deploying Microsoft Foundry Classic agents and integrations.
hmem — Setup
Interactive installer and setup guide for hmem (persistent memory MCP server); automates .mcp.json config, memory dir, and adds agent hooks for Claude Code, Gem
OpenViking Memory Plugin
Provides automatic long-term memory capture and recall for OpenClaw agents: auto-capture, auto-recall, and memory management tools for more context-aware conver
Synalinks Framework
Keras-inspired framework for building structured, neuro-symbolic LLM programs with DataModel schemas, modular Programs, and training/optimization tools.