by wshobson
memory-safety-patterns helps agents apply RAII, ownership, smart pointers, and resource cleanup across C, C++, and Rust. Use it to review backend or systems code, reduce leaks and dangling pointers, and guide safer refactors around files, sockets, buffers, and FFI boundaries.
by wshobson
python-performance-optimization helps diagnose slow or memory-heavy Python code with profiling-first guidance, covering CPU, memory, I/O bottlenecks, caching, vectorization, async, and benchmarking workflows.
by wshobson
python-resource-management helps agents generate Python code for context managers, exception-safe cleanup, async resource lifecycles, and streaming patterns. Use it for files, DB connections, sockets, and backend code that needs deterministic teardown.
by aaron-he-zhu
memory-management helps Claude persist project context across sessions with a HOT/WARM/COLD file workflow. Use it to maintain `CLAUDE.md`, `memory/` folders, glossary entries, and event-driven updates for audits, rankings, competitors, and reports in SEO or Context Engineering workflows.
by alinaqi
mnemos is a task-scoped memory skill for agents that need durable context across compactions. It uses a typed MnemoGraph to keep goals and constraints persistent, compress results, and preserve checkpoints for resume. Useful for context engineering, debugging, repo maintenance, and handoffs.
by microsoft
continual-learning is a skill for AI coding agents that need to remember useful lessons across sessions. It supports hooks, two-tier memory, and reflection so agents can reuse project conventions, avoid repeated mistakes, and improve Agent Orchestration over time.
by zhaono1
self-improving-agent is a meta-skill for Agent Orchestration that captures task outcomes, extracts reusable patterns, and routes updates through memory, templates, hooks, and optional PR review.
