Context Engineering and Agent Memory skills for Claude Code and Codex
Skills for managing what sits in an agent's context window and what it remembers between sessions: context fundamentals, compression, degradation and optimization guides, filesystem scratchpads, handoff documents, conversation cloning, and persistent memory backed by Redis, Activeloop Hivemind, Deep Agents stores or a codebase graph. They keep long tasks on track without rereading everything.
Highest-scoring context engineering skills in the October 22, 2026 snapshot: chat-history from mblode/agent-skills (91/100), deep-reader from tronghieu/agent-skills (90/100) and slicing-code-context from trailofbits/skills (89/100). Scores come from the Suede Skill Check.
- 31 listed skills
- 16 repositories
- 12 with full pages
9 from official publishers. 11 bundle scripts. 2 connect to an outside service. Listed in AI Agents and LLM Engineering (29), Productivity and Knowledge Work (1), Developer Tools and Frameworks (1).
All 31 context engineering skills
No matching skills. Try fewer words or clear your search.
| Skill | Repository | What it does |
|---|---|---|
| chat-history 91/100 · A | mblode/agent-skills | Recovers decisions, previous fixes, and research from past AI conversations with source evidence, reading local Claude Code, Codex, Grok, and Cursor history. |
| context-compression 86/100 · B | muratcankoylan/Agent-Skills-for-Context-Engineering | Guides compression of long-running agent sessions through structured summarization, compaction, and durable handoff summaries that preserve decisions, files, risks, and next actions. |
| context-degradation 86/100 · B | muratcankoylan/Agent-Skills-for-Context-Engineering | Diagnoses and mitigates context degradation, including lost-in-middle failures, context poisoning, context clash, context confusion, and performance problems caused by accumulated or conflicting context. |
| context-fundamentals 84/100 · B | muratcankoylan/Agent-Skills-for-Context-Engineering | Explains the foundations of context engineering, including the anatomy of a context window, attention mechanics, and why context quality matters more than quantity. |
| context-optimization 86/100 · B | muratcankoylan/Agent-Skills-for-Context-Engineering | Improves context efficiency through context budgeting, observation masking, KV-cache strategy, partitioning, and token-cost reduction, extending effective context capacity without lowering answer quality. |
| data-structure-protocol 82/100 · B | k-kolomeitsev/data-structure-protocol | Builds and navigates a graph-based structural memory of codebases for LLM agents, storing modules, functions, dependencies, public APIs, and the reasons for each connection. |
| deep-reader 90/100 · A | tronghieu/agent-skills | Reads and answers questions about long books and papers without loading the whole text into one context window, keeping page-anchored notes. |
| filesystem-context 86/100 · B | muratcankoylan/Agent-Skills-for-Context-Engineering | Guides file-backed context for agent work, including durable scratchpads, tool-output offloading, cross-agent handoff files, and cleanup policies for context stored outside the prompt. |
| iris-development 75/100 · C | redis/agent-skills | Guides work with the Iris Redis Agent Memory data plane on Redis Cloud, covering session events, long-term memories, store configuration, and memory promotion. |
| memory-systems 86/100 · B | muratcankoylan/Agent-Skills-for-Context-Engineering | Supports persistent semantic memory in agent systems, including cross-session knowledge retention, entity tracking, graph or vector retrieval, memory consolidation, and memory benchmark selection. |
| slicing-code-context 89/100 · B | trailofbits/skills | Selects bounded, graph-informed source slices with Trailmark and delegates focused code analysis or patch-proposal work to a smaller subagent. |
| swarmclaw 74/100 · C | swarmclawai/swarmclaw | Teaches agents running on SwarmClaw how to use its 6 primitive tools, persistent memory, dreaming, delegation, connectors, credentials, and the skill system. |
| codebase-memory-mcp 77/100 · C | github/awesome-copilot | Use when exploring unfamiliar code, mapping architecture, finding symbols or relationships, tracing callers, callees, data flow or dependencies… |
| context-engineering 64/100 · D | NeoLabHQ/context-engineering-kit | Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or… |
| context-engineering-advisor 68/100 · D | deanpeters/Product-Manager-Skills | Diagnose context stuffing vs. context engineering. Use when an AI workflow feels bloated, brittle, or hard to steer reliably. |
| context-engineering-collection 76/100 · C | muratcankoylan/Agent-Skills-for-Context-Engineering | A comprehensive collection of Agent Skills for context engineering, harness engineering, multi-agent architectures, and production agent systems… |
| deep-agents-memory 77/100 · C | langchain-ai/langchain-skills | INVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral), StoreBackend (persistent)… |
| half-clone 64/100 · D | ykdojo/claude-code-tips | Clone the later half of the current conversation, discarding earlier context to reduce token usage while preserving recent work. |
| handoff 60/100 · D | mattpocock/skills | Compact the current conversation into a handoff document for another agent to pick up. |
| handoff 62/100 · D | ykdojo/claude-code-tips | Write or update a handoff document so the next agent with fresh context can continue this work. |
| hivemind-memory 72/100 · C | activeloopai/hivemind | Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information. |
| integrate-context-matic 77/100 · C | github/awesome-copilot | Discovers and integrates third-party APIs using the context-matic MCP server. Uses `fetch_api` to find available API SDKs, `ask` for integration… |
| latent-briefing 87/100 · B | muratcankoylan/Agent-Skills-for-Context-Engineering | This skill should be used when the user asks to "share memory between agents", "KV cache compaction for multi-agent", "orchestrator worker context"… |
| long-context 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents… |
| memorize 66/100 · D | NeoLabHQ/context-engineering-kit | Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering |
| mini-context-graph 74/100 · C | github/awesome-copilot | A persistent, compounding knowledge base combining Karpathy's LLM Wiki pattern with a structured knowledge graph. Ingest documents once — the LLM… |
| nemo-rl-session-memory 82/100 · B | NVIDIA/skills | Manage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code… |
| onboard-context-matic 84/100 · B | github/awesome-copilot | Interactive onboarding tour for the context-matic MCP server. Walks the user through what the server does, shows all available APIs, lets them pick… |
| pinecone-rag 84/100 · B | github/awesome-copilot | Build production RAG pipelines and persistent agent memory using Pinecone as the vector database backend. ALWAYS USE THIS SKILL when the user… |
| quarter-clone 64/100 · D | ykdojo/claude-code-tips | Clone the last quarter of the current conversation, discarding earlier context to reduce token usage while preserving recent work. |
| self-managed-context 79/100 · C | muratcankoylan/Agent-Skills-for-Context-Engineering | This skill should be used when a model gets read-write control over its own live context window instead of a harness-scheduled compaction policy… |
How to choose context engineering skills
Start with a method skill if sessions drift or run out of room. The muratcankoylan context-engineering collection covers fundamentals, compression, degradation and filesystem context as separate skills you can install together.
Memory backends are a bigger commitment. Hivemind, Iris on Redis Cloud and Deep Agents memory each store data in a service you configure, so check the environment variables under Before you install and decide what is allowed to persist.
Handoff and clone skills (handoff, half-clone, quarter-clone) are the lightest option. They write or trim context inside your current tool with no service behind them, which makes them easy to try on one long task.
Related topics
MCP Servers 82Subagents and Multi-Agent Orchestration 40Agent Tracing and Observability 41AI Agent Builders 56Codex, Cursor and Coding Agents 23RAG and Retrieval 32Claude Code Setup and Hooks 31Fine-Tuning and Model Training 127
Find your next useful skill
Explore Rising Skills with quality scores and source reports, or search from inside your agent.
Get Rising Skills by email · Read Rising Skills · Install the finder · State of Agent Skills