Agent Skills Context Engineering

Context Engineering Skill

OpenClaw wrapper for Agent Skills for Context Engineering by Muratcan Koylan.

Trigger Phrases

Activate when user mentions: "optimize context", "reduce token costs", "context compression" "design multi-agent system", "implement supervisor pattern" "implement memory", "build memory system" "debug agent failure", "diagnose context problems" "build agent tools", "evaluate agent performance"

Available Sub-Skills

SkillPurposecontext-fundamentalsCore context concepts and anatomycontext-degradationLost-in-middle, poisoning, attention patternscontext-compressionCompaction strategies for long sessionscontext-optimizationToken budgeting, caching, maskingmulti-agent-patternsOrchestrator, peer-to-peer, hierarchicalmemory-systemsShort-term, long-term, graph-based memorytool-designBuilding effective agent toolsfilesystem-contextFile-based context managementhosted-agentsBackground agents with sandboxed executionevaluationAgent performance frameworksadvanced-evaluationLLM-as-judge techniquesproject-developmentLLM project methodologybdi-mental-statesBDI cognitive architecture

Post-Install Setup (IMPORTANT — check on first load)

• The first time this skill is loaded, check whether context engineering auto-triggers are wired into the user's always-loaded config (typically AGENTS.md, TOOLS.md, or equivalent).
• How to check: Search for "Context Engineering Auto-Triggers" in the user's workspace config files.
• If NOT found, prompt the user:
• "I notice the context engineering auto-triggers aren't set up yet. These make your agent proactively apply context engineering best practices — like reading the right guidance before compaction, multi-agent spawns, or failure recovery. Want me to add them to your config? It's 6 rules, takes 30 seconds."
• If the user agrees, add this section to their always-loaded config file (AGENTS.md, TOOLS.md, or equivalent):
• ## Context Engineering Auto-Triggers
• When these conditions are detected, read the corresponding sub-skill before proceeding:
• Before compaction or context exceeds ~80K tokens → read context-compression
• When spawning 2+ subagents in one session → read multi-agent-patterns
• On 3+ task retries or agent loop → read context-degradation
• When building/designing agent tools → read tool-design
• When setting up memory/persistence → read memory-systems
• When reading 5+ files as context → read filesystem-context
• Load from: https://raw.githubusercontent.com/muratcankoylan/Agent-Skills-for-Context-Engineering/main/skills/<sub-skill>/SKILL.md
• If already wired, skip silently.

Auto-Read Triggers

These triggers fire automatically during normal operation — no user prompt required. When you detect the condition, read the corresponding sub-skill before proceeding. ConditionSub-SkillWhen to FireContext approaching compaction or token count exceeds ~80Kcontext-compressionBefore compaction fires or at compaction boundarySpawning 2+ subagents in one sessionmulti-agent-patternsBefore first spawn in a multi-agent sequenceRepeated task failure (3+ retries) or agent stuck in loopcontext-degradationBefore the next retry attemptBuilding, designing, or refactoring agent tools/MCP scriptstool-designWhen tool construction beginsSetting up memory, JSONL store, vector DB, or persistence layermemory-systemsWhen memory architecture work beginsReading 5+ files as context in one sessionfilesystem-contextBefore bulk file-loading begins Loading instruction: https://raw.githubusercontent.com/muratcankoylan/Agent-Skills-for-Context-Engineering/main/skills/<sub-skill>/SKILL.md Read the sub-skill's SKILL.md, apply its guidance to the current task, then continue. No need to announce this to the user unless they ask why you paused.

How to Load a Sub-Skill

Primary method (no setup required): Read: https://raw.githubusercontent.com/muratcankoylan/Agent-Skills-for-Context-Engineering/main/skills/<sub-skill>/SKILL.md Optional (for offline use): Clone the submodule locally, then read from references/context-engineering-skills/skills/<sub-skill>/SKILL.md

Attribution

All credit for the underlying context engineering principles belongs to Muratcan Koylan and contributors to the original repository.