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

Skill	Purpose
context-fundamentals	Core context concepts and anatomy
context-degradation

Lost-in-middle, poisoning, attention patterns | | context-compression | Compaction strategies for long sessions | | context-optimization | Token budgeting, caching, masking | | multi-agent-patterns | Orchestrator, peer-to-peer, hierarchical | | memory-systems | Short-term, long-term, graph-based memory | | tool-design | Building effective agent tools | | filesystem-context | File-based context management | | hosted-agents | Background agents with sandboxed execution | | evaluation | Agent performance frameworks | | advanced-evaluation | LLM-as-judge techniques | | project-development | LLM project methodology | | bdi-mental-states | BDI 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):

CODEBLOCK0

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.

Condition	Sub-Skill	When to Fire
Context approaching compaction or token count exceeds ~80K	INLINECODE0	Before compaction fires or at compaction boundary
Spawning 2+ subagents in one session

multi-agent-patterns | Before first spawn in a multi-agent sequence |
| Repeated task failure (3+ retries) or agent stuck in loop | context-degradation | Before the next retry attempt |
| Building, designing, or refactoring agent tools/MCP scripts | tool-design | When tool construction begins |
| Setting up memory, JSONL store, vector DB, or persistence layer | memory-systems | When memory architecture work begins |
| Reading 5+ files as context in one session | filesystem-context | Before bulk file-loading begins |

Loading instruction:

CODEBLOCK1

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):
CODEBLOCK2

Optional (for offline use):
Clone the submodule locally, then read from INLINECODE6

Attribution

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