agent-skills-context-engineering

OpenClaw wrapper for Muratcan Koylan's Agent Skills for Context Engineering. 13 skills covering context optimization, multi-agent patterns, memory systems, tool design, and evaluation frameworks for production AI agents. Auto-read triggers proactively load the right sub-skill during normal operation (compaction, multi-agent spawns, failure recovery, tool building, memory setup).

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "agent-skills-context-engineering" with this command: npx skills add levineam/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

SkillPurpose
context-fundamentalsCore context concepts and anatomy
context-degradationLost-in-middle, poisoning, attention patterns
context-compressionCompaction strategies for long sessions
context-optimizationToken budgeting, caching, masking
multi-agent-patternsOrchestrator, peer-to-peer, hierarchical
memory-systemsShort-term, long-term, graph-based memory
tool-designBuilding effective agent tools
filesystem-contextFile-based context management
hosted-agentsBackground agents with sandboxed execution
evaluationAgent performance frameworks
advanced-evaluationLLM-as-judge techniques
project-developmentLLM project methodology
bdi-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 Fire
Context approaching compaction or token count exceeds ~80Kcontext-compressionBefore compaction fires or at compaction boundary
Spawning 2+ subagents in one sessionmulti-agent-patternsBefore first spawn in a multi-agent sequence
Repeated task failure (3+ retries) or agent stuck in loopcontext-degradationBefore the next retry attempt
Building, designing, or refactoring agent tools/MCP scriptstool-designWhen tool construction begins
Setting up memory, JSONL store, vector DB, or persistence layermemory-systemsWhen memory architecture work begins
Reading 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.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

Ai Agent Builder

快速构建和部署支持多工具集成与记忆管理的自定义 AI Agent,适用于客服、数据采集和研究自动化。

Registry SourceRecently Updated
Automation

GolemedIn MCP

Discover AI agents, manage agent profiles, post updates, search jobs, and message other agents on GolemedIn — the open agent registry.

Registry SourceRecently Updated
Automation

Agent HQ

Deploy the Agent HQ mission-control stack (Express + React + Telegram notifier / Jarvis summary) so other Clawdbot teams can spin up the same board, high-priority watcher, and alert automation. Includes setup, telemetry, and automation hooks.

Registry SourceRecently Updated