Agent Skills For Context Engineering
Agent Skills For Context Engineering from muratcankoylan/Agent-Skills-for-Context-Engineering.
Skills in this plugin
16- ▌ Evaluation · muratcankoylan bundleBuild evaluation frameworks for agent systems with deterministic checks, regression suites, multi-dimensional rubrics, quality gates, production monitoring, and outcome measurement.
- ▌ Tool Design · muratcankoylan bundleDesign tool descriptions, schemas, and response formats that agents can reliably route on, including MCP server design, tool-set consolidation, and naming conventions.
- ▌ Hosted Agents · muratcankoylan bundleDesign and build hosted agent infrastructure with sandboxed execution, warm pools, session persistence, and multiplayer collaboration.
- ▌ Memory Systems · muratcankoylan bundleDesigns persistent memory architectures for AI agents, covering cross-session knowledge retention, entity tracking, temporal validity, graph/vector retrieval, and memory consolidation.
- ▌ Latent Briefing · muratcankoylan bundleShares memory between agents at the representation level by compacting the orchestrator's KV cache for efficient worker handoff, reducing token costs without summarization or retrieval.
- ▌ Bdi Mental States · muratcankoylan bundleModel agent mental states using BDI (Beliefs, Desires, Intentions) ontology patterns, enabling cognitive reasoning, explainability, and semantic interoperability in multi-agent systems.
- ▌ Filesystem Context · muratcankoylan bundleUses the filesystem as a durable overflow layer for agent context, enabling scratch pads, plan persistence, sub-agent communication, dynamic skill loading, and log management.
- ▌ Advanced Evaluation · muratcankoylan bundleProvides production-grade techniques for evaluating LLM outputs using LLMs as judges, covering direct scoring, pairwise comparison, bias mitigation, rubric generation, and confidence calibration.
- ▌ Context Compression · muratcankoylan bundleOptimizes long-running agent sessions with structured context compression, summarization, and durable handoff summaries that preserve decisions, files, risks, and next actions.
- ▌ Context Degradation · muratcankoylan bundleDiagnose and mitigate context degradation patterns including lost-in-middle failures, context poisoning, distraction, confusion, and clash in AI agent systems.
- ▌ Harness Engineering · muratcankoylanDesigns autonomous agent harnesses with locked evaluators, editable surfaces, durable logging, novelty gates, pruning, rollback, and human approval boundaries.
- ▌ Project Development · muratcankoylan bundleGuides project-level decisions for LLM-powered systems: task-model fit, pipeline architecture, token and cost estimation, and agent-assisted iteration.
- ▌ Context Fundamentals · muratcankoylan bundleExplains foundational concepts of context engineering: what context is, attention mechanics, the U-shaped attention curve, and why context quality matters more than quantity.
- ▌ Context Optimization · muratcankoylan bundleExtends effective context capacity through strategic compression, masking, caching, and partitioning techniques.
- ▌ Multi Agent Patterns · muratcankoylan bundleDesign multi-agent systems with context isolation, supervisor or swarm coordination, explicit handoffs, parallel execution, and decision frameworks for when multiple agents are justified.
- ▌ Self Improvement Loops · muratcankoylan bundleDesigns and governs recursive self-improvement loops where an agent mines its own failures and proposes edits to its own harness, prompts, or workflow, covering acceptance gates, diversity preservation, and the optimization ladder.