Agent Skills For Context Engineering

Agent Skills For Context Engineering from muratcankoylan/Agent-Skills-for-Context-Engineering.

by @muratcankoylan 16 skills

Skills in this plugin

16
  1. ▌
    Evaluation · muratcankoylan bundle
    Build evaluation frameworks for agent systems with deterministic checks, regression suites, multi-dimensional rubrics, quality gates, production monitoring, and outcome measurement.
    18.3k repo stars
  2. ▌
    Tool Design · muratcankoylan bundle
    Design tool descriptions, schemas, and response formats that agents can reliably route on, including MCP server design, tool-set consolidation, and naming conventions.
    18.3k repo stars
  3. ▌
    Hosted Agents · muratcankoylan bundle
    Design and build hosted agent infrastructure with sandboxed execution, warm pools, session persistence, and multiplayer collaboration.
    18.3k repo stars
  4. ▌
    Memory Systems · muratcankoylan bundle
    Designs persistent memory architectures for AI agents, covering cross-session knowledge retention, entity tracking, temporal validity, graph/vector retrieval, and memory consolidation.
    18.3k repo stars
  5. ▌
    Latent Briefing · muratcankoylan bundle
    Shares 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.
    18.3k repo stars
  6. ▌
    Bdi Mental States · muratcankoylan bundle
    Model agent mental states using BDI (Beliefs, Desires, Intentions) ontology patterns, enabling cognitive reasoning, explainability, and semantic interoperability in multi-agent systems.
    18.3k repo stars
  7. ▌
    Filesystem Context · muratcankoylan bundle
    Uses the filesystem as a durable overflow layer for agent context, enabling scratch pads, plan persistence, sub-agent communication, dynamic skill loading, and log management.
    18.3k repo stars
  8. ▌
    Advanced Evaluation · muratcankoylan bundle
    Provides production-grade techniques for evaluating LLM outputs using LLMs as judges, covering direct scoring, pairwise comparison, bias mitigation, rubric generation, and confidence calibration.
    18.3k repo stars
  9. ▌
    Context Compression · muratcankoylan bundle
    Optimizes long-running agent sessions with structured context compression, summarization, and durable handoff summaries that preserve decisions, files, risks, and next actions.
    18.3k repo stars
  10. ▌
    Context Degradation · muratcankoylan bundle
    Diagnose and mitigate context degradation patterns including lost-in-middle failures, context poisoning, distraction, confusion, and clash in AI agent systems.
    18.3k repo stars
  11. ▌
    Harness Engineering · muratcankoylan
    Designs autonomous agent harnesses with locked evaluators, editable surfaces, durable logging, novelty gates, pruning, rollback, and human approval boundaries.
    18.3k repo stars
  12. ▌
    Project Development · muratcankoylan bundle
    Guides project-level decisions for LLM-powered systems: task-model fit, pipeline architecture, token and cost estimation, and agent-assisted iteration.
    18.3k repo stars
  13. ▌
    Context Fundamentals · muratcankoylan bundle
    Explains foundational concepts of context engineering: what context is, attention mechanics, the U-shaped attention curve, and why context quality matters more than quantity.
    18.3k repo stars
  14. ▌
    Context Optimization · muratcankoylan bundle
    Extends effective context capacity through strategic compression, masking, caching, and partitioning techniques.
    18.3k repo stars
  15. ▌
    Multi Agent Patterns · muratcankoylan bundle
    Design multi-agent systems with context isolation, supervisor or swarm coordination, explicit handoffs, parallel execution, and decision frameworks for when multiple agents are justified.
    18.3k repo stars
  16. ▌
    Self Improvement Loops · muratcankoylan bundle
    Designs 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.
    18.3k repo stars