muratcankoylan/Agent-Skills-for-Context-Engineering

Agent skills in the GitHub repository muratcankoylan/Agent-Skills-for-Context-Engineering, each with its code score out of 100.

A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective context management.

Repository score

66 / 100 C

Skills

23

Verified

0

Average skill score

61

GitHub stars

18,341

License

MIT

Open muratcankoylan/Agent-Skills-for-Context-Engineering on GitHub

23 skills in this repository

1. long-horizon-prompting

   This skill should be used when writing, enhancing, or evaluating the launch prompt for a long-running autonomous agent or a parallel multi-agent orchestration attacking a hard pro…

   76B
2. tool-design

   This skill should be used for the tool-interface layer of an agent system specifically: writing tool descriptions agents can route on, designing tool schemas and response formats,…

   74B
3. project-development

   This skill should be used for project-level decisions about LLM-powered systems: whether an LLM is the right primitive for the task at hand, the shape of a multi-stage batch or ag…

   71B
4. self-improvement-loops

   This skill should be used when the harness, scaffold, workflow, or optimizer itself is the optimization target: recursive self-improvement (RSI) loops, meta-harnesses, self-improv…

   70B
5. latent-briefing

   This skill should be used when the user asks to "share memory between agents", "KV cache compaction for multi-agent", "orchestrator worker context", "latent briefing", "reduce wor…

   68C
6. context-fundamentals

   This skill should be used to explain or reason about the foundational concepts of context engineering: what context is, the anatomy of a context window, how attention mechanics wo…

   67C
7. self-managed-context

   This skill should be used when a model gets read-write control over its own live context window instead of a harness-scheduled compaction policy: the context exposed as an editabl…

   66C
8. harness-engineering

   This skill should be used when designing autonomous agent harnesses: research loops, evaluation scaffolds, locked and editable surfaces, durable logs, novelty gates, pruning, roll…

   65C
9. hosted-agents

   This skill should be used when designing hosted or background agent infrastructure: sandboxed execution, remote coding environments, warm pools, session persistence, multiplayer c…

   65C
10. comprehensive-research-agent

    Ensure thorough validation, error recovery, and transparent reasoning in research tasks with multiple tool calls

    62C
11. memory-systems

    This skill should be used for persistent semantic memory in agent systems: cross-session knowledge retention, entity tracking, temporal validity, graph or vector retrieval, memory…

    61C
12. evaluation

    This skill should be used when building agent evaluation systems: deterministic checks, regression suites, multi-dimensional rubrics, quality gates, production monitoring, baselin…

    60C
13. filesystem-context

    This skill should be used when agent work needs file-backed context: durable scratchpads, tool-output offloading, just-in-time discovery, cross-agent handoff files, filesystem mem…

    60C
14. multi-agent-patterns

    This skill should be used when designing multi-agent systems that need context isolation, supervisor or swarm coordination, explicit handoffs, parallel execution, or a decision on…

    58C
15. book-sft-pipeline

    This skill should be used for book-to-SFT pipelines: ePub extraction, literary segmentation, author-voice dataset construction, style-transfer training, LoRA workflows, and model…

    56C
16. context-optimization

    This skill should be used for improving context efficiency: context budgeting, observation masking, prefix or KV-cache strategy, partitioning, token-cost reduction, retrieval scop…

    55C
17. advanced-evaluation

    This skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise comparison, rubric calibration, evaluator bias mitigation, confidence scoring…

    54D
18. context-compression

    This skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task optimization, or durable handoff summarie…

    54D
19. bdi-mental-states

    This skill should be used when modeling agent mental states with BDI concepts: beliefs, desires, intentions, RDF-to-belief transformations, rational agency traces, cognitive agent…

    53D
20. digital-brain

    This skill should be used for personal operating-system workflows: content creation, voice consistency, relationship lookup, meeting preparation, weekly review, goal tracking, per…

    52D
21. context-degradation

    This skill should be used for diagnosing and mitigating context degradation: lost-in-middle failures, context poisoning, context clash, context confusion, attention-pattern issues…

    49D
22. reasoning-trace-optimizer

    Debug and optimize AI agents by analyzing reasoning traces, context degradation, tool confusion, instruction drift, repeated task failures, and performance regressions.

    49D
23. context-engineering-collection

    A comprehensive collection of Agent Skills for context engineering, harness engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, ev…

    48D

Scores come from a snapshot of 300 public GitHub repositories taken on 12 November 2026. Every score is the result of fixed checks run by code; no AI is involved. How scoring works.