muratcankoylan/Agent-Skills-for-Context-Engineering

这个仓库里有 19 个技能，GitHub 星标 ★ 17,994。

• context-engineering-collectionA comprehensive collection of Agent Skills for context engineering, harness engi
• advanced-evaluationThis skill should be used for advanced LLM evaluation: LLM-as-judge systems, dir
• bdi-mental-statesThis skill should be used when modeling agent mental states with BDI concepts: b
• context-compressionThis skill should be used when long-running agent sessions need context compress
• context-degradationThis skill should be used for diagnosing and mitigating context degradation: los
• context-fundamentalsThis skill should be used to explain or reason about the foundational concepts o
• context-optimizationThis skill should be used for improving context efficiency: context budgeting, o
• evaluationThis skill should be used when building agent evaluation systems: deterministic
• filesystem-contextThis skill should be used when agent work needs file-backed context: durable scr
• harness-engineeringThis skill should be used when designing autonomous agent harnesses: research lo
• hosted-agentsThis skill should be used when designing hosted or background agent infrastructu
• latent-briefingThis skill should be used when the user asks to \"share memory between agents\",
• long-horizon-promptingThis skill should be used when writing, enhancing, or evaluating the launch prom
• memory-systemsThis skill should be used for persistent semantic memory in agent systems: cross
• multi-agent-patternsThis skill should be used when designing multi-agent systems that need context i
• project-developmentThis skill should be used for project-level decisions about LLM-powered systems:
• self-improvement-loopsThis skill should be used when the harness, scaffold, workflow, or optimizer its
• tool-designThis skill should be used for the tool-interface layer of an agent system specif
• skill-templateTemplate for creating new Agent Skills for context engineering. Use this templat