Stats
Actions
Tags
Designs and optimizes AI agent operation spaces, tool definitions, and observation formats to improve task completion rates. Covers architectures, error recovery, and context budgeting.
How this skill is triggered — by the user, by Claude, or both
Slash command
/everything-claude-code:agent-harness-constructionThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
在改进智能体如何规划、调用工具、从错误中恢复并收敛到完成时使用此技能。
在改进智能体如何规划、调用工具、从错误中恢复并收敛到完成时使用此技能。
智能体输出质量受限于：
每个工具响应应包括：
status：success|warning|errorsummary：单行结果next_actions：可操作的后续步骤artifacts：文件路径 / ID对于每个错误路径，包括：
跟踪：
npx claudepluginhub aaione/everything-claude-code-zhDesigns and optimizes AI agent action spaces, tool definitions, observation formatting, error recovery, and context budgeting for higher task completion rates.
Designs and optimizes AI agent action spaces, tool definitions, observation formatting, and error recovery for higher completion rates.
Designs and builds autonomous AI agents with expertise in tool use, memory systems, planning strategies, and multi-agent orchestration. Covers ReAct loops, hierarchical memory, and supervisor patterns.