millitool
agent-harness-construction/

agent-harness-construction

设计和优化AI代理的动作空间、工具定义和观察格式，以提高完成率。

agentharnessconstructionai
Content Preview
---
name: agent-harness-construction
description: 设计和优化AI代理的动作空间、工具定义和观察格式，以提高完成率。
origin: ECC
---

# 智能体框架构建

当你在改进智能体的规划、调用工具、从错误中恢复以及收敛到完成状态的方式时，使用此技能。

## 核心模型

智能体输出质量受限于：

1. 行动空间质量
2. 观察质量
3. 恢复质量
4. 上下文预算质量

## 行动空间设计

1. 使用稳定、明确的工具名称。
2. 保持输入模式优先且范围狭窄。
3. 返回确定性的输出形状。
4. 除非无法隔离，否则避免使用全能型工具。

## 粒度规则

* 对高风险操作（部署、迁移、权限）使用微工具。
* 对常见的编辑/读取/搜索循环使用中等工具。
* 仅当往返开销是主要成本时使用宏工具。

## 观察设计

每个工具响应都应包括：

* `status`: success|warning|error
* `summary`: 一行结果
* `next_actions`: 可执行的后续步骤
* `artifacts`: 文件路
How to Use

Recommended: Install to project (local)

mkdir -p .claude/skills
curl -o .claude/skills/agent-harness-construction.md \
  https://raw.githubusercontent.com/affaan-m/everything-claude-code/main/docs/zh-CN/skills/agent-harness-construction/SKILL.md

Skill is scoped to this project only. Add .claude/skills/ to your .gitignoreif you don't want to commit it.

Alternative: Clone full repo

git clone https://github.com/affaan-m/everything-claude-code

Then reference at docs/zh-CN/skills/agent-harness-construction/SKILL.md

Related Skills

agent-sdk-dev/agent-sdk-verifier-py
Use this agent to verify that a Python Agent SDK application is properly configured, follows SDK best practices and documentation recommendations, and is ready for deployment or testing. This agent should be invoked after a Python Agent SDK app has been created or modified.
agentagentagent-sdk-devagent-sdk-verifier-py

by Anthropic · anthropic-official-plugins

agent-sdk-dev/agent-sdk-verifier-ts
Use this agent to verify that a TypeScript Agent SDK application is properly configured, follows SDK best practices and documentation recommendations, and is ready for deployment or testing. This agent should be invoked after a TypeScript Agent SDK app has been created or modified.
agentagentagent-sdk-devagent-sdk-verifier-ts

by Anthropic · anthropic-official-plugins

hookify/conversation-analyzer
Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Examples: <example>Context: User is running /hookify command without arguments\nuser: "/hookify"\nassistant: "I'll analyze the conversation to find behaviors you want to prevent"\n<commentary>The /hookify command without arguments triggers conversation analysis to find unwanted behaviors.</commentary></example><example>Context: User wants to create hooks from recent frustrations\nuser: "Can you look back at this conversation and help me create hooks for the mistakes you made?"\nassistant: "I'll use the conversation-analyzer agent to identify the issues and suggest hooks."\n<commentary>User explicitly asks to analyze conversation for mistakes that should be prevented.</commentary></example>
agentagenthookifyconversation-analyzer

by Anthropic · anthropic-official-plugins

plugin-dev/agent-creator
Use this agent when the user asks to "create an agent", "generate an agent", "build a new agent", "make me an agent that...", or describes agent functionality they need. Trigger when user wants to create autonomous agents for plugins. Examples:
agentagentplugin-devagent-creator

by Anthropic · anthropic-official-plugins