affaan-m/agent-harness-construction
docs/zh-CN/skills/agent-harness-construction/SKILL.md
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。
$ install --global
skillsauthnpx skillsauth add affaan-m/everything-claude-code agent-harness-constructionInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Mar 29, 2026, 5:52 AM36.7s1 file scanned
SKILL.md
- 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：
- 行动空间质量
- 观察质量
- 恢复质量
- 上下文预算质量
行动空间设计
- 使用稳定、明确的工具名称。
- 保持输入模式优先且范围狭窄。
- 返回确定性的输出形状。
- 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|errorsummary: 一行结果next_actions: 可执行的后续步骤artifacts: 文件路径 / ID
错误恢复契约
对于每个错误路径，应包括：
- 根本原因提示
- 安全重试指令
- 明确的停止条件
上下文预算管理
- 保持系统提示词最少且不变。
- 将大量指导信息移至按需加载的技能中。
- 优先引用文件，而不是内联长文档。
- 在阶段边界处进行压缩，而不是任意的令牌阈值。
架构模式指导
- ReAct：最适合路径不确定的探索性任务。
- 函数调用：最适合结构化的确定性流程。
- 混合模式（推荐）：ReAct 规划 + 类型化工具执行。
基准测试
跟踪：
- 完成率
- 每项任务的重试次数
- pass@1 和 pass@3
- 每个成功任务的成本
反模式
- 太多语义重叠的工具。
- 不透明的工具输出，没有恢复提示。
- 仅输出错误而没有后续步骤。
- 上下文过载，包含不相关的引用。
Related Skills
affaan-m/unified-memory
development
VerifiedTrustedCommunity
Share durable, inspectable context and handoffs between Claude, Codex, Hermes, Cursor, OpenCode, and other agents through the local ECC Memory Vault. Use when an agent must save work state, transfer context, resume another agent's task, or search shared project knowledge.
234,238SKILL.mdUpdated Jul 28, 2026
affaan-m/contract-first
development
VerifiedTrustedCommunity
Use when multiple consumers and providers must evolve an API or event schema without field drift, integration surprises, or one side silently redefining the interface.
234,238SKILL.mdUpdated Jul 28, 2026
affaan-m/ito-compute
tools
VerifiedTrustedCommunity
Query live GPU inventory, submit an authenticated Itô fixed-rate RFQ, inspect RFQ or procurement status, and run explicitly gated node qualification through the separately installed canonical CLI. Use when a user asks to find H100/H200 capacity, request a fixed compute rate, check Itô compute status, or validate GPU nodes.
234,238SKILL.mdUpdated Jul 24, 2026
affaan-m/continuous-learning-v2
data-ai
VerifiedTrustedCommunity
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.
234,238SKILL.mdUpdated Mar 27, 2026