agent-design-review
仓库创建 2026年1月29日最近提交 14 小时前SkillHot 收录 20 天前
▸ 精选理由
快速定位导致循环、滥用工具或成本失控的设计缺陷
▸ 风险提示
可能被用于增强有害自动化系统的攻击面
这个 Skill 做什么
评估代理架构，找出不可靠、昂贵或不安全的设计点
把一个多步、会调用工具的 LLM 代理从可靠性、成本和安全角度拆开评审：检查任务适配、控制流、工具接口、记忆/context、失败处理和费用点，并给出按优先级排序的修复建议。上线前硬化、排查代理死循环或跑偏、或在设计阶段要降低风险时用。重点不是模型强弱，而是发现那些会让代理失控或变昂贵的设计决策。
▸ 展开 SKILL.md 英文原文
Review an LLM agent design and find where it will be unreliable, expensive, or unsafe. Use when asked to review an agent architecture, critique a multi-step/tool-using agent, debug an agent that loops or goes off-task, or harden an agent before launch. Produces a structured review — task fit, control flow, tools, memory/context, failure handling, cost, and safety — with prioritised findings and fixes.
1.2k
Stars
220
Forks
40
仓库内 Skill
+74
7 日增星
安装 / 使用
给你的 Agent 一句话（通用）
帮我安装这个 skill：https://raw.githubusercontent.com/mohitagw15856/pm-claude-skills/main/skills/agent-design-review/SKILL.md或 curl 直取 SKILL.md
curl -fsSL "https://raw.githubusercontent.com/mohitagw15856/pm-claude-skills/main/skills/agent-design-review/SKILL.md"SKILL.MD 节选查看完整文件 ↗
# Agent Design Review Skill
Most agents don't fail because the model is weak — they fail because the *design* lets them loop, call the
wrong tool, lose the thread across steps, or burn tokens with no stopping rule. This skill reviews an agent's
architecture against the decisions that actually determine reliability, and ranks the fixes — so "it works in
the demo but not in prod" becomes a specific list of changes. (Writing a new agent spec? Use
[`agent-spec`](../agent-spec/SKILL.md).)
## Working from a brief
Given a sketch ("a research agent that searches, reads, and writes a report"), **deliver the full review
anyway** — infer the likely control flow and tools, label the inference, and flvia SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有