mohitagw15856/pm-claude-skills✦ 精选0°

agent-spec

仓库创建 2026年1月29日最近提交 13 小时前SkillHot 收录 20 天前

⬈ GitHub 仓库 ⬈ SKILL.md 原文件 ⬇ Raw 原始文件

▸ 精选理由

明确权限与失败处理，降低误用与越权风险

▸ 风险提示

若配置不当可导致代理拥有过大权限，应谨慎限制

这个 Skill 做什么

在构建前规范代理目标、工具、权限与守卫机制

在你要造一个会用工具或能自主决策的 AI 时，帮你把目标、权限和可用工具逐条写清楚；会输出目标范围、工具权限、控制循环、记忆与接手/升级规则、评估和失败处理方案。适合写 agent 规格书/PRD、划定哪些事必须人工批准或设计安全守卫时使用。特别之处是把“谁能干什么、什么时候需要人介入”写成明确规则，避免模型越权或工具滥用。

▸ 展开 SKILL.md 英文原文

Specify an autonomous or tool-using AI agent before building it. Use when asked to design an AI agent, define an agent's tools and guardrails, scope what an agent is allowed to do, or write an agent spec/PRD. Produces an agent spec — goal & scope, tools with permissions, the control loop, guardrails & approval gates, memory, escalation/handoff, evaluation, and failure handling.

Skill 开发管理代理规范权限与守卫控制回路通用

1.2k

Stars

220

Forks

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-spec/SKILL.md

或 curl 直取 SKILL.md

curl -fsSL "https://raw.githubusercontent.com/mohitagw15856/pm-claude-skills/main/skills/agent-spec/SKILL.md"

SKILL.MD 节选查看完整文件 ↗

# Agent Spec Skill

An agent is a model plus tools plus a loop — and the danger lives in the tools and the loop, not the
model. This skill specifies an agent so its *authority is explicit*: what it can do, what needs a human
yes, and what happens when it's wrong. Scope and guardrails first; cleverness second.

## Required Inputs

Ask for these only if they aren't already provided:

- **Job to be done** — the outcome the agent owns, and the boundary of its authority.
- **Tools/actions** — what it can call (read APIs, write actions, code execution), and which are irreversible.
- **Autonomy level** — fully autonomous, propose-then-approve, or co-pilot.
- **Risk surface** — what's the worst thin

via SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有