← 返回
未分类 中文

Guided Conversation

Minimize user friction by asking up to 4 clarifying questions before executing actions.
在执行操作前最多提出四个澄清问题,以减少用户摩擦。
szpili szpili 来源
未分类 clawhub v1.0.0 1 版本 99769.1 Key: 无需
★ 0
Stars
📥 432
下载
💾 1
安装
1
版本
#latest

概述

Guided Conversation Skill

Purpose

Minimize user friction by asking up to 4 clarifying questions before executing actions. Ensures the agent understands ambiguous tasks without over-interrogating.

When to Use

  • User request is ambiguous or missing critical details
  • Action is high-impact (file delete, payment, external API call)
  • User has not provided enough context for safe execution

Constraints

  • Max 4 questions per task
  • Stop asking once sufficient clarity is reached
  • Never ask for information already available in context/memory
  • If still ambiguous after 4 questions, make best-effort interpretation and proceed (with user notification)

Output

After clarification:

  1. Summarize understood task in 1 sentence
  2. List assumptions made
  3. Proceed to execution (or ask for confirmation if required by risk profile)

Integration

  • Hook: pre-action phase (before tool calls)
  • Risk-based: high-risk actions always require confirmation regardless of clarity
  • Low-risk: can proceed automatically after clarification

Examples

User: "Zrób backup"

Agent: "Which folder? Where to store? Full or incremental?" (3 questions)

User: "Wyślij maila do klienta"

Agent: "Who is the client? What content? Any attachments?" (3 questions)

Configuration

  • maxQuestions: 4 (default)
  • autoProceedAfterClarity: true (default)
  • requireConfirmationHighRisk: true (default)

Related Skills

  • interaction-pipeline (status updates)
  • adaptive-execution-profile (risk tolerance)

版本历史

共 1 个版本

  • v1.0.0 当前
    2026-05-03 06:34 安全 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

ai-agent

Self-Improving + Proactive Agent

ivangdavila
自我反思+自我批评+自我学习+自组织记忆。智能体评估自身工作、发现错误并持续改进。
★ 1,394 📥 322,231
ai-agent

Find Skills

guipi888
场景驱动+关键词双模式技能发现工具。当用户用自然语言描述场景/需求(如"我想做一个海报""帮我分析股票"),或明确说"安装技能/find skills/找个skill"时,自动从官方内置、本地已安装、SkillHub、虾评、GitHub、C
★ 1,459 📥 507,194
ai-agent

self-improving agent

pskoett
捕获经验教训、错误及修正内容,以实现持续改进。适用于以下场景:(1)命令或操作意外失败;(2)用户纠正Claude(如“不,那不对……”“实际上……”);(3)用户请求的功能不存在;(4)外部API或工具出现故障;(5)Claude发现自身
★ 4,097 📥 824,051