interview-framework
仓库创建 2026年1月12日最近提交 4 天前SkillHot 收录 21 天前
▸ 精选理由
结构化访谈算法,能在规格各阶段高效收集澄清信息。
这个 Skill 做什么
用于交互式需求访谈,按相位引导问题并生成选项化决策路径。
用来做交互式需求访谈,按“理解问题—提出方案—确认并存档”三阶段引导对话,边问边给用户 2–4 个有针对性的选项来缩小范围。适合在正式写 spec 或分配任务前,通过对话厘清需求和优先级。特点是结构化且可选项限制在 2–4 个,方便快速达成共识并把结论记进记忆库。
▸ 展开 SKILL.md 英文原文
This skill should be used when running an interactive interview before a spec phase, gathering requirements through dialogue, asking the user clarifying questions before delegating to a subagent, or when any Ralph phase command (research, requirements, design, tasks) needs adaptive brainstorming dialogue. Covers the 3-phase algorithm (Understand, Propose Approaches, Confirm and Store).
431
Stars
37
Forks
30
仓库内 Skill
+16
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/tzachbon/smart-ralph/main/plugins/ralph-specum/skills/interview-framework/SKILL.md或 curl 直取 SKILL.md
curl -fsSL "https://raw.githubusercontent.com/tzachbon/smart-ralph/main/plugins/ralph-specum/skills/interview-framework/SKILL.md"SKILL.MD 节选查看完整文件 ↗
# Interview Framework
Adaptive brainstorming dialogue algorithm for all spec phases. Each phase command provides its own exploration territory (phase-specific areas to probe).
## Option Limit Rule
Each question must have 2-4 options (max 4). Keep the most relevant options, combine similar ones.
## Recommendation Format
Every question asked via `AskUserQuestion` in Phase 1 leads with the recommended option (except when options are symmetric, in which case `[Recommended]` may be omitted):
```yaml
AskUserQuestion:
question: "[Context-aware question referencing prior answers]. [One sentence rationale for the recommendation.]"
options:
- "[Recommended] [Option text -- the AI's suggevia SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有