بنقرة واحدة
interview
Interview users to convert rough ideas into structured specs. Use before starting non-trivial features.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
Interview users to convert rough ideas into structured specs. Use before starting non-trivial features.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
| name | interview |
| description | Interview users to convert rough ideas into structured specs. Use before starting non-trivial features. |
| context | fork |
| globs | [] |
| alwaysApply | false |
Use this skill to transform a rough idea into a structured spec before implementation. A 5-minute interview prevents hours of rework.
Invoke via the /sketch command:
/sketch Add a notification system so users get alerted when their order ships
Or trigger Athena directly:
@athena: Interview me about this feature: real-time dashboard for agent cost tracking
Ask questions in this priority order, stopping after you have enough clarity:
Rules:
Before writing the spec, summarize your understanding in 2–3 sentences and ask: "Does this match what you have in mind, or did I miss anything?"
Produce the spec only after getting confirmation.
# Feature Spec: <Feature Name>
**Date:** YYYY-MM-DD
**Status:** Draft
## Overview
<2–3 sentence description of the feature and its purpose>
## Goals
- <Goal 1>
- <Goal 2>
- <Goal 3>
## Non-Goals
- <What this feature explicitly does NOT cover>
- <Scope boundary 1>
- <Scope boundary 2>
## Functional Requirements
### Must Have (MVP)
- [ ] <Requirement 1>
- [ ] <Requirement 2>
- [ ] <Requirement 3>
### Should Have (v1.1)
- [ ] <Requirement 4>
### Won't Have (out of scope)
- <Explicitly excluded>
## Technical Constraints
- **Stack:** <relevant tech>
- **Integrations:** <APIs, services>
- **Performance:** <latency, throughput requirements if any>
- **Security:** <auth, data sensitivity>
## Success Criteria
- [ ] <Measurable outcome 1>
- [ ] <Measurable outcome 2>
## Open Questions
- [ ] <Unresolved decision 1>
- [ ] <Unresolved decision 2>
## Suggested Implementation Phases
1. **Phase 1:** <database/schema>
2. **Phase 2:** <backend API>
3. **Phase 3:** <frontend>
Hand off to Athena or Zeus with the completed spec:
@athena: Use this spec to create a TDD implementation plan:
[paste spec]
Or for immediate orchestration:
@zeus: Implement this feature based on the spec:
[paste spec]
Tool-agnostic search — query construction, tool selection, source trust hierarchy.
Auto-continue through todos with idle detection and safety gates. Use for multi-step orchestration.
Level 2 — Pantheon-native context compression with priority scoring, semantic summarization, downstream-aware compression, budget allocation, and cross-references
Automated visual review pipeline — Playwright screenshots, self-analysis, fix loop, escalation. Used by Aphrodite for UI verification.
Multi-agent orchestration with model routing, category delegation, and sprint management. Use for coordinating Pantheon agents.
MCP security hardening — credential leakage prevention, input sanitization, and tool access control. Use for reviewing agent MCP configurations.