菜单
How to run the two-round multiple-choice discovery questionnaire. Defines the 30 default round-1 questions across 6 categories, how to adapt them per project type, and how to generate the 15 round-2 follow-ups from gaps and contradictions.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Guidance for picking the right model per role ("droid whispering"). Activate when configuring agents, starting a new mission, or diagnosing why a role is misbehaving. Model strings age fast — verify current names via search per P-2 before relying on the defaults below.
How to set up every external service the project needs WITHOUT asking the user to run commands or follow long tutorials. The orchestrator handles all installation, configuration, MCP setup, and verification. The user provides only the data the orchestrator cannot obtain itself (credentials, choices). MCP servers are preferred over raw API integration where available.
How to produce the validation contract, draft plan, and tech-decisions from the description and discovery answers. Web-searches for current versions before committing to anything. Targets fine-grained feature decomposition (more features = better). Features here are DRAFTS — the /mission-tasks phase enriches them. Activate during /mission-plan.
Mandatory handoff template every worker fills out before exiting. The pre-worker-exit hook validates this file and blocks the worker if anything is missing. Activate inside any worker subagent.
Per-feature 20-question interrogation that turns a draft feature spec into a fully-specified one. Three rounds — 10 task questions, 5 follow-ups, 5 "definition of done" questions. Each question has 4 options with one ★ recommended based on context. Activate during /mission-tasks.
Format and quality rules for the validation contract — the flat, numbered, falsifiable assertion list every feature must satisfy. Activate when planning a mission or when validating one.
| name | discovery-questions |
| description | How to run the two-round multiple-choice discovery questionnaire. Defines the 30 default round-1 questions across 6 categories, how to adapt them per project type, and how to generate the 15 round-2 follow-ups from gaps and contradictions. |
The discovery phase produces shared understanding before any planning. Two rounds:
Every question has exactly 4 lettered options. The user may also write a
custom answer for any question (7: custom — ...).
Emit all questions of a round in one message. Use this structure:
# Discovery — Round 1 of 2 (30 questions)
Reply with one line per question: `1: a`, `2: c`, etc.
For a question where none of the options fit, write your own: `7: custom — internal teams plus selected partners`.
---
## A. Users & Access
**1. Who are the primary users?**
- (a) Internal team only
- (b) External customers (B2C or B2B)
- (c) Public / anonymous OK
- (d) Mixed — some signed-in, some public
**2. Expected user count at v1?**
- (a) <10
- (b) 10–1,000
- (c) 1,000–100,000
- (d) >100,000
... and so on
Keep options short (≤8 words each) and mutually exclusive within a question.
Adapt these per project type — see "Adapting" below.
Use the description.md to detect the project type and swap entire categories or specific questions:
When you adapt, keep the 30-question total and the 6-category structure. Note any substitutions in a header comment at the top of round-1.md.
After parsing round-1 answers, identify gaps using these heuristics:
Compose exactly 15 follow-ups that maximize information gain. Each must have 4 lettered options.
Same single-message structure as round 1, but with a 1-line preamble at the top:
# Discovery — Round 2 of 2 (15 follow-ups)
Based on your round-1 answers, these gaps need clarifying.
---
# Discovery Round 1
_Captured: <UTC>_ _Adaptations from defaults: <none | list>_
## A. Users & Access
**1. Who are the primary users?**
- (a) Internal team only
- (b) External customers (B2C or B2B) ← chosen
- (c) Public / anonymous OK
- (d) Mixed — some signed-in, some public
**2. Expected user count at v1?**
- (a) <10
- (b) 10–1,000 ← chosen
- (c) 1,000–100,000
- (d) >100,000
...
Custom answers go below the four options as ← custom: <user text>.