一键导入
spec
Interview the user one question at a time, walking the decision tree, to clarify a feature proposal before implementation
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。
菜单
Interview the user one question at a time, walking the decision tree, to clarify a feature proposal before implementation
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。
Stress-test the spec pipeline outputs against each other and the codebase before implementation begins
Authoritative guidance on modern Kotlin language features (2.2.0 through 2.3.21) — writing idiomatic code, reviewing or modernizing older code, and upgrading across the 2.2 → 2.3 line. Make sure to use this skill whenever the user mentions Kotlin 2.2, 2.2.20, 2.3, 2.3.0, 2.3.20, or 2.3.21, or any of these features: guard conditions in `when`, non-local `break`/`continue` in inline lambdas, multi-dollar string interpolation, context parameters, context-sensitive resolution, nested type aliases, the `@all` annotation use-site target, unused return value checker, explicit backing fields, name-based destructuring, data-flow exhaustiveness for `when`, or `return` in expression-body functions. Also trigger for compiler flags `-Xreturn-value-checker`, `-Xexplicit-backing-fields`, `-Xname-based-destructuring`; annotations `@MustUseReturnValues` and `@IgnorableReturnValue`; or any question framed as "what's new in Kotlin" or "latest Kotlin features."
基于 SOC 职业分类
| name | spec |
| description | Interview the user one question at a time, walking the decision tree, to clarify a feature proposal before implementation |
Walk down the decision tree, surfacing ambiguities, missing info, implicit assumptions, and edge cases through one-at-a-time questioning until the spec is implementable.
Pipeline position: proposal → spec → criteria → rules → review → plan
You prepare requirements for implementation by an AI coding agent.
Feature request: @file:spec/proposal.md
Scan the proposal and identify ambiguities, missing info, implicit assumptions, edge cases, and decision dependencies. Use this to plan interview order: root decisions first, then branch into details each answer reveals. Draft candidate behaviors to verify.
Only ask if the answer changes at least one of:
If none, decide it yourself and record under "Resolved ambiguities" or "Explicit assumptions" with the rationale. Trivial questions waste turns and erode trust in the interview.
The criteria step depends on this section as its primary handoff. Treat it as a contract.
Complete only when ALL hold:
A clean spec has ZERO open questions. Before writing, do a final verification pass. If any item fails, return to the interview loop.
If a decision genuinely requires input the user cannot give now (another stakeholder, blocked review, vendor response), record it under "External dependencies" with the question, blocker, and a proposed default. External dependencies are not open questions: they have a decision (the default) and a tracked path to resolution.
Write to spec/spec.md: