Agent Skills › kdlbs/kandev › interview-me

interview-me

GitHub

在需求或设计前澄清意图、检查假设,通过依赖顺序提问解决未决决策。用于大型不确定项目的压力测试和意图确认,避免盲目执行。

.agents/skills/interview-me/SKILL.md kdlbs/kandev

Trigger Scenarios

进行功能或修复规划前的假设检查 对大型不确定项目进行意图澄清和压力测试

Install

npx skills add kdlbs/kandev --skill interview-me -g -y
More Options

Non-standard path

npx skills add https://github.com/kdlbs/kandev/tree/main/.agents/skills/interview-me -g -y

Use without installing

npx skills use kdlbs/kandev@interview-me

指定 Agent (Claude Code)

npx skills add kdlbs/kandev --skill interview-me -a claude-code -g -y

安装 repo 全部 skill

npx skills add kdlbs/kandev --all -g -y

预览 repo 内 skill

npx skills add kdlbs/kandev --list

SKILL.md

Frontmatter
{
    "name": "interview-me",
    "description": "Clarify a standalone idea or check assumptions before feature or fix planning. Use focused questions, stress-test intent, and map unresolved decisions for large uncertain initiatives."
}

Interview Me

Run the assumption check before requirements, system designs, or implementation plans. Reuse settled answers throughout the design package. An assumption check does not require an interview when the material choices are already clear.

For a standalone interview or stress test, clarify intent without automatically creating a design package. Skip this workflow for mechanical edits and pure information requests.

1. Check assumptions

Read the request, relevant specifications, source, and tests. Separate:

  • Confirmed: the user explicitly requested or previously settled it.
  • Verified: source, tests, or documentation establish a fact. Keep its source reference and distinguish current behavior from intended behavior.
  • Unresolved: a choice or missing fact can change behavior, scope, ownership, permissions, persistence, compatibility, or acceptance criteria.

State the intended outcome and material unresolved assumptions briefly. Do not invent confidence percentages. Investigate facts that available tools can resolve before asking the user. Evidence of current behavior is not user agreement to preserve it.

Ask about consequential choices that evidence cannot settle. Choose routine, reversible implementation details within the agreed scope. A request for speed reduces questions; it does not make an unanswered material choice confirmed.

For a clear regression, use the active acceptance criterion without asking the user to define the behavior again.

2. Ask questions in dependency order

Identify which decisions depend on other answers. Ask only questions whose prerequisites are settled. Use the active harness's user-question tool and obey its limits and waiting rules. Ask one to four independent questions per round, within those limits. Without a question tool, ask one question at a time in chat during a normal interactive session.

If this is an autopilot root or another non-interactive session with no question tool, record each unresolved material choice as an assumption. Continue only when the caller permits autonomous planning for that choice and use the most conservative reversible option. Otherwise return the assumption as a blocker to the caller. Never present an assumption as confirmed, and preserve the normal chat fallback for interactive sessions.

Give each question concrete options, a recommended answer, and a short reason. Align the question with the recommendation so agreement has one clear meaning. Do not ask the user to locate code or supply facts you can investigate.

For example, first settle what "preserve task context" includes. Ask about retention duration only after the user chooses persistent context.

Wait for answers before resolving dependent choices. After each round, update the remaining questions. If an answer changes an earlier assumption, revisit the affected choices and artifacts. Do not repeat settled questions without new evidence or changed scope.

If the initiative has too many dependent unknowns to specify reliable work orders, use decision mapping. Ordinary features and clear fixes do not need a map.

3. Stress-test the answers

Use concrete scenarios to expose material gaps in success, failure, recovery, and scope. Select scenarios relevant to the request; do not invent adjacent features or an exhaustive questionnaire.

Challenge vague terms such as "robust" with an observable outcome. Compare domain terms with the owning specifications and any existing glossary. If a term or claimed behavior conflicts with those sources, name the conflict and resolve it.

Distinguish uncertainty that needs evidence from a choice that needs the user. If a design question needs an experiment, define the question and observable result first. Keep prototypes temporary and separate from production changes. Record what the experiment proves and what remains undecided.

4. Capture decisions and continue

After each answer, preserve the choice and its reason in the current task notes. Use the Kandev task plan when available, preserving user edits. Do not create a separate intent document unless requested.

During authorized specification or planning work, put settled behavior in the owning requirement and technical contracts in its system design. Use /record for significant decisions that meet its ADR criteria. Preserve meaningful alternatives and rationale there. Update an existing glossary when terminology changes; do not introduce a parallel glossary by default.

Keep unresolved choices visibly unresolved. A recommendation, silence, or timeout is not confirmation. If the user explicitly delegates a choice, record the selected option as an agent decision made under that delegation.

When intent is clear and no material choice blocks the next design phase, finish the interview. This includes success criteria, constraints, and scope. Explicit answers and prior instructions count as confirmation; do not require a second approval of their restatement. If broad intent remains ambiguous, ask about the specific remaining gap before continuing.

Summarize the settled intent and exclusions. If another skill called this check, return to its current phase without restarting specification or planning. For a direct planning request, continue through /spec and /plan to the existing design-package handoff. For a standalone interview, return the clarified intent. Neither path authorizes implementation or delegation.

Version History

  • d324d49 Current 2026-09-22 09:45

    优化规划阶段的假设检查流程,移除置信度百分比要求,改进非交互会话的处理逻辑。

  • 0e4ae86 2026-08-27 18:28
  • b4239d8 2026-07-24 17:32

Same Skill Collection

.agents/skills/acp-debug/SKILL.md
.agents/skills/add-integration/SKILL.md
.agents/skills/clean-branches/SKILL.md
.agents/skills/code-review/SKILL.md
.agents/skills/commit/SKILL.md
.agents/skills/context-engineering/SKILL.md
.agents/skills/create-kandev-plugin/SKILL.md
.agents/skills/debug/SKILL.md
.agents/skills/docs-maintainer/SKILL.md
.agents/skills/e2e/SKILL.md
.agents/skills/fix/SKILL.md
.agents/skills/harness-improvement/SKILL.md
.agents/skills/plan/SKILL.md
.agents/skills/planner-orchestration/SKILL.md
.agents/skills/playwright-cli/SKILL.md
.agents/skills/pr-fixup/SKILL.md
.agents/skills/pr-walkthrough/SKILL.md
.agents/skills/pr/SKILL.md
.agents/skills/product-demo-seeding/SKILL.md
.agents/skills/product-video-capture/SKILL.md
.agents/skills/push/SKILL.md
.agents/skills/qa/SKILL.md
.agents/skills/record/SKILL.md
.agents/skills/release/SKILL.md
.agents/skills/runtime-feature-flags/SKILL.md
.agents/skills/simplify/SKILL.md
.agents/skills/spec-driven-development/SKILL.md
.agents/skills/spec/SKILL.md
.agents/skills/tdd/SKILL.md
.agents/skills/using-agent-skills/SKILL.md
.agents/skills/verify/SKILL.md
.agents/skills/diagram-design/SKILL.md
.agents/skills/mobile-parity/SKILL.md

Metadata

Files
0
Version
359b5ff
Hash
e1adf676
Indexed
2026-07-24 17:32

ホーム - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-09-29 05:41
浙ICP备14020137号-1