From work-session-tools
This skill should be used when the user asks to "walk through items", "review items one by one", "go through the list", "interview me on these", "let's address each item", "explore findings", says "/interview", or wants to systematically work through a presented list of items (code review findings, errors, contradictions, action items) ensuring nothing is missed.
How this skill is triggered — by the user, by Claude, or both
Slash command
/work-session-tools:interviewThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Walk through a list of items one by one using AskUserQuestion, ensuring every item gets a deliberate decision.
Walk through a list of items one by one using AskUserQuestion, ensuring every item gets a deliberate decision.
Identify all items from the conversation context. Consolidate if scattered. Number sequentially from 1.
**Interview: [N] items to address**
Starting walk-through. Each item will be presented for your decision.
Present each item one at a time via AskUserQuestion.
header: index + optional severity tag — "#3 HIGH" or "#3"question: "[Title]: [Description] — How to address?"options: actionable choices, recommended firstWhen an item involves code or config, use preview on options to show what each action produces (proposed fix, alternative implementation, before/after). Skip preview for trivial items.
AskUserQuestion({
questions: [{
question: "Missing null check in parse_config(): Line 42 dereferences config.timeout without None check — How to address?",
header: "#3 HIGH",
options: [
{
label: "Fix now (Recommended)",
description: "Add null check with sensible default",
preview: "def parse_config(path: str) -> Config:\n config = load_yaml(path)\n if config is None:\n return Config(timeout=30)\n return Config(timeout=config.timeout)"
},
{
label: "Raise error",
description: "Fail explicitly instead of defaulting",
preview: "def parse_config(path: str) -> Config:\n config = load_yaml(path)\n if config is None:\n raise ConfigError(f\"Missing: {path}\")\n return Config(timeout=config.timeout)"
},
{ label: "Skip", description: "Accept the risk" }
],
multiSelect: false
}]
})
After each response, acknowledge briefly and state progress:
#3 HIGH — Missing null check: **Fix now** (add null check with default)
Progress: 3/10 items addressed
Apply agreed actions after each item, or batch if user prefers.
**Interview Complete: [N]/[N] items addressed**
| # | Severity | Item | Decision |
|---|----------|------|----------|
| 1 | HIGH | Missing null check | Fix now |
| 2 | MED | Unused import | Fix now |
| 3 | LOW | Naming convention | Skip |
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub alex-kopylov/zweihander --plugin work-session-tools