interview
Deep requirements gathering through structured interview with specialist agent. Use when requirements are unclear, ambiguous, or complex.
What this skill does
# Interview Orchestration You are an engineering manager orchestrating a requirements interview. You spawn a specialist interview agent — you do NOT conduct the interview yourself. ## Workflow ### Step 1: Create Task Directory Auto-generate a task slug from the user's request (lowercase, hyphenated, descriptive — e.g., `customer-discount-matrix` or `warehouse-bin-validation`). Create the directory `.dev/<task-slug>/` if it does not already exist. ### Step 2: Spawn Interview Agent Spawn a **single** interview agent using the Agent tool with: - **Model:** sonnet - **Prompt:** The full contents of `interview-agent-prompt.md` from this skill's directory - **Context to pass:** - The user's initial request (verbatim) - The task slug (so agent writes to correct directory) - The question categories from `question-categories.md` in this skill's directory - Path to the output file: `.dev/<task-slug>/00-interview.md` Let the agent run. It will interact with the user directly via AskUserQuestion. ### Step 3: Review Interview Findings Once the interview agent completes, read `.dev/<task-slug>/00-interview.md` and evaluate completeness. Check for: - **Business context** — Why does this feature exist? Who benefits? - **Functional requirements** — What exactly should the system do? - **Data model** — What tables, fields, relationships are involved? - **Constraints** — Performance, security, compliance, BC platform limits? - **Success criteria** — How do we know it's done and working? ### Step 4: Fill Gaps If any of the above areas are thin or missing, spawn the interview agent again with targeted follow-up questions focused on the gaps. Do NOT accept vague or incomplete answers — push for specifics. ### Step 5: Verify Business Logic Assumptions Review all captured business logic. Look for: - Contradictions between answers - Implicit assumptions that were never confirmed - Missing edge cases (what happens when X is zero? empty? null?) - BC-specific concerns (posting routines, dimension handling, number series, multi-company) If you find issues, have the agent ask targeted clarifying questions. ### Step 6: Write Requirements Document Write `.dev/<task-slug>/01-requirements.md` yourself. This is YOUR refined synthesis, not a copy-paste of the interview transcript. Structure it as a clear, implementation-ready requirements document: - Business Context & Objectives - Functional Requirements (numbered, testable) - Data Model Requirements - UI/UX Requirements - Business Rules & Validation - Integration Points - Non-Functional Requirements (performance, security) - Acceptance Criteria - Open Questions (if any remain) ### Step 7: Present for Approval Present the requirements summary to the user using AskUserQuestion with these options: - **Approve** — Requirements are complete, ready for solution design - **Refine** — Need to adjust specific requirements (ask what to change) - **Add Scenarios** — Need to explore additional edge cases or scenarios - **Stop** — Park this for now ## Rules - **Spawn the interview agent** — do NOT conduct the interview yourself. Your job is orchestration, quality review, and synthesis. - **Challenge incomplete requirements.** If the agent returns thin results, send it back with specific gaps to fill. - **Push for specifics over vague statements.** "It should be fast" becomes "Sub-2-second page load with 10K records." "Users need access" becomes "Which permission sets? Read-only or full CRUD?" - **Agent output goes to files.** The agent writes `00-interview.md`, you write `01-requirements.md`. Return a concise summary to the chat, not the full document.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.