skills/interview/SKILL.md
Interview user in-depth to elicit requirements, clarify ideas, and surface blind spots. Use when user is vague about what they want, starting a new feature, or needs help thinking through a problem.
npx skillsauth add ardasevinc/agent-devtools interviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Socratic interviewer that elicits requirements through non-obvious, probing questions. Helps surface blind spots, challenge assumptions, and crystallize vague ideas into actionable understanding.
$ARGUMENTS provided, use as starting topicCover these systematically - they're the common blind spots:
Periodically (every 3-5 questions or when switching domains) show a structured summary:
## Current Understanding
**Core concept**: ...
**Key decisions**:
- ...
**Open questions**:
- ...
**Tensions/risks**:
- ...
Ask if anything needs correction before continuing.
When answers reveal the thing is bigger than initially thought:
Exit when:
On exit:
You have full tool access. Use it to inform your questions:
Ground your questions in reality when relevant codebase context exists.
User-triggered: /interview build a notification system
Claude-suggested: When user is vague or starting something new, you may suggest:
"Want me to interview you on this to clarify requirements before we start?"
Do NOT auto-invoke without asking.
User: /interview
Claude: No topic provided - I see we've been discussing auth. Want me to interview you about the authentication system, or something else?
User: yeah the auth thing
Claude: Got it. Let's explore the auth system.
**Starting broad** - thinking about the basics first: you're adding auth to something, but the "why" shapes everything. Is this security theater for a demo, or do you have real adversarial concerns?
[Uses AskUserQuestion tool]
Question: "What's the context for this auth system?"
Options:
- New app from scratch
- Replacing existing auth
- Adding to existing app without auth
User: [selects "New app from scratch"]
Claude: New app - clean slate, nice. That means no migration headaches but also no existing session infrastructure to lean on.
[Uses AskUserQuestion tool]
Question: "What's your token strategy preference?"
Options:
- JWT (stateless)
- Session cookies (server-side state)
- Not sure yet
[... several rounds mixing discussion + AskUserQuestion ...]
Claude:
## Current Understanding
**Core concept**: JWT-based auth with refresh tokens, social login (Google/GitHub)
**Key decisions**:
- Stateless tokens, no server-side sessions
- Refresh tokens stored in httpOnly cookies
- Social login optional, email/password required
**Open questions**:
- Password reset flow?
- Rate limiting on login attempts?
**Tensions/risks**:
- "Stateless" but also want to revoke tokens - need to reconcile
Want me to dig into the open questions, or does this need correction?
[... continues until done ...]
<instructions>$ARGUMENTS</instructions>
development
Review dense SaaS, ops, security, observability, admin, or compliance dashboards with evidence-first UX and design findings. Use when the user asks to improve dashboard readability, information density, tables, filters, charts, freshness, or operational workflows.
testing
Browse and load skills on-demand from ~/.agents/lazy-skills without exposing every skill description to the base agent. Use when the user explicitly asks for a lazy skill or a capability that should be loaded only on demand.
testing
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".
testing
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).