deep-interview

deep-interview is a skill for Claude Code from vigneshbarani24/sap-superpowers. It costs 49 tokens per session (1,605 once invoked), scanned A, original, MIT.

A structured interview skill for gathering complete requirements for an SAP project, feature, or change. It asks follow-up questions about assumptions, constraints, decisions, and unusual cases.

In plain words
What is it for?
Use it before development or configuration work to clarify the business context, expected behavior, constraints, and rejected alternatives, then produce a reviewable requirements document.
Why use it?
It reduces unclear requirements, missed edge cases, and scope changes caused by building from incomplete answers.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the sap-superpowers plugin — 61 skills, 8 commands, 15 agents, 5 hooks shipped together

Good fit Use it before development or configuration work to clarify the business context, expected behavior, constraints, and rejected alternatives, then produce a reviewable requirements document.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vigneshbarani24/sap-superpowers/deep-interview
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add vigneshbarani24/sap-superpowers --skill deep-interview
Clone the repo
git clone --depth 1 https://github.com/vigneshbarani24/sap-superpowers

Made for: Claude Code.

Or install sap-superpowers, the plugin that ships this one along with the rest of its 61 skills, 8 commands, 15 agents, 5 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for deep-interview

README.md
[![agentmods](https://agentmods.dev/badge/skills/vigneshbarani24/sap-superpowers/deep-interview.svg)](https://agentmods.dev/skills/vigneshbarani24/sap-superpowers/deep-interview)
Your own site
<a href="https://agentmods.dev/skills/vigneshbarani24/sap-superpowers/deep-interview"><img src="https://agentmods.dev/badge/skills/vigneshbarani24/sap-superpowers/deep-interview.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,605 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.01605
Opus 5 $0.00024 $0.00803
Sonnet 5 $0.00010 $0.00321
Haiku 4.5 $0.00005 $0.00161

Measured 7d ago against content hash 3bda7c67ad11, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

deep-interview scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/consulting/deep-interview/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Interview — Structured Requirements Gathering

This skill conducts a systematic interview to extract complete requirements from the user. It uses Socratic questioning — never accepting the first answer, always probing for edge cases, constraints, and unstated assumptions.

Iron Laws

  1. NEVER ACCEPT THE FIRST ANSWER AS COMPLETE. The user's first description of what they want is always incomplete. Probe deeper. Ask "what happens when..." and "what if..." until edge cases are surfaced.

  2. NEVER ASSUME BUSINESS CONTEXT. If the user says "we need a report," do not assume the audience, frequency, format, or authorization model. Ask.

  3. ALWAYS DOCUMENT DECISIONS AND ALTERNATIVES REJECTED. When a design choice is made during the interview, document what was chosen AND what was explicitly rejected. This prevents re-litigation later.

  4. ALWAYS PRODUCE A REQUIREMENTS DOCUMENT. The interview output is a structured document, not a conversation summary. It must be reviewable, signable, and traceable.

  5. NEVER LEAD THE WITNESS. Do not suggest answers in your questions. "Should we use RAP?" is leading. "What is the target UI technology and why?" is not.

Rationalization Table

Agent Will Try To... Why It Seems Reasonable Why It Fails Counter
Start coding after the first requirement "I have enough to start prototyping" Prototyping from incomplete requirements produces throwaway code that somehow becomes production code. Complete the interview first. All 7 dimensions.
Suggest solutions during requirements "I can guide them to the right approach" Suggesting solutions during requirements gathering biases the requirements toward that solution. Iron Law 5. Gather requirements first. Design later.
Skip non-functional requirements "Performance and security can be added later" NFRs that aren't requirements become constraints discovered in production. Cover all 7 dimensions. NFRs are not optional.
Accept "same as the old report" "They know what they want" "Same as" means "similar to" plus 47 unstated changes. What specifically is the same? What's different? What's missing?

Read the full file on GitHub · 157 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 157 lines · 49 tokens per session scan A 3bda7c67ad11

Subscribe to this mod's changes

deep-interview is a skill published in the GitHub repository vigneshbarani24/sap-superpowers (9 stars, last pushed 15d ago), licensed MIT. It adds 49 tokens to every session and 1,605 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

add-linear

Add Linear channel integration via Chat SDK. Issue comment threads as conversations.

nanocoai/nanoclaw · 17 tokens

add-github

Add GitHub channel integration via Chat SDK. PR and issue comment threads as conversations.

nanocoai/nanoclaw · 21 tokens

slack-construct-agents

Standing context for Slack sibling agents — one room per team, creator-posted introductions, bot-to-bot hop discipline. Ships as instructions.md composed into the group's CLAUDE.md at spawn; there is no workflow to invoke.

nanocoai/nanoclaw · 53 tokens

sap-expert

Expert in SAP ERP systems, ABAP programming, SAP HANA, S/4HANA, Fiori applications, and SAP integration patterns including OData, RFC, and IDoc. Use when the user mentions ERP, enterprise, business apps, ABAP, HANA, or S/4HANA, or when the task involves SAP Ecosystem, ABAP Development, Integration Technologies, or…

personamanagmentlayer/pcl · 92 tokens

roadmap-interview

Run a short product-discovery interview with a user of Kochab to surface what they actually need, then turn it into structured roadmap input. Use when someone says "interview me about features," "run the roadmap interview," "I have feedback on the tool," "what should this tool do next," or when a maintainer wants to…

btmoriarty/kochab · 105 tokens

eso-guild-social-manager

Creates, updates, and uses ESO GUILD.md files for guild discovery and social planning. Use when finding, evaluating, joining, tracking, or interacting with ESO guilds.

Neetx/eso-skills · 41 tokens