spec-interview

spec-interview is a skill for Claude Code from jellydn/my-ai-tools. It costs 18 tokens per session (1,829 once invoked), scanned A, original, MIT.

A requirements interview tool that asks targeted questions when a feature description is incomplete or ambiguous.

In plain words
What is it for?
It is for reviewing a proposed feature, finding gaps, and clarifying requirements that could change the design or implementation.
Why use it?
It exposes missing decisions about scope, user experience, technical choices, architecture, and edge cases before they cause rework.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions Codex; built for cline; mentions OpenCode.

Good fit It is for reviewing a proposed feature, finding gaps, and clarifying requirements that could change the design or implementation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jellydn/my-ai-tools/spec-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 jellydn/my-ai-tools --skill spec-interview
Clone the repo
git clone --depth 1 https://github.com/jellydn/my-ai-tools

Made for: Claude Code.

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 spec-interview

README.md
[![agentmods](https://agentmods.dev/badge/skills/jellydn/my-ai-tools/spec-interview/github.svg)](https://agentmods.dev/skills/jellydn/my-ai-tools/spec-interview)
Your own site
<a href="https://agentmods.dev/skills/jellydn/my-ai-tools/spec-interview"><img src="https://agentmods.dev/badge/skills/jellydn/my-ai-tools/spec-interview/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for spec-interview

Your own site · 80×15
<a href="https://agentmods.dev/skills/jellydn/my-ai-tools/spec-interview"><img src="https://agentmods.dev/badge/skills/jellydn/my-ai-tools/spec-interview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,829 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00018 $0.01829
Opus 5 $0.00009 $0.00915
Sonnet 5 $0.00004 $0.00366
Haiku 4.5 $0.00002 $0.00183

Measured 9d ago against content hash 371f6c225c08, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

spec-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 9d 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.

configs/amp/plugins/my-ai-tools-skills/skills/spec-interview/SKILL.md · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Interview

When to Use

Use this skill when:

  • Feature requirements are vague or incomplete
  • You have a general idea but lack specifics
  • Stakeholders said "you know what I mean"
  • The spec has obvious gaps
  • Making assumptions that could be wrong

What It Does

The agent interviews you to uncover unknown unknowns in your feature specification, focusing on questions that would change architectural decisions.

How to Execute

Step 1: Review Initial Spec

Analyze what the user provided:

  • Explicit requirements (what they said)
  • Implicit requirements (what they assumed)
  • Missing details
  • Ambiguous areas

Step 2: Categorize Gaps

Identify question categories:

Scope & Boundaries:

  • What's in scope vs out of scope?
  • Edge cases to handle?
  • MVP vs future iterations?

User Experience:

  • What happens when...?
  • Error states and recovery?
  • Loading and async states?

Technical Decisions:

  • Performance requirements?
  • Data consistency needs?
  • Integration points?
  • Security considerations?

Architecture Impact:

  • Does this change existing patterns?
  • New abstractions needed?
  • Migration strategy for existing data?

Step 3: Prioritize Questions

Sort by impact on implementation:

  1. Architecture-changing: Would change core approach
  2. High-impact: Significant implementation difference
  3. Medium-impact: Affects specific modules
  4. Low-impact: Nice to clarify but not blocking

Step 4: Conduct Interview (One Question at a Time)

Use the ask_user_question tool for each question. Ask one question at a time — present it, wait for the answer, then proceed to the next. This keeps the interview focused and lets the user's answer to one question influence follow-ups.

Guidelines for using ask_user_question:

  • Set header to a short category label (max 16 chars), e.g. "Architecture", "Scope", "UX", "Edge Cases"
  • Write a clear question string with context about why you're asking
  • Provide 2-4 concrete options with concise label (1-5 words) and descriptive description explaining trade-offs
  • After the user answers, acknowledge the choice and explain how it impacts the implementation before asking the next question
  • Architecture-changing questions first, then high-impact, then medium-impact

Read the full file on GitHub · 236 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. 9d ago First seen · 236 lines · 18 tokens per session scan A 371f6c225c08

Subscribe to this mod's changes

spec-interview is a skill published in the GitHub repository jellydn/my-ai-tools (119 stars, last pushed 3d ago), licensed MIT. It adds 18 tokens to every session and 1,829 once invoked, about $0.0001 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 2026-08-30.