interview

A guided question-and-answer process that turns a vague request, ticket, or idea into a clear specification for a coding agent. TDD means test-driven development, but this description does not say that the process uses it.

In plain words
What is it for?
Use it to clarify feature requests, bug reports, Jira tickets, and project ideas into structured, actionable requirements.
Why use it?
It helps uncover missing requirements and ambiguities before coding begins, reducing misunderstandings and rework.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/fatihgune/interviewer/interview
Any agent
npx skills add fatihgune/interviewer --skill interview
Clone the repo
git clone --depth 1 https://github.com/fatihgune/interviewer

Made for: Claude Code, Codex.

Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,155 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00014 $0.01155
Opus 5 $0.00007 $0.00577
Sonnet 5 $0.00003 $0.00231
Haiku 4.5 $0.00001 $0.00115

Measured 2d ago against content hash a3f32f6d00fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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/interview/SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/interview

Interview that transforms vague requirements (Jira tickets, ideas, feature requests) into clear, structured specifications ready for a coding agent.

Usage

/interview <context>
/interview           (starts with no context, asks what to work on)

The <context> can be anything: a Jira ticket summary, a feature idea, a bug description, a pasted ticket body.

Instructions

When the user invokes this skill:

Step 1: Adopt the Interviewer Persona

Read agents/interviewer.md and adopt that role for the duration of the interview.

Step 2: Gather Initial Context

  • If the user provided context (ticket content, topic), use it as the starting point.
  • If no context was provided, ask: "What are we building or solving?"

Step 3: Brownfield Detection

Check the current working directory for project markers:

  • Use Glob to look for: package.json, pyproject.toml, go.mod, Cargo.toml, pom.xml, Gemfile, *.sln, Makefile, docker-compose.yml
  • If any exist, this is a brownfield project. Use Read/Glob/Grep to scan key files and understand the tech stack, patterns, and structure BEFORE asking the first question.
  • Incorporate what you find into your questions as confirmation-style: "I see X in the codebase. Should I assume Y?"

Step 4: Run the Interview Loop

Ask clarifying questions one at a time. Each question should target the biggest remaining source of ambiguity.

Present each question using AskUserQuestion with 2-3 contextually relevant suggested answers:

{
  "questions": [{
    "question": "<your question>",
    "header": "Q<N>",
    "options": [
      {"label": "<likely answer 1>", "description": "<brief context>"},
      {"label": "<likely answer 2>", "description": "<brief context>"}
    ],
    "multiSelect": false
  }]
}

Rules for generating options:

  • Binary questions (yes/no, greenfield/brownfield): use the natural choices
  • Technology choices: suggest common options relevant to the detected stack
  • Open-ended questions: suggest representative categories
  • The user can always type a custom response

Read the full file on GitHub · 148 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. 2d ago First seen · 148 lines · 14 tokens per session scan A a3f32f6d00fe

Subscribe to this mod's changes

interview is a skill published in the GitHub repository fatihgune/interviewer (1 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 1,155 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 2026-08-31.

Related

Other skills, from other repositories

epoch

Use Epoch for time estimation, business-day math, PERT/COCOMO/Monte Carlo forecasting, token cost comparison, schedule risk, and estimate-vs-actual feedback. Trigger when an agent needs realistic duration, deadline, model-cost, or planning calibration instead of a vibes-based guess.

KyaniteLabs/Epoch · 61 tokens

github-project-management

GitHub project management with issue tracking, project-board automation, and sprint planning. Use when triaging or organizing issues, automating a project board, planning a sprint, or running release/roadmap coordination on GitHub.

frankxai/claude-skills-library · 49 tokens

devflow-planning

AI-powered sprint planning, velocity analysis, and capacity forecasting. Use for planning sprints, predicting outcomes, and providing agile recommendations based on historical data.

Yoshikemolo/mcp-jira-devflow · 35 tokens

git-jira-integration

Integration between Git workflows and Jira issues. Generates branch names from issues, validates commit messages, and provides PR context from Jira specifications.

Yoshikemolo/mcp-jira-devflow · 32 tokens

git-operations

Git repository operations including branching, committing, pushing, and viewing history. Use for version control tasks. Destructive operations require explicit approval.

Yoshikemolo/mcp-jira-devflow · 31 tokens

jira-read

Read data from Jira including issues, comments, sprints, and execute JQL queries. Use when you need to fetch or search Jira data without making changes.

Yoshikemolo/mcp-jira-devflow · 35 tokens