What do I need to use Source Interview Prep?

Who; What you need; The dynamic.

Is Source Interview Prep free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

Source Interview Prep

Q: How do I know the Source Interview Prep output is good?

The skill verifies itself against its own quality checks: Ground rules (on/off record, attribution) are defined and agreed before the hard part; Questions are sequenced rapport → record → core → hard, not front-loaded with accusations; The core asks are specific and answerable, tied to what the story needs; There's a concrete plan for evasive/hostile responses.

🔵 Stable🕐 updated 2026-10-06 🔷 SkillSpec L3 pm-journalism

Prepare a journalist to interview a source or subject — including hostile or accountability interviews. Use when a reporter needs to prep an interview with a source, plan questions for a subject, handle an on-the-record accountability interview, or get a reluctant person to talk. Produces a question plan sequenced from rapport to the hard asks, ground-rules handling (on/off record, attribution), techniques for evasive or hostile subjects, and a capture plan. Distinct from expert-interview-prep (learning from an expert).

▶ Run it free — no key needed 📝 Grade your existing draft ⬇ Add to Claude (works in Duet) 📱 Use as an app View SKILL.md ↗ What changed

🗣 Say this to your agent

“Plan questions for a subject.”“Handle an on-the-record accountability interview.”“Get a reluctant person to talk.”

What to give it

▸Who — you're interviewing and their relationship to the story (witness, expert, accountable party, whistleblower)

▸What you need — the facts, quotes, or confirmation this interview must produce

▸The dynamic — cooperative, reluctant, or adversarial; on/off record expectations

✅ The bar it holds itself to

Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.

✓Ground rules (on/off record, attribution) are defined and agreed before the hard part

✓Questions are sequenced rapport → record → core → hard, not front-loaded with accusations

✓The core asks are specific and answerable, tied to what the story needs

✓There's a concrete plan for evasive/hostile responses

✓Capture includes a recording-consent/legal note (laws vary by jurisdiction)

✓No advice to deceive, entrap, or misrepresent who you are

⚠️ What it refuses to do

Leading with the accusatory question (the subject shuts down or leaves)

Never settling on/off-record, then fighting about it later

Vague questions that invite a non-answer

Arguing with or editorializing at the subject instead of pressing on facts

No plan for the dodge — accepting the first evasion

Install

npx pm-claude-skills add --agent claude   # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y -p pm-claude-skills pm-claude-skills-mcp

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="source-interview-prep"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Source Interview Prep is one of 1326 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog