What do I need to use Discovery Call Prep?

Prospect company name; Contact name and role; Any known context; Your product / solution; Call duration.

Is Discovery Call 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.

Discovery Call Prep

Q: How do I know the Discovery Call Prep output is good?

The skill verifies itself against its own quality checks: Research summary includes recent news (last 90 days) — not just LinkedIn bio; Call hypothesis is written before the call (not post-rationalised after); Discovery questions progress from context → pain → business impact → buying process; Success criteria define what "not successful" looks like (not just the ideal outcome).

🔵 Stable🕐 updated 2026-06-08 🔷 SkillSpec L3 pm-sales

Prepare a structured discovery call plan for any prospect. Use when asked to prepare for a sales call, discovery call, prospect meeting, or first call with a potential customer. Produces a call brief with research, hypotheses, questions, and success criteria.

▶ Run it free — no key needed 📝 Grade your existing draft View SKILL.md ↗

🗣 Say this to your agent

“Prepare me for a discovery call with [company/contact]”“Build a call brief for my meeting with [name] at [company]”“What questions should I ask in a discovery call for [use case]?”

What to give it

▸Prospect company name

▸Contact name and role

▸Any known context — how they found you, prior interaction

▸Your product / solution — one line

▸Call duration — 15 / 30 / 45 / 60 min

✅ 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.

✓Research summary includes recent news (last 90 days) — not just LinkedIn bio

✓Call hypothesis is written before the call (not post-rationalised after)

✓Discovery questions progress from context → pain → business impact → buying process

✓Success criteria define what "not successful" looks like (not just the ideal outcome)

✓A specific next step is proposed (not "let's stay in touch")

⚠️ What it refuses to do

Do not write the call hypothesis after the call — hypotheses written post-hoc are rationalisations, not testable predictions

Do not open with a product pitch before establishing the prospect's problem — leading with pitch signals you are not there to learn, which closes discovery conversations

Do not use closed questions in the discovery phase ("Do you have this problem?") — they produce yes/no answers that confirm bias rather than reveal pain

Do not skip the "not successful" definition in success criteria — a call that ends with "send me more info" feels like progress but is not a qualified next step

Do not treat all prospect research equally — recent news (last 90 days) is more relevant to call context than static company facts from LinkedIn

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 pm-claude-skills-mcp

Start with

Related skills

🔌 Embed this skill

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

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

💬 Discussion

Discovery Call Prep is one of 1153 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog