What do I need to use Brief Builder?

The raw ask; Who is asking and who will consume the output.

Is Brief Builder 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.

Brief Builder

Q: How do I know the Brief Builder output is good?

The skill verifies itself against its own quality checks: Questions are asked a few at a time, highest-leverage first — not a giant wall; Vague answers are followed up until concrete (named audience, real dates, specifics); Sensible defaults are offered when the user is unsure, and labeled as assumptions; The interview stops once there's enough — it doesn't over-interrogate.

🔵 Stable🕐 updated 2026-07-08 🔷 SkillSpec L3 pm-cross

Interview the user with sharp, one-at-a-time questions to turn a vague request into a tight, complete brief any other skill can run on. Use when a request is fuzzy, under-specified, or 'help me think this through', or before running a skill that needs inputs the user hasn't given. Produces a structured brief (goal, audience, constraints, success criteria) and hands off to the right skill — by interrogating, not guessing.

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

What to give it

▸The raw ask — whatever the requester actually said, however vague ("we need a dashboard", "marketing wants a one-pager"). Verbatim beats paraphrased; the gaps in their words are the interrogation map.

▸Who is asking and who will consume the output — (if known) — the same ask from a CEO and an intern needs different briefs.

✅ 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.

✓Questions are asked a few at a time, highest-leverage first — not a giant wall

✓Vague answers are followed up until concrete (named audience, real dates, specifics)

✓Sensible defaults are offered when the user is unsure, and labeled as assumptions

✓The interview stops once there's enough — it doesn't over-interrogate

✓The final brief is complete enough that another skill could produce great output from it alone

✓It ends by handing off to the right skill(s)

⚠️ What it refuses to do

Do not produce the deliverable yourself from a vague prompt — the job is to build the brief first

Do not dump 15 questions at once — pace them, lead with what matters most

Do not accept vague answers — "more sales", "everyone", "soon" all need a follow-up

Do not interrogate forever — once you can write a strong brief, stop and summarize

Do not silently assume — when you default, say so and let the user correct it

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="brief-builder"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Brief Builder is one of 599 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog