Is Morning Intelligence 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.

Morning Intelligence

Q: How do I know the Morning Intelligence output is good?

The skill verifies itself against its own quality checks: Every interview question was asked — none skipped unless the user already provided the answer; The "What I Heard" summary was shown and confirmed before writing the master prompt; The master prompt uses specific topic angles, not vague category names (not "AI" — "AI applied to enterprise software"); Exclusions are explicitly stated in the master prompt with a NEVER INCLUDE section.

🟡 Experimental🕐 updated 2026-06-08 🔷 SkillSpec L3 pm-operations

Interviews you across 15 questions to capture your role, topics, sources, exclusions, and format preferences, then writes a master prompt you can paste into a scheduled task or Claude Code Routine. Use when you want to set up a personalised daily news brief, build a reusable morning news prompt, or create an automated intelligence briefing. Produces a confirmed summary of your preferences, a ready-to-paste master prompt, and setup instructions for both Cowork Scheduled Tasks and Claude Code Routines.

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

🗣 Say this to your agent

“Set up my morning intelligence brief”“Build me a morning news prompt”“Interview me for a morning briefing skill”“I want to start every day with a personalised news digest”“Help me set up a daily AI news brief”

✅ 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.

✓Every interview question was asked — none skipped unless the user already provided the answer

✓The "What I Heard" summary was shown and confirmed before writing the master prompt

✓The master prompt uses specific topic angles, not vague category names (not "AI" — "AI applied to enterprise software")

✓Exclusions are explicitly stated in the master prompt with a NEVER INCLUDE section

✓Sources are listed in order of preference, not as a flat unordered list

✓Story type mix is written as a directive, not just a list

✓Recency instruction handles the edge case of slow news days

✓Format instruction is precise enough that a different AI could follow it correctly

⚠️ What it refuses to do

Do not skip the interview and write a generic master prompt — a brief that is not tailored to the user's specific role and topics will be ignored after the first day

Do not proceed to write the master prompt without confirming the "What I Heard" summary — errors in the summary will silently propagate into a prompt that produces the wrong briefing every morning

Do not use broad topic labels in the master prompt (e.g. "AI", "tech news") — every topic must have a specific angle or focus to produce signal-to-noise ratio worth reading

Do not omit the NEVER INCLUDE section — without explicit exclusions, the briefing will fill with noise that the user said they wanted filtered out

Do not ask all 15 questions at once — the interview must run one question or small group at a time to produce specific, considered answers

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

💬 Discussion

Morning Intelligence is one of 1174 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog