What do I need to use Follow-up Sweep (Live)?

Window; Who counts; Draft or list-only.

Is Follow-up Sweep (Live) 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.

Follow-up Sweep (Live)

Q: How do I know the Follow-up Sweep (Live) output is good?

The skill verifies itself against its own quality checks: Nothing was sent — only drafted; Each item is correctly typed (you owe / owed / promised) from the real last message; Resolved threads were excluded (checked the latest message, not just the first); Ranking reflects staleness AND stakes, not date alone.

🔵 Stable🕐 updated 2026-10-23 🔷 SkillSpec L3 ⚙ ships an executable helper pm-cowork-live

Sweep the user's REAL mail and calendar for dropped balls — threads awaiting their reply, promises they made, and replies they're owed — then draft the nudges. Use when asked what am I forgetting, what have I not replied to, who owes me a reply, or chase my open threads in Cowork. Reads sent/received mail via the Gmail connector and recent events via Calendar, finds the open loops, and produces a follow-up-list artifact plus ready-to-send draft nudges.

▶ 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

“What am I forgetting to follow up on?”“Sweep my inbox for dropped balls and draft the nudges.”“Who owes me a reply, and who am I ignoring?”“Chase my open threads from the last two weeks in Cowork.”

What to give it

▸Window — how far back to sweep (default: last 14 days)

▸Who counts — everyone, or just external/customers/VIPs

▸Draft or list-only — may it write draft nudges? (default: yes, drafts only)

✅ 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.

✓Nothing was sent — only drafted

✓Each item is correctly typed (you owe / owed / promised) from the real last message

✓Resolved threads were excluded (checked the latest message, not just the first)

✓Ranking reflects staleness AND stakes, not date alone

✓Promises attributed to the user actually appear in their sent mail

⚠️ What it refuses to do

**Nudging on a thread that was already answered** — always read the latest message.

**Auto-sending chases** — draft, let the human send.

**Inventing a promise** to manufacture a follow-up.

**Flat date-sort** that buries a stale customer thread under fresh internal noise.

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

💬 Discussion

Follow-up Sweep (Live) 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