What do I need to use Inbox Unsubscribe Purge?

The census data; Honest reading behavior; The platform.

Is Inbox Unsubscribe Purge 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.

Inbox Unsubscribe Purge

Q: How do I know the Inbox Unsubscribe Purge output is good?

The skill verifies itself against its own quality checks: The census is by measured volume, not by annoyance salience; Every kill passed the would-you-notice test; The click/never-click line is applied per sender, with the sketchy ones named; Digest filters skip the inbox, not just label it.

🔵 Stable🕐 updated 2026-07-19 🔷 SkillSpec L3 ⚙ ships an executable helper pm-cowork

Cut inbox volume at the source — the unsubscribe purge that classifies recurring senders into kill/digest/keep, executes safely (real unsubscribes vs. spam-report vs. never-click), and installs the filters that catch the rest. Use when asked my inbox is all newsletters, mass unsubscribe safely, cut my email volume, or set up filters for the noise. Produces the sender census, the kill/digest/keep sort, the safe-unsubscribe rules, and the filter set.

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

What to give it

▸The census data — search counts per suspected sender, or a description of the noise ("LinkedIn, three newsletters, shop marketing, GitHub notifications")

▸Honest reading behavior — which newsletters actually get read (the calendar answer; "I mean to" is a kill vote)

▸The platform — Gmail/Outlook/other; filter syntax differs, and the skill writes the real rules

✅ 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.

✓The census is by measured volume, not by annoyance salience

✓Every kill passed the would-you-notice test

✓The click/never-click line is applied per sender, with the sketchy ones named

✓Digest filters skip the inbox, not just label it

✓Notification volume is fixed at the source where a source setting exists

⚠️ What it refuses to do

Do not click unsubscribe on spam — it's a liveness beacon; report instead

Do not keep newsletters aspirationally — the read-rate is the vote, not the intention

Do not build filters for email that shouldn't exist — source settings first

Do not purge alphabetically — impact order; the top ten senders are half the volume

Do not skip the first-touch habit — without it, the purge is an annual chore instead of a one-time fix

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

Related skills

🔌 Embed this skill

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

<div data-pm-skill="inbox-unsubscribe-purge"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Inbox Unsubscribe Purge is one of 750 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog