What do I need to use Standing Meeting Audit?

The calendar's recurring population; Per meeting, the archaeology; The dependencies; The authority.

Is Standing Meeting Audit 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.

Standing Meeting Audit

Q: How do I know the Standing Meeting Audit output is good?

The skill verifies itself against its own quality checks: Every recurring slot is in the inventory with cost annualized; Origin purposes were checked in present tense, not assumed alive; Verdicts cite attendance and outcome evidence, not vibes; Contested kills route through the experiment, not the argument.

🔵 Stable🕐 updated 2026-07-19 🔷 SkillSpec L3 pm-cowork

Audit the recurring meetings a team has accreted — each standing slot tested against its original purpose, current attendance reality, and outcomes, with keep/shrink/merge/kill verdicts and the two-week cancellation experiment that settles arguments. Use when asked audit our recurring meetings, our calendar is all standing syncs, which meetings should die, or reset the team's meeting load. Produces the inventory with per-meeting verdicts, the experiment protocol, the merge map, and the re-accretion guard.

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

What to give it

▸The calendar's recurring population — the standing meetings with their casts, lengths, frequencies; the audit needs the census, not the impressions

▸Per meeting, the archaeology — why it was created (ask the oldest attendee), what it decided/produced last month (check the notes — absent notes are themselves a finding)

▸The dependencies — which meetings feed others (the prep meeting for the review meeting is a chain; verdicts consider chains whole)

▸The authority — who can actually kill what; auditing meetings the auditor can't touch produces resentment reports, not calendars

✅ 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 recurring slot is in the inventory with cost annualized

✓Origin purposes were checked in present tense, not assumed alive

✓Verdicts cite attendance and outcome evidence, not vibes

✓Contested kills route through the experiment, not the argument

✓The expiry default and re-audit cadence are installed

⚠️ What it refuses to do

Do not audit by survey — people defend meetings they multitask through; behavior testifies, opinions perform

Do not kill by decree what an experiment can kill by evidence — reversibility is the political unlock

Do not shrink everything politely instead of killing anything — ten 25-minute zombies still eat the calendar

Do not ignore the chains — killing the prep meeting while keeping the review it feeds breaks both

Do not audit once — without the expiry guard, the calendar regrows to baseline in two quarters

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

💬 Discussion

Standing Meeting Audit 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