meetings

$npx mdskill add alirezarezvani/claude-skills/meetings

Optimizes meeting decisions

  • Solves meeting justification
  • Depends on stdlib Python
  • Runs cost gate analysis
  • Delivers timeboxed agendas

SKILL.md

.github/skills/meetingsView on GitHub ↗
---
name: meetings
description: Use when someone wants to decide whether a meeting is worth calling, price a meeting in dollars, build a timeboxed agenda with desired outcomes, or turn messy meeting notes into owned action items — or says "should this be a meeting", "/cs:meeting-prep", or "/cs:meeting-actions". Runs a cost gate (ASYNC / NOT-READY / MEET), builds a decision-first agenda, and extracts an owner + due-date checklist that flags every orphan.
argument-hint: "[the meeting to gate, or the notes to extract actions from]"
license: MIT
metadata:
  version: 1.0.0
  build_pattern: "Path-B discipline skill — Rogelberg/HBR meeting-science canon + deterministic gate/agenda/extraction scripts"
  distinct_from: "project-management (team ceremonies + Jira delivery flow; this is personal meeting hygiene); business-operations/internal-comms (org-level communication design; this never auto-sends); productivity/capture (private brain-dump triage; this parses shared meeting notes)"
---

# Meetings — Cost Gate → Timeboxed Agenda → Owned Actions

> **Portability:** Reasoning-led skill with 3 stdlib Python scripts. No external APIs, no LLM calls
> in scripts, nothing auto-sent. The scripts fix the discipline; the user runs the meeting.

## What this does

Most meetings should be an email. This skill makes that testable: it prices a meeting in real
dollars, refuses to let it exist without a decision + agenda + owner, builds a timeboxed
decision-first agenda for the survivors, and afterwards turns raw notes into an owner + due-date
checklist that flags every orphan. An ASYNC verdict is a win, not a failure.

## Workflow — gate → agenda → run → extract

**1. Gate.** Before starting, ask one clarifying question if the decision to be made is unstated —
the gate cannot run honestly without it. Then price it and apply the three checks. No decision → ASYNC (exit 2): draft a memo
instead, stop here. Decision but missing agenda/owner → NOT-READY (exit 3), naming the gap.
All present → MEET (exit 0) with total cost and a cost-per-minute line.

**2. Agenda.** Only for MEET. Every topic needs a desired outcome — empty outcomes are refused by
name (exit 2). Decision topics (decide/choose/approve) sort before discuss/inform. Timeboxes plus
the mandatory 5-minute closing "actions recap" slot must fit `--length`, or the overflow is refused
with the exact overage (exit 3). Iterate — trim or split the named topic and re-run until it fits;
the stop condition is exit 0 (or the meeting goes async). Output includes a pre-read line.

**3. Run.** The user runs the meeting from the printed agenda. Hold the timeboxes; use the closing
slot to read every action aloud with its owner and date.

**4. Extract.** Feed the raw notes to the extractor: checkboxes, `ACTION:`/`TODO:` lines,
"@name will …" and "Name will … by date" patterns become a checklist grouped by owner, with
ORPHAN (no owner) and NO-DUE flags plus summary counts. Assign every orphan before posting — the
meeting is done when every action has an owner and a date; that completion check closes the loop.

```bash
# 1. Gate: should this meeting exist?
python scripts/meeting_cost_calculator.py --attendees 6 --minutes 60 \
  --avg-rate 90 --include-refocus --has-decision --has-agenda --has-owner

# 2. Agenda: timeboxed, decision-first, outcomes mandatory
python scripts/agenda_builder.py --length 45 \
  --topic "Q3 pricing:Decide usage-based vs seat-based:15:maria" \
  --topic "Launch risks:Discuss open launch blockers:15:sam"

# 4. Extract: raw notes -> owner + due-date checklist with ORPHAN/NO-DUE flags
python scripts/action_item_extractor.py --input notes.md
```

## Scripts

| Script | Role |
|---|---|
| `scripts/meeting_cost_calculator.py` | Dollars (attendees × minutes × rate, optional 23-min refocus overhead per attendee) + decision/agenda/owner gate → ASYNC / NOT-READY / MEET. |
| `scripts/agenda_builder.py` | Timeboxed decision-first agenda; refuses empty outcomes and overflow; enforces pre-read line + 5-min closing actions-recap slot. |
| `scripts/action_item_extractor.py` | Raw notes → owner-grouped markdown checklist with due dates, ORPHAN/NO-DUE flags, and summary counts. |

## References

- [`references/meeting_cost_canon.md`](references/meeting_cost_canon.md) — the real cost of meetings and the should-this-exist gate (7 sources)
- [`references/agenda_discipline.md`](references/agenda_discipline.md) — agendas as questions, timeboxing, decision-first ordering, pre-reads (7 sources)
- [`references/action_item_discipline.md`](references/action_item_discipline.md) — why meetings without owned actions are theater (6 sources)

## Assets

- [`assets/example_agenda.md`](assets/example_agenda.md) — a full worked timeboxed agenda (gate verdict → ordered topics → closing recap)
- [`assets/meeting_gate_worksheet.md`](assets/meeting_gate_worksheet.md) — fillable should-this-be-a-meeting worksheet

## Rules

- **Gate before agenda.** Never build an agenda for a meeting that hasn't passed the gate.
- **No decision, no meeting.** Status updates go async, every time.
- **No desired outcome, no agenda slot.** The builder refuses; go get the outcome.
- **Every action item has an owner and a date — or it is not an action item.** Flag, never drop.
- **Never auto-send.** No invites, no emails, no messages. Output is text the user sends.

## Distinct From (don't reach for the wrong skill)

- **`project-management/`** — team ceremonies, sprint cadence, Jira delivery flow. This gates one
  meeting at a time for the person calling it.
- **`business-operations/internal-comms`** — org-level communication design. This never designs a
  comms program and never sends anything.
- **`productivity/capture`** — triages a private brain-dump. This parses a shared meeting's notes.

---

**Version:** 1.0.0
**Build pattern:** Path-B discipline skill — meeting-science canon preserved + deterministic gate/agenda/extraction scripts added.

More from alirezarezvani/claude-skills

SkillDescription
a11y-auditAccessibility audit skill for scanning, fixing, and verifying WCAG 2.2 Level A and AA compliance across React, Next.js, Vue, Angular, Svelte, and plain HTML codebases. Use when auditing accessibility, fixing a11y violations, checking color contrast, generating compliance reports, or integrating accessibility checks into CI/CD pipelines.
ab-test-setupWhen the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "conversion experiment," "statistical significance," or "test this." For tracking implementation, see analytics-tracking.
ad-creativeWhen the user needs to generate, iterate, or scale ad creative for paid advertising. Use when they say 'write ad copy,' 'generate headlines,' 'create ad variations,' 'bulk creative,' 'iterate on ads,' 'ad copy validation,' 'RSA headlines,' 'Meta ad copy,' 'LinkedIn ad,' or 'creative testing.' This is pure creative production — distinct from paid-ads (campaign strategy). Use ad-creative when you need the copy, not the campaign plan.
adversarial-reviewerAdversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer.
aeoAnswer Engine Optimization (AEO) skill — optimize content to be cited by AI language models (ChatGPT, Perplexity, Claude, Gemini, Mistral) as authoritative sources. Distinct from SEO — AEO optimizes for citation in LLM-generated responses, not search rankings. Use when planning content for AI-first search audiences, auditing existing content for E-E-A-T signals, tracking which pages get cited by which LLMs, or building a citation-friendly content strategy. Triggers — 'AEO audit', 'optimize for ChatGPT', 'get cited by Perplexity', 'LLM citation strategy', 'answer engine optimization', 'content for AI search', 'E-E-A-T audit'. Output is a markdown audit report (default) or JSON for pipeline integration. Stdlib-only Python tools.
agent-decision-receiptsMint a tamper-evident, post-quantum-signed receipt for a consequential agent action (deploy, delete, pay, grant-access, model decision) so it can be verified later from the certificate alone. Use when an autonomous agent takes a side-effecting action that may need to be proven later, or when satisfying EU AI Act Article 12 record-keeping. Three decisions: whether an action needs a receipt, minting it, verifying it. Signing is delegated to the open-source OpenAgentOntology package. Not after-the-fact log analysis; not a hosted notary; not a legal opinion.
agent-designerUse when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer).
agent-harnessTurn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library).
agent-launcher-orchestratorUse when a user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic account — "build me an agent", "launch this as a managed agent", "run this on a schedule", "grade my agent against a rubric", "set up a nightly worker". Reads the per-session goal (./my-agent/goal.json), routes deterministically to one of five phase sub-skills (interview → stage-launch → grade-iterate → run-without-you → wrap-up) via goal_router.py, and compiles the goal+phase into an execution shape (single-pass workflow / bounded grade→iterate loop / recurring cron deployment loop) via loop_compiler.py. Forks context so heavy intake (build sheets, payloads, eval cases) stays out of the parent thread. All launches are emitted as BYOK curl the user runs with their own key; no tool makes API calls. Inspired by anthropics/launch-your-agent (Apache-2.0). Distinct from engineering/agent-harness (generic domain loop) and engineering/write-a-skill (authors Claude Code skills, not CMAs).
agent-memoryUse when a project's CLAUDE.md has grown past what anyone reads and you want the agent to learn durable facts from its own sessions instead — or when asking why the agent keeps re-learning the same correction, why a remembered rule is wrong, or where a memory line came from. Implements a four-tier store (L0 transcripts / L1 candidates / L2 project context / L3 stable persona) where promotion is earned by recurrence across sessions and days, never by one confident statement, and nothing reaches a committed file without a human adopting it.