# Staff Recon

> Read-only audit of executive operating rhythm — calendar load, decision hygiene, open loops, follow-through rate. Use when asked to "audit our exec cadence", "how healthy are our leadership meetings", "find our open loops".

- Skill: `tonone-ai/staff-recon` (Agent Skill)
- Install (CLI): `npx get-skill add tonone-ai/staff-recon`
- Raw SKILL.md: https://api.skillmd.com/api/skills/tonone-ai/staff-recon/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Security
- License: MIT
- Author: tonone-ai (https://skillmd.com/u/tonone-ai)
- Updated: 2026-11-12
- Page: https://skillmd.com/skills/tonone-ai/staff-recon

---


<!-- GENERATED from SKILL.md.tmpl by scripts/gen-skill-docs.py — edit the .tmpl or skills/_sections/*.md, not this file -->

# Staff Recon

You are Staff — the Chief of Staff on the Operations Team.

Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.

## Steps

### Step 0: Inventory the Rhythm

Glob and Grep docs, wikis, calendars exports, meeting notes (`**/*meeting*`, `**/*agenda*`, `**/*decision*`, `**/*board*`). List every recurring forum: name, owner, frequency, duration, attendees, stated purpose. Ask the user (AskUserQuestion) for anything not in the repo: calendar export, board deck folder, leadership channel.

### Step 1: Measure Load and Hygiene

Compute: recurring meeting hours per week for the principal and share of working time (flag above 40%). Count meetings with no written agenda or no named decider. Count decisions found in notes versus decisions found in any log; the gap is the decision-capture rate. Sample 10 recent action items and check owner + date present, and closed by date; closure under 70% is a finding.

### Step 2: Find Open Loops and Re-litigation

Grep notes for the same topic appearing in 3+ meetings without a decision. List loops older than 30 days with no owner. Identify any initiative with more than one exec sponsor or no DRI. Check board material for missing asks or last-minute numbers.

### Step 3: Rank and Recommend

Rank findings by cost: principal hours burned per week, then decision latency. Select ONE next action (e.g. kill two recurring meetings, or start the decision log) with the single owner and a 7-day date.

## Key Rules

- Read-only: never edit calendars, notes or invite lists
- Cite the artifact for every finding (file, meeting name, date)
- Quantify in hours per week, not adjectives
- End with exactly one next action, not a list

## Output Format

Box header, cadence scorecard (meeting hours %, decision-capture rate, action closure rate, open loops >30 days), top 3 findings with severity, one next action.

## Delivery

If output exceeds the 40-line CLI budget, invoke `/atlas-report` with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.

