Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

chief-of-staff

ASecurity

Personal Chief of Staff system for ADHD-ish operators. Vault-based, loop-driven, nervous-system-aware. Built and lived-in across daily sessions on real consulting, content, and long-running personal work.

97 stars
0 votes
0 copies
0 views
Added 8/30/2026
ai-agentsgoshellgit

Works with

claude codeclimcp

Security Analysis

A100/100

Scanned 8/30/2026

Install to Claude Code

$npx -y skills add jdpolasky/ai-chief-of-staff --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of chief-of-staff?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for chief-of-staff
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/jdpolasky-chief-of-staff/badge)](https://www.skillsdirectory.com/skills/jdpolasky-chief-of-staff)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: chief-of-staff
description: Personal Chief of Staff system for ADHD-ish operators. Vault-based, loop-driven, nervous-system-aware. Built and lived-in across daily sessions on real consulting, content, and long-running personal work.
tags: [chief-of-staff, productivity, adhd, memory, obsidian, claude-code, vault, loop]
---

# Chief of Staff

**Executive function as a service. For the brain that builds everything and remembers nothing.**

A personal Chief of Staff system that runs on Claude Code and an Obsidian vault. Four commands, one loop, persistent memory. Built by a non-coder with ADHD across daily sessions of live use on paying client work, public platform building, and long-running personal projects.

## What It Solves

- **Session amnesia.** Every new Claude session forgets who you are, what you're working on, and where you left off. You waste the first ten minutes re-priming. The vault and memory layer fix this at boot.
- **Task pile-up without executive function.** Lists grow, nothing moves, shame compounds. The loop forces a small win first and flags what matters now, not everything.
- **Nervous system collapse under pressure.** Financial stress triggers freeze, freeze prevents action, inaction deepens shame. The system leads with what's working, shrinks the task when stuck, and never uses guilt.
- **Drift between sessions.** What you decided Tuesday is gone by Friday. `/wrap` writes it down. `/start` reads it back.

## The Loop

| Command | When | What It Does |
|---------|------|--------------|
| `/setup` | Once | Conversational wizard. Generates `CLAUDE.md`, seeds `.claude/memory/`, copies vault templates. |
| `/start` | Opens every session | Reads Command Center + To-Do List. Delivers Must/Should/Could briefing. Flags overdue Waiting For items. Ends with "what do you want to work on?" |
| `/sync` | Mid-session (optional) | Checkpoint. Saves anything worth keeping to memory. Updates Command Center or To-Do if needed. |
| `/wrap` | Closes every session | Reflects wins. Updates Command Center date. Queues open threads. Rotates stale memory entries out. |

## The Key Insight

> **The loop is the thing. The commands are cheap. The state they read and write is where the value lives.**

Your Claude does not need to be smarter. It needs to be oriented. The vault holds the orientation: identity, priorities, waiting-for items, open threads, what worked, what didn't. Every session boots with that context loaded and ends with it updated. The AI becomes a Chief of Staff, not a task executor.

## Setup

See [Quickstart in the README](README.md#quickstart). Four questions get you a working system; the rest is optional.

## Prerequisites

- Claude Code installed (`claude.ai/code`)
- Obsidian (free, `obsidian.md`) with a vault set up
- A Claude subscription (any tier; Pro works)
- Optional but recommended: Gmail, Google Calendar, Google Drive MCP connectors for briefing enrichment

## What You Get Out of It

- A Claude that wakes up knowing who you are, what's on your plate, and what's overdue
- A morning briefing that starts with a small win, not a guilt list
- A single source of truth for tasks, waiting-for items, and open threads
- Memory stored as plain Markdown on your disk. Survives model swaps, session resets, and vendor changes.
- A system that gets *more* useful over time as the vault grows, not less

## What This Is Not

- Not a task manager. It is an *operating shell* for a task manager.
- Not a life coach. It is a structural prosthetic for executive function.
- Not a productivity cult. No streaks, no guilt, no shame. You skip a day, you pick back up.

## Links

- **Repo:** https://github.com/jdpolasky/ai-chief-of-staff
- **Architecture deep-dive:** [ARCHITECTURE.md](ARCHITECTURE.md)
- **Obsidian setup guide:** [obsidian-setup](obsidian-setup.md)
- **Notion vs Obsidian (why vault-based):** [notion-vs-obsidian](notion-vs-obsidian.md)

Attribution

jdpolaskyjdpolasky
View sourceMore from jdpolasky →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →