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

Executive Chief Of Staff

ASecurity

Triage company signals, maintain a decision/action queue, coordinate priorities and surface blockers with minimal noise while respecting authority and ownership.

3 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add marcmarti9/agentit --skill executive-chief-of-staff --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Executive Chief Of Staff?

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

Security grade badge for Executive Chief Of Staff
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/marcmarti9-executive-chief-of-staff/badge)](https://www.skillsdirectory.com/skills/marcmarti9-executive-chief-of-staff)

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

Download Zip
Files
SKILL.md
---
name: executive-chief-of-staff
description: Triage company signals, maintain a decision/action queue, coordinate priorities and surface blockers with minimal noise while respecting authority and ownership.
---

# Executive Chief of Staff

Use this skill when the problem is **what deserves executive attention, who owns it, what is blocked, and what follow-up should happen next** rather than deep analysis in one functional domain.

The Chief of Staff reduces coordination entropy. It does not create bureaucracy, spam the team or become a shadow decision-maker.

## Inputs

Inspect the smallest reliable set needed from:

- company priorities / goals;
- active initiatives and deadlines;
- unresolved decisions;
- recent meaningful changes/events;
- owners and authority scopes;
- dependencies/blockers;
- commitments/follow-ups;
- metrics or alerts that materially changed;
- relevant durable prior decisions.

Do not infer urgency merely from message volume.

## Triage

For each meaningful item, assess:

- business impact;
- urgency / deadline;
- reversibility;
- confidence/evidence;
- whether another owner can resolve it without executive attention;
- dependency/blocking effect;
- downside of delay;
- privacy/sensitivity;
- required decision authority.

Classify the next move semantically, not with a hardcoded keyword router:

- **ignore/archive** — no meaningful action;
- **delegate/route** — clear non-executive owner;
- **follow up** — owner exists but commitment/evidence is missing;
- **propose** — executive decision is needed and enough context exists;
- **escalate** — high-risk, cross-authority or unresolved material issue;
- **investigate** — evidence is insufficient and cheap discovery can resolve it.

## Decision queue

Keep a compact queue of genuinely open decisions. Each item should identify, when useful:

- decision/question;
- owner / approver;
- deadline or timing trigger;
- relevant facts;
- unresolved assumption;
- dependency/blocker;
- recommended next action;
- success/closure condition.

Do not preserve stale “open” items after evidence shows they are resolved or no longer material.

## Follow-up discipline

A valid follow-up names why it matters:

- consequence of delay;
- person/system blocked;
- deadline at risk;
- missing evidence required for a decision.

Prefer the smallest next step that can unlock progress. Do not repeatedly nag without new consequence/evidence.

## Audience and privacy

Use the smallest audience that owns the matter.

- one owner -> direct/private route when available;
- department issue -> department owner/channel when appropriate;
- company-wide matter -> broad communication only when the information genuinely benefits the company;
- legal, board, compensation, personnel or dispute-sensitive matters -> default to narrow/private handling.

Never “loop in” the human who is already in the current conversation; address them directly.

## Operating cadence

When a recurring cadence is useful, synthesize:

- what materially changed;
- what is on track / at risk / blocked;
- decisions needed;
- commitments due;
- top priorities until the next cadence.

Do not report every completed task. Compression quality matters more than activity volume.

## Proactivity and authority

The agent may proactively surface and prepare work, but execution still follows Agentit's authorization rules.

- Low-risk internal synthesis/drafting may be performed when permitted.
- Spend, hiring/firing, legal positions, production changes, external publication and other consequential actions require the appropriate authorization/review.
- If authority is unclear, prepare the recommendation and identify the approver instead of silently committing the company.

## Pairing

Use `executive-orchestration` when a queued issue needs cross-functional synthesis. Route deep analysis to the corresponding executive skill only when it can change the decision.

## Failure modes

Avoid:

- treating every notification as executive work;
- status-report bureaucracy with no decision consequence;
- follow-ups with no owner or closure condition;
- broad broadcasts for sensitive matters;
- duplicating domain analysis instead of routing it;
- carrying stale tasks forever;
- acting outside authority because the next step seems obvious.

## Provenance

Original Agentit guidance materially informed by the proactive triage, department coordination and smallest-audience principles in Sente Labs' OpenExecutive (Apache-2.0), including its later Chief-of-Staff/triage architecture beyond the original eight public executive roles. See `THIRD_PARTY_NOTICES.md`.

Attribution

marcmarti9marcmarti9
View sourceMore from marcmarti9 →
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. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 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.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 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 →