C-Level Advisory OperationsFrameworkSystems

Company OS

The meta-framework for how a company runs across all C-suite roles.

$skillfish add ~skills/company-os

What This Skill Can Do

Concrete capabilities you get when you install this skill.

Design the company operating rhythm: weekly, monthly, and quarterly cadences

Build decision-making frameworks that clarify who decides what and how

Create cross-functional communication templates and meeting structures

Define company metrics framework with leading and lagging indicators

Build OKR infrastructure from goal-setting to tracking to retrospective

Document operating procedures and institutional knowledge for scale

Real Conversations

See how the Company OS skill responds to actual requests. These are representative examples of what your AI agent will produce.

You

We've been flying by the seat of our pants. 22 people, $1.6M ARR. No formal meeting cadence, no OKR process, no way to track decisions. Leadership team spends 3 hours a week in status meetings that feel useless. What's a minimal operating system that actually works?

Agent

The goal is the minimum cadence to keep everyone aligned without adding bureaucracy. Here's a proven model for 20-30 person companies.

The Operating Cadence Stack:

Daily (async):

  • Standup bot in Slack: what did you ship, what's blocking you? (5 mins per person, async)
  • No synchronous daily standups at this stage — they don't scale and you're not building a factory

Weekly (60 min total):

  • Monday: Leadership team sync — metrics review, top 3 priorities for the week, blockers only (30 min)
  • Friday: Company-wide "wins + what we learned" in Slack channel — builds culture and alignment without a meeting

Monthly (90 min):

  • All-hands: company metrics, one strategic update, one customer story, Q&A
  • Skip the slide deck for all-hands at this stage — it signals hierarchy you don't need yet

Quarterly (half-day):

  • OKR setting: company → department → individual
  • Retrospective on previous quarter
  • One strategic decision per quarter that requires everyone's input

Decision Tracking (not a meeting, a system):

  • Notion/Linear decision log: who decided what, what was the context, what did we reject and why
  • Any decision with >3 months of impact gets logged. Takes 5 minutes.

The 3-hour status meeting problem: Kill it by replacing it with async metrics dashboards. If everyone can see the numbers anytime, you don't need a meeting to recite them.

What software stack are you on — I can recommend specific tools that fit.

Get Started

How to install and use this skill in your preferred environment.

Skills are designed for AI coding agents (Claude Code, Cursor, Windsurf) and IDE-based workflows where the agent can read files, run scripts, and act on your codebase. Web-based AI can use the knowledge and frameworks, but won't have tool access.

Models & Context

Which AI models and context windows work best with this skill.

Recommended Models

Best
Claude Opus 4 Claude Sonnet 4 GPT-4.1 Gemini 2.5 Pro Grok 3 Kimi K2
Good
Claude Haiku 4.5 GPT-4.1 mini Gemini 2.5 Flash Grok 3 mini

Larger models produce more detailed, production-ready outputs.

Context Window

This skill's SKILL.md is typically 3–10 KB — fits in any modern context window.

8K Skill only
32K+ Skill + conversation
100K+ Skill + references + codebase

All current frontier models (Claude, GPT, Gemini) support 100K+ context. Use the full window for complex multi-service work.

Pro tips for best results

1

Be specific

Include numbers — users, budget, RPS — so the skill can size the architecture.

2

Share constraints

Compliance needs, team size, and existing stack all improve the output.

3

Iterate

Start with a high-level design, then ask follow-ups for IaC, cost analysis, or security review.

4

Combine skills

Pair with companion skills below for end-to-end coverage.

Ready to try Company OS?

Install the skill and start getting expert-level guidance in your workflow — any agent, any IDE.

$skillfish add ~skills/company-os
← Browse all 169 skills