Назад към всички

Company

// Build an agent-powered organization by mapping functions to skills and iterating on structure.

$ git log --oneline --stat
stars:1,933
forks:367
updated:March 4, 2026
SKILL.mdreadonly
SKILL.md Frontmatter
nameCompany
descriptionBuild an agent-powered organization by mapping functions to skills and iterating on structure.

Triggers

Activate on: "automate my company", "agents for my business", "replace team with AI", "company structure with agents", "which skills do I need".

Different from: startup (methodology) and business (strategy). This is about building the organization itself.

Core Flow

  1. Discovery — What does the company do? What functions exist?
  2. Mapping — Each function → existing skill, custom skill, or hybrid
  3. Sequence — Quick wins first, customer-facing later
  4. Iteration — Run → review → adjust → expand

Discovery Questions

Ask before recommending anything:

  • What's the core value you deliver to customers?
  • What functions exist today? (sales, support, ops, finance, marketing, legal, HR)
  • Where does work pile up? What's the bottleneck?
  • What do you actually want to do yourself?

Function Mapping

For each function, determine approach:

ApproachWhen
Install existing skillCommon function (email, CRM, support)
Create custom skillUnique to this business
HybridExisting skill + company-specific rules
Human + agent assistNeeds judgment, agent handles prep

See functions.md for common mappings.

Building Sequence

Build in order of impact, not org chart:

  1. Internal ops — Low risk, clear inputs/outputs
  2. Support — After internal proves reliable
  3. Sales — After support is stable
  4. Strategy — Agents assist, humans decide

See patterns.md for organizational structures.

Iteration Protocol

After each function is delegated:

  1. Run 1-2 weeks with human oversight
  2. Review: what did the agent miss?
  3. Adjust scope based on errors
  4. Reduce oversight only when stable

Never hand off completely on day one.

See iteration.md for tracking template.

Learning System

As the company evolves, capture:

  • Decisions made and why
  • Adjustments to agent scope
  • What worked vs what failed
  • New skills needed

This becomes the company's operational memory.

Red Flags

Stop and reassess:

  • Automating trust-building → agents assist, humans close
  • Delegating legal/compliance decisions → agents draft, lawyers approve
  • No clear function boundaries → define before automating
  • Expecting 100% automation immediately → set realistic timeline