Installable skillMIT

Company

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

BY clawicUPDATED Oct 28, 2026
INTENDED FORβ—ˆOpenClawInstall in a listed agent.

instructions.md

---
name: company-c269d940bd54
slug: company
version: 1.0.0
description: Build an agent-powered organization by mapping functions to skills and iterating on structure.
homepage: https://clawic.com/skills/company
metadata:
  clawdbot:
    emoji: 🏒
    displayName: Company
---

## 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** β€” What does the company do? What functions exist?
2. **Mapping** β€” Each function β†’ existing skill, custom skill, or hybrid
3. **Sequence** β€” Quick wins first, customer-facing later
4. **Iteration** β€” Run β†’ review β†’ adjust β†’ 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:

| Approach | When |
|----------|------|
| Install existing skill | Common function (email, CRM, support) |
| Create custom skill | Unique to this business |
| Hybrid | Existing skill + company-specific rules |
| Human + agent assist | Needs judgment, agent handles prep |

See `functions.md` for common mappings.

## Building Sequence

Build in order of impact, not org chart:
1. **Internal ops** β€” Low risk, clear inputs/outputs
2. **Support** β€” After internal proves reliable
3. **Sales** β€” After support is stable
4. **Strategy** β€” 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 β†’ agents assist, humans close
- Delegating legal/compliance decisions β†’ agents draft, lawyers approve
- No clear function boundaries β†’ define before automating
- Expecting 100% automation immediately β†’ set realistic timeline
COMPATIBILITY & REFERENCES

Platform guidance

Imported from the listed AgentSkill.sh category. Complete supplied package files and notices are retained. Required external tools and credentials are not installed. No bundled code was executed during import. Individual agent task behavior has not been tested.