← Back to Skills Marketplace
765
Downloads
4
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install company
Description
Build an agent-powered organization by mapping functions to skills and iterating on structure.
README (SKILL.md)
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
- Discovery — What does the company do? What functions exist?
- Mapping — Each function → existing skill, custom skill, or hybrid
- Sequence — Quick wins first, customer-facing later
- 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:
| 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:
- Internal ops — Low risk, clear inputs/outputs
- Support — After internal proves reliable
- Sales — After support is stable
- Strategy — Agents assist, humans decide
See patterns.md for organizational structures.
Iteration Protocol
After each function is delegated:
- Run 1-2 weeks with human oversight
- Review: what did the agent miss?
- Adjust scope based on errors
- 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
Usage Guidance
This skill is coherent and appears safe as a set of operational guidelines for building agent-driven orgs. Before applying its recommendations in production, do the following: (1) Pilot automation on low-risk internal functions (as the documents themselves recommend) and keep humans in the loop; (2) When the skill advises 'install existing skill' or 'create custom skill', review any third-party integrations' permissions and credentials carefully—grant least privilege and audit access; (3) Treat legal, compliance, finance, and customer-impacting decisions as human-reviewed per the skill's own red flags; (4) Maintain logs, versioned operational memory, and rollback triggers as described; (5) If you later implement custom code or integrations based on these templates, have those code/install artifacts reviewed separately (this evaluation covers only the instruction-only skill).
Capability Analysis
Type: OpenClaw Skill
Name: company
Version: 1.0.0
The skill bundle consists entirely of markdown files providing instructions and guidance for an AI agent on how to advise a user in structuring an 'agent-powered organization'. The content focuses on organizational design, function mapping, iterative deployment, and safety protocols, repeatedly emphasizing human oversight, clear boundaries, and rollback mechanisms. There are no instructions for the agent to perform malicious actions such as data exfiltration, unauthorized command execution, network calls to external endpoints, or prompt injection against the user. The explicit 'Red Flags' and 'Anti-Patterns' sections further reinforce a design focused on responsible AI deployment.
Capability Assessment
Purpose & Capability
Name/description (build agent-powered org) align with the provided guidance and templates. The skill requires no binaries, env vars, or installs that would be unrelated to its purpose.
Instruction Scope
SKILL.md, functions.md, iteration.md, and patterns.md contain process guidance, question templates, mapping heuristics, and iteration protocols. They do not instruct the agent to read local files, access credentials, call external endpoints, or perform actions outside the stated organizational-design scope.
Install Mechanism
No install spec or code files are present (instruction-only). Nothing is downloaded or written to disk by the skill itself.
Credentials
The skill declares no required environment variables, credentials, or config paths — appropriate for a methodology/consulting-style skill that provides process guidance only.
Persistence & Privilege
Skill is not forced-activated (always:false) and does not request elevated persistence or modification of other skills/configurations. It allows normal autonomous invocation, which is the platform default and acceptable here.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install company - After installation, invoke the skill by name or use
/company - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release
Metadata
Frequently Asked Questions
What is Company?
Build an agent-powered organization by mapping functions to skills and iterating on structure. It is an AI Agent Skill for Claude Code / OpenClaw, with 765 downloads so far.
How do I install Company?
Run "/install company" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Company free?
Yes, Company is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Company support?
Company is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Company?
It is built and maintained by Iván (@ivangdavila); the current version is v1.0.0.
More Skills