Terms of Service

1. Acceptance of these terms

AgentPod ("AgentPod", "we", "us", "our") is operated by UNICORNARY, a société par actions simplifiée (SAS) registered in France under SIREN 994 689 305, with its registered office at 8 rue de Douai, 75009 Paris, France.

By accessing or using the AgentPod website and its catalog of skills (together, the "Service"), you agree to be bound by these Terms of Service. If you do not agree, please do not use the Service.

You can browse and use skills without creating an account. If you subscribe with your email address, you also agree to the handling of that data as described in our Privacy Policy, which forms part of these terms.

2. What AgentPod provides

AgentPod is a free, curated catalog of "skills". A skill is a set of instructions (a prompt or instruction set) that you copy and paste into a third-party AI tool such as ChatGPT or Claude to give it a specific capability.

Skills are text. They are not software that we run for you, and they are not a substitute for the AI tool itself. You bring your own AI tool and your own account with that tool. AgentPod does not process your prompts, your AI conversations, or the output those tools produce.

We focus on curation: quality over quantity, with each listed skill reviewed before it goes live. The catalog and individual skills may change, be updated, or be removed at any time.

• Skills are instruction sets you paste into AI tools you already use.
• AgentPod does not run the AI or see your conversations with it.
• The catalog is curated and may change without notice.

3. Your responsibilities and acceptable use

You agree to use the Service lawfully and reasonably. In particular, you agree not to:

• Use the Service or any skill for unlawful, harmful, deceptive, or infringing purposes.
• Attempt to disrupt, overload, probe, or gain unauthorized access to the site or its infrastructure.
• Scrape, copy, or redistribute the catalog wholesale, or resell skills as your own, except as permitted in section 6.
• Misrepresent your affiliation with AgentPod or use our name or brand to imply an endorsement we have not given.
• Submit an email address that is not yours, or otherwise misuse the subscribe form.

4. Skills are pasted into third-party AI tools, and you own how you use the output

Skills are designed to be copied into third-party AI tools (for example, ChatGPT or Claude). What happens after you paste a skill is up to you and the tool you use.

You are responsible for how you run a skill, what data you choose to give the AI tool, and how you use the output it generates. AI tools can produce results that are inaccurate, incomplete, or unsuitable for your situation. You should review and verify any output before relying on it, especially for anything important, sensitive, professional, legal, financial, or medical.

AgentPod is not responsible for the behaviour of third-party AI tools or for the results you obtain from them.

5. About our "security-checked" review (important disclaimer)

Every skill listed on AgentPod is reviewed and security-checked before it goes live. We label what data a skill can touch, and we favour the least access needed, so a skill only reads what you give it or runs on your device unless it truly needs more.

This review is a good-faith, best-effort check. It is not an absolute guarantee that a skill is safe, accurate, free of errors, or suitable for your particular needs. "Security-checked" and "scanned" describe our review process; they do not promise a specific outcome.

Please use your own judgement. Read what a skill does before you run it, be careful about the data you share with any AI tool, and do not paste secrets or sensitive information unless you are comfortable doing so.

• Our review is good-faith and best-effort, not a guarantee.
• We label the data a skill can touch and give it the least access needed.
• You should still read each skill and use your own judgement before running it.

6. Intellectual property

The AgentPod name, logo, branding, site design, text, and the way the catalog is curated and presented are owned by AgentPod or its licensors and are protected by intellectual property laws. You may not use them without our permission, except as needed to use the Service normally.

Skill content is provided so you can use it with your AI tools for your own purposes. You may copy a skill and paste it into ChatGPT, Claude, or similar tools, and use the results, in line with these terms. This does not transfer ownership of the underlying skill content, and it does not give you the right to republish, resell, or redistribute the catalog or skills as your own offering.

Where a skill incorporates third-party material, the rights in that material remain with its owners.

7. Third-party services and AI tools

AgentPod relies on third parties, and your use of skills depends on third-party AI tools. ChatGPT (OpenAI), Claude (Anthropic), and any other tools you use have their own terms of service, usage policies, and privacy policies. You are responsible for reading and following them.

We do not control these tools, their pricing, their availability, or how they handle your data once you paste a skill into them. Linking to or referencing a tool does not mean we endorse it or are affiliated with it. Our infrastructure providers (for hosting, data storage, and email) are described in our Privacy Policy.

8. No warranty: the Service is provided "as is"

The Service and all skills are provided "as is" and "as available", without warranties of any kind, whether express or implied. To the fullest extent permitted by law, we disclaim implied warranties of merchantability, fitness for a particular purpose, accuracy, and non-infringement.

We do not warrant that the Service will be uninterrupted, error-free, secure, or that any skill will produce particular results. Nothing in this section limits any rights you have under mandatory consumer protection law, including, where applicable, the legal guarantees available to consumers under French and EU law.

9. Limitation of liability

To the fullest extent permitted by law, AgentPod will not be liable for any indirect, incidental, special, or consequential damages, or for any loss of data, profits, or opportunity, arising out of or related to your use of the Service or any skill, or your use of third-party AI tools.

Because the Service is provided free of charge, our total liability to you for any claim relating to the Service is limited to the extent permitted by law. Nothing in these terms excludes or limits our liability for fraud, for death or personal injury caused by negligence, or for anything that cannot lawfully be excluded or limited, including under French and EU consumer law.

10. Changes to the Service and to these terms

AgentPod is evolving. We may add, change, or remove skills and features, and we may update these terms from time to time, for example to reflect new features, legal requirements, or the planned introduction of paid or premium offerings.

When we make material changes, we will update the "last updated" date above and, where appropriate, let subscribers know by email. Your continued use of the Service after changes take effect means you accept the updated terms. If you do not agree, please stop using the Service.

11. Governing law and jurisdiction

These terms are governed by the laws of France, without regard to conflict-of-law rules. Subject to any mandatory consumer protection rules that may grant you the right to bring proceedings in your country of residence, the courts of Paris, France will have jurisdiction over any dispute arising from these terms or the Service.

If you are a consumer in the EU, you may also have access to the European Commission's online dispute resolution platform.

12. Contact

If you have questions about these terms or the Service, please contact us at hello@agentpod.com.

Publication director: Alexandre Leciel. Registered company: UNICORNARY, 8 rue de Douai, 75009 Paris, France, SIREN 994 689 305.