terms-of-service-generation
Draft Terms of Service documents for web applications, SaaS platforms, and digital marketplaces. Use when the user requests terms of service generation or provides relevant inputs for this workflow.
git clone --depth 1 https://github.com/seb1n/awesome-ai-agent-skills /tmp/terms-of-service-generation && cp -r /tmp/terms-of-service-generation/legal-and-compliance/terms-of-service-generation ~/.claude/skills/terms-of-service-generationSKILL.md
# Terms of Service Generation
Draft comprehensive Terms of Service (ToS) documents tailored to web applications, SaaS platforms, and digital marketplaces. This skill produces enforceable, jurisdiction-aware terms covering user rights and restrictions, acceptable use, liability, warranties, dispute resolution, and platform-specific concerns like content moderation, subscription billing, and API usage.
## Workflow
1. **Understand Business Model** — Determine the platform type (SaaS, marketplace, social platform, API service), revenue model (subscription, freemium, transaction fees, advertising), user types (consumers, businesses, or both), and the core value proposition. Identify whether the service handles payments, user content, third-party integrations, or regulated data. These factors dictate which ToS sections are essential.
2. **Define User Rights and Restrictions** — Establish what users are permitted to do (acceptable use) and explicitly prohibited from doing (abuse, scraping, reverse engineering, circumventing access controls). Define account creation requirements including age minimums, accurate information obligations, and account security responsibilities. Specify the license granted to users and any usage limits tied to subscription tiers.
3. **Draft Liability and Warranty Sections** — Craft disclaimers of warranties (AS-IS/AS-AVAILABLE), limitations of liability with monetary caps, and exclusions for consequential damages. Include specific carve-outs required by consumer protection laws in key jurisdictions. Address service availability commitments or explicitly disclaim uptime guarantees if no SLA exists.
4. **Add Dispute Resolution Mechanisms** — Define the governing law and jurisdiction, include arbitration clauses with class action waivers where enforceable, specify small claims court exceptions, and outline informal dispute resolution steps that must precede formal proceedings. Consider whether B2B users should have different dispute terms than consumers.
5. **Review Enforceability** — Audit the draft for unconscionable terms that courts routinely strike down, ensure conspicuous presentation of material terms (auto-renewal, arbitration), verify compliance with platform-specific requirements (app store guidelines), and confirm that modification and termination provisions are reasonable and provide adequate notice.
## Usage
Describe your platform, business model, user base, and any specific concerns. Mention if you handle user-generated content, process payments, or operate in regulated industries.
**Example prompt:**
```
Generate Terms of Service for "CloudDeploy", a freemium SaaS platform for deploying web applications. Free tier has resource limits, paid tiers are monthly subscriptions. Users deploy their own code. We're a US Delaware company with global users.
```
## Examples
### Example 1: Freemium SaaS Platform
**Input:** CloudDeploy — a web application deployment platform. Delaware C-Corp. Free tier (3 projects, 1GB bandwidth), Pro tier ($29/mo), Team tier ($99/mo). Users deploy their own code and static assets. Integrates with GitHub.
**Output (key sections):**
**1. Acceptance of Terms**
By creating an account or using CloudDeploy, you agree to these Terms of Service and our Privacy Policy. If you use CloudDeploy on behalf of an organization, you represent that you have authority to bind that organization to these terms.
**2. Account and Subscription Terms**
Free tier accounts are subject to the resource limits published on our pricing page, which we may adjust with 30 days' notice. Paid subscriptions are billed monthly in advance. You may upgrade or downgrade at any time — upgrades take effect immediately with prorated charges, downgrades take effect at the next billing cycle. We will attempt to charge your payment method automatically; after two failed attempts, we may suspend your account after 7 days' written notice.
**3. User Responsibilities and Acceptable Use**
You are responsible for all code, content, and data you deploy through CloudDeploy ("User Content"). You must not deploy content that: (a) violates any law or regulation, (b) infringes third-party intellectual property, (c) contains malware or is designed to disrupt other users' deployments, (d) operates as an open proxy or relay, (e) mines cryptocurrency, or (f) exceeds your tier's resource allocation through circumvention. We reserve the right to suspend deployments that threaten platform stability without prior notice.
**4. Limitation of Liability**
TO THE MAXIMUM EXTENT PERMITTED BY LAW, CLOUDDEPLOY'S TOTAL LIABILITY FOR ANY CLAIMS ARISING FROM THESE TERMS OR YOUR USE OF THE SERVICE SHALL NOT EXCEED THE GREATER OF (A) THE FEES YOU PAID IN THE 12 MONTHS PRECEDING THE CLAIM OR (B) $100. THIS CAP DOES NOT APPLY TO CLOUDDEPLOY'S INDEMNIFICATION OBLIGATIONS OR WILLFUL MISCONDUCT.
### Example 2: Marketplace with User-Generated Content
**Input:** ArtVault — a digital art marketplace. Artists upload and sell digital artwork. Platform takes 15% commission. Users can leave reviews. DMCA compliance needed.
**Output (key sections):**
**Content Ownership and License**
Artists retain full ownership of their uploaded artwork. By listing content on ArtVault, you grant us a non-exclusive, worldwide license to display, reproduce, and distribute thumbnails and previews of your artwork solely for operating and promoting the marketplace. This license terminates 30 days after you remove the content, except for copies already purchased by buyers.
**Content Moderation**
ArtVault reserves the right to remove content that violates these terms or our Content Guidelines. We use a combination of automated scanning and human review. Content may be removed without prior notice if it depicts illegal activity, non-consensual intimate imagery, or child exploitation. For other violations, we will notify the creator and provide 48 hours to appeal before removal, except where immediate removal is requireDesign reproducible evaluations for AI agents with representative task sets, explicit rubrics, appropriate graders, baselines, regression gates, and failure analysis. Use when defining agent quality, comparing prompts or models, validating a release, measuring tool-use reliability, investigating regressions, or deciding whether an agent is ready for production.
Design privacy-aware observability for AI agents using traces, spans, structured events, metrics, cost attribution, dashboards, alerts, and investigation workflows. Use when instrumenting an agent, debugging intermittent tool or model failures, defining service-level objectives, analyzing latency or spend, auditing agent decisions, or preparing production monitoring.
Design and verify auditable human oversight, approval gates, escalation paths, and safe state transitions for AI agent workflows. Use when deciding which agent actions require review, adding approve/reject or dual-control flows, preventing unauthorized autonomous effects, creating decision records, reducing rubber-stamping, or recovering safely from rejected, expired, or failed actions.
Design, implement, harden, and verify Model Context Protocol (MCP) servers with precise tool contracts, least-privilege authorization, safe transports, structured errors, and interoperability tests. Use when creating a new MCP server, exposing an API or data source through MCP, reviewing an MCP server design, adding or revising MCP tools, or preparing an MCP server for production.
Design and operate bounded multi-agent workflows with task decomposition, dependency graphs, ownership, handoff contracts, shared-state controls, approvals, recovery, and synthesis. Use when a task contains genuinely independent workstreams, specialized roles, parallel research or implementation, reviewer-worker loops, or coordination problems that one agent should not execute sequentially.
Design and validate model-facing tool definitions with clear names, action-oriented descriptions, bounded JSON Schema parameters, explicit side effects, safe defaults, idempotency, errors, and realistic tests. Use when creating function-calling tools, MCP tools, agent actions, structured tool inputs, or when a model selects the wrong tool, invents arguments, or causes unsafe side effects.
Plan, execute, document, and retest authorized security assessments of AI agents and multi-agent workflows using safe adversarial cases, synthetic identities, canaries, and evidence-based findings. Use when defining red-team rules of engagement, assessing prompt injection or excessive agency, testing tool and identity boundaries, evaluating memory or cross-agent attacks, scoring a campaign, or verifying remediation in an approved environment.
Threat-model and harden AI agents, RAG systems, assistants, and tool-using workflows against direct, indirect, stored, cross-agent, and multimodal prompt injection. Use when reviewing an agent architecture, isolating untrusted content, constraining tools and egress, protecting secrets, adding injection-focused tests, investigating a suspected injection incident, or documenting residual prompt-injection risk.