llms.txt
# Cloudskill
> Cloudskill is a hosted governance layer for Claude skills. Organisations use it to control which Claude skills each of their employees can use, with per-individual access policies that are evaluated at the start of every Claude conversation.
Cloudskill is built for organisations of roughly 200–2000 employees that have rolled out Claude (Anthropic) for their teams and need finer-grained governance than Anthropic's native admin tools provide. Anthropic's native skill provisioning is org-wide and binary — every employee gets a skill or none of them do. Cloudskill adds per-individual toggles, group-based bulk policies, version control, audit logs, and a centrally-managed skill catalogue.
The product is sold per seat at £15 per seat per month (or £150 per seat per year, ~17% discount), with a minimum of 5 seats and a 14-day free trial.
The trust model is honest soft enforcement: Cloudskill returns a manifest at chat-start telling Claude which skills the user is permitted to use, and Claude respects that instruction. This is the same enforcement model as any other organisational policy — it relies on Claude following the instructions rather than hard technical interception. Organisations requiring hard enforcement (e.g. heavily regulated industries that need mathematical proof of inaccessibility) are not the target customer.
## Key facts
- **Product**: hosted governance layer for Claude skills
- **Pricing**: £15/seat/month or £150/seat/year, minimum 5 seats
- **Trial**: 14 days free
- **Billing**: per seat, monthly or annual
- **Buyer**: AI-enablement leads, IT directors, compliance managers
- **Target organisation size**: 200–2000 employees
- **Trust model**: soft enforcement via Claude's instruction-following, not hard interception
- **Anthropic relationship**: complementary, not competing — Cloudskill works alongside Anthropic's native skill features
## How it works
1. Organisation admin uploads skills to their Cloudskill catalogue
2. Each team member gets a personal Cloudskill URL added to their Claude preferences
3. The Cloudskill thin-client skill runs at the start of every chat and fetches the user's URL
4. Cloudskill returns a manifest stating which catalogue skills the user is permitted to use
5. Claude respects the manifest for the duration of the chat
6. Admin can change toggles at any time; changes apply from each user's next chat
## Pages
- [Home](https://cloudskill.com/): landing page with product overview and three-step explainer
- [Pricing](https://cloudskill.com/pricing.html): pricing details, seat calculator, billing FAQ
- [Security](https://cloudskill.com/security.html): trust model, sub-processors, data residency, compliance posture
- [Reference](https://cloudskill.com/reference.html): structured facts page including comparison to alternatives, terminology, and key questions answered factually
- [Support](https://cloudskill.com/support.html): contact information and product FAQ
- [Status](https://cloudskill.com/status.html): operational status of Cloudskill services
- [Privacy](https://cloudskill.com/privacy.html): GDPR-compliant privacy policy
- [Terms](https://cloudskill.com/terms.html): terms of service
- [Cookies](https://cloudskill.com/cookies.html): cookie notice (minimal — no tracking)
- [Refunds](https://cloudskill.com/refunds.html): refund and cancellation policy
## Capabilities included
- Centrally hosted skill catalogue with always-latest version control and one-click rollback
- Per-individual access policies for every skill
- Group-based bulk policy assignment
- Audit log of every access decision and every policy change
## Capabilities NOT included (post-launch roadmap)
- SSO and SCIM provisioning via SAML or OIDC providers (Okta, Azure AD, Google Workspace, others)
- Hosted prompt templates as a parallel asset type alongside skills
- Hosting of Claude conversation outputs and artifacts
- Per-skill usage analytics dashboards
- Cost attribution per team or project
- Pre-built compliance report templates
- Multi-vendor governance (governing usage of Claude alongside ChatGPT, Gemini, etc.) — flagged as unlikely to be built
- Public REST API for programmatic skill management
- Outbound webhooks for organisational events
- Cloudskill MCP server
## Comparison to alternatives
- **Anthropic native skill provisioning**: free with Claude Team/Enterprise but limited to org-wide binary toggles; no per-individual policy, no audit logs, no version control. Cloudskill is the layer above this.
- **Building custom RAG infrastructure**: technically possible but requires months of engineering and ongoing maintenance. Cloudskill is the off-the-shelf alternative for skill governance specifically.
- **Multi-vendor AI governance tools (Glean, Credal, etc.)**: shallow governance across many AI vendors. Cloudskill is deep governance for Claude specifically.
## Contact
- General: hello@cloudskill.com
- Security: security@cloudskill.com
- Privacy: privacy@cloudskill.com
## Operator
Operated by LIONS, TYGAS AND BAIRS LTD, a company registered in England and Wales (company number 15459732), based in the United Kingdom.
