Organization Skills
Your team's standards, in every coding agent
Every team has conventions an agent should follow, from how to review code to which internal libraries to use, and copying them between repositories drifts fast. Organization Skills give them one home. Owners and admins publish skills under Organization → Skills by importing a SKILL.md, importing a folder with references and scripts, or writing one in the dashboard. Developers discover and install them with the LLM Gateway CLI, which writes each skill where their agent looks: Claude Code, Codex, OpenCode, Cursor, and others. Disabling a skill removes it from discovery, and every publish and management action lands in Enterprise Audit Logs without storing the skill content. Developers can sign in to the CLI through the browser, including your organization's SSO.
Why teams turn it on
One library for every agent
The CLI installs skills for Claude Code, Codex, OpenCode, Cursor, Qwen, Pi, or the shared .agents directory.
Folders, not just prompts
A skill can bundle references, scripts, and assets: up to 100 supporting files and 1 MB per skill.
Access follows the organization
Downloads use a project API key from an active member, so removed access stops new downloads with a 403.
Managed by admins, audited
Owners and admins publish, edit, disable, and delete. Every action is in the audit log; the content itself is not.
How it works
From decision to deployed in three short steps
- 01
Publish
Under Organization → Skills, import a SKILL.md, import a folder, or write a custom skill. New skills are enabled immediately.
- 02
Discover
Developers run npx @llmgateway/cli skills list to see what the organization publishes.
- 03
Install
skills add <name> --agent claude, or codex, cursor, and others, writes the skill where that agent reads it.
bash
Install organization skills
npx @llmgateway/cli skills list
npx @llmgateway/cli skills add code-review --agent claude
npx @llmgateway/cli skills add --all --agent codexReal-world use cases
Why customers actually adopt this
Code review standards
Publish your review checklist once and have every agent apply it.
Internal platform knowledge
Ship instructions for your internal SDKs and deploy tooling together with the scripts they need.
Day-one onboarding
New developers install the whole library with one command.
Frequently asked
- What format do skills use?
- A folder with SKILL.md at its root. Its YAML header needs a unique lowercase, hyphenated name of up to 64 characters and a description of up to 1,024 characters.
- What happens when a skill is disabled?
- It disappears from CLI discovery and can no longer be downloaded. Copies already on a developer's machine are not removed.
- How are downloads authorized?
- With a project API key issued to an active member who has access to that project. Expired or revoked keys return 401, and missing project or Enterprise access returns 403.
More enterprise capabilities
The rest of the enterprise stack
Organization-Wide Analytics
Cost, requests, and tokens totaled across every project, with breakdowns by model, project, API key, and member. Built on pre-aggregated rollups, so any date range stays fast.
Per-Member Budgets & Developer Role
Per-member spend caps enforced at request time, org-wide default developer limits, and a project-scoped Developer role. An over-budget request is rejected before it ever reaches a provider.
Teams & Directory Sync
Group developers under a shared project ceiling, per-developer budgets, and IAM rules. Microsoft Entra groups map onto teams over SCIM.
Enterprise Audit Logs
Tamper-evident audit trails for SOC 2, HIPAA, ISO 27001, and internal investigations. Every config change, key rotation, and admin action — captured, attributed, exportable.
Data Streams to Your SIEM
Forward audit logs to your SIEM and export request log metadata to your own HTTPS endpoint in signed, ordered batches, with replay of up to 30 days.
Per-Project Routing Overrides
Override global routing rules at the project level — region, provider order, fallback chain, and cost ceilings. Production stays pinned; experimental teams stay flexible.
Dynamic Routes
Named, versioned routing flows with conditions, classifier branches, A/B splits, and model targets. Call one with dynamic/<name> and roll back instantly.
Enterprise Guardrails
Server-side detection for prompt injection, PII, secrets, and policy violations. Configured centrally, enforced at the gateway, auditable per-request.
Provider Compliance Policies
Require SOC 2, ISO 27001, GDPR, zero data retention, no prompt training, or approved headquarters countries, and the gateway refuses every provider that falls short.
Zero Data Retention
Enforce zero data retention across provider routing, gateway storage, response caches, and the Responses API, for the whole organization or a single API key.
Discord & Slack Alerts
Native webhook integrations for Discord and Slack. Get the enterprise contact-sales form, billing events, guardrail trips, and SLA breaches in the channels your team already monitors.
Single Sign-On (SAML / OIDC)
SAML 2.0 and OIDC SSO with SCIM provisioning, group-based role mapping, and enforced-only access. No local credentials, no shared passkeys, no off-boarding gaps.
Master Keys & Provisioning API
Org-scoped bearer tokens that create projects, gateway API keys, IAM rules, and custom providers from your backend, and report cost per member and model.
White-Label Chat & Playground
Embed or stand up a fully white-labeled chat app and playground under your own domain. Customize branding, default models, system prompts, and feature toggles.
See organization skills on your real workloads
Bring a sample workload to a 30-minute call. We'll wire it up live and show you the actual experience your team will get.