Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
61 changes: 41 additions & 20 deletions rh-basic/.catalog/deploy_and_use.md
Original file line number Diff line number Diff line change
Expand Up @@ -3,43 +3,64 @@
Golden sources: skills/*/SKILL.md, README.md, AGENTS.md
-->

## Deploy and use
**Note:** This skill pack is released as Developer Preview. Developer Preview features provide early access to functionality in advance of possible inclusion in a Red Hat product offering. For more information about the support scope of Red Hat Developer Preview features, see [Developer Preview Support Scope](https://access.redhat.com/support/offerings/devpreview).

### Prerequisites

- Claude Code CLI or IDE extension (if using Claude Code)
- Red Hat service account ([console.redhat.com](https://console.redhat.com/iam/service-accounts))
- At least one supported AI coding assistant:
- [Claude Code](https://claude.com/product/claude-code) (CLI or IDE extension)
- [GitHub Copilot](https://github.com/features/copilot) (CLI or VS Code)
- [Cursor](https://www.cursor.com/)
- [Gemini CLI](https://github.com/google-gemini/gemini-cli)
- [OpenCode](https://opencode.ai/)
- [Lola](https://github.com/LobsterTrap/lola) CLI installed

Skills fall back to WebFetch on public Red Hat documentation if the MCP server is not configured.
### Step 1: Install the skill pack

### Environment setup
```bash
# Add the Red Hat Agentic marketplace (one-time setup)
lola market add rh-agentic-plugins https://raw.githubusercontent.com/RHEcosystemAppEng/agentic-catalog/main/marketplace/rh-agentic-collection.yml

No environment variables are required for this pack's MCP server. Authentication uses Red Hat Customer Portal browser SSO.
# Install the rh-basic pack (replace claude-code with your AI assistant)
# Valid targets: claude-code, copilot-cli, copilot-vscode, cursor, gemini-cli, opencode
lola install rh-basic -a claude-code
```

### Installation (Lola)
This installs the skills, the instructions file, and the MCP server definitions into your project.

From a checkout of this repository, install the pack with [Lola](https://github.com/LobsterTrap/lola):
Verify the installation:

```bash
lola install -f rh-basic
lola list
```

The module is declared in **`marketplace/rh-agentic-collection.yml`** ([agentic-catalog](https://github.com/RHEcosystemAppEng/agentic-catalog)) (`path: rh-basic`). See the root [README.md](../../README.md) for marketplace setup.
### Step 2: Set up the MCP server

### Installation (Claude Code)
This pack uses the Red Hat Security MCP server, which authenticates via browser SSO — no environment variables are required.

```bash
lola install -f rh-basic -a claude-code
After installation, run the setup skill to configure the server:

```
/red-hat-security-mcp-setup
```

### Installation (Cursor)
This adds the Red Hat Security MCP server to your project's `.mcp.json` and guides you through browser SSO authentication.

```bash
lola install -f rh-basic -a cursor
```
### Step 3: Use the skills

The pack provides 6 skills. See the [rh-basic README](../README.md) for the full list with descriptions and usage examples.

### MCP configuration
### Uninstall

Server definitions live in **`mcps.json`** at the pack root and use HTTP transport:
Remove the skill pack from your project:

- `red-hat-security` -> `https://security-mcp.api.redhat.com/mcp`
```bash
lola uninstall rh-basic
```

After installation, run `/red-hat-security-mcp-setup` to add the server to your project's `.mcp.json` and complete browser SSO authentication.
To also remove the marketplace registry:

```bash
lola market rm rh-agentic-plugins
```
68 changes: 46 additions & 22 deletions rh-sre/.catalog/deploy_and_use.md
Original file line number Diff line number Diff line change
Expand Up @@ -3,50 +3,74 @@
Golden sources: skills/*/SKILL.md, README.md, AGENTS.md
-->

### Prerequisites
## Deploy and use
**Note:** This skill pack is released as Developer Preview. Developer Preview features provide early access to functionality in advance of possible inclusion in a Red Hat product offering. For more information about the support scope of Red Hat Developer Preview features, see [Developer Preview Support Scope](https://access.redhat.com/support/offerings/devpreview).

- Claude Code CLI or IDE extension (if using Claude Code)
- Podman or Docker installed (for container-based MCP servers)
- Red Hat Lightspeed service account ([console](https://console.redhat.com/))
### Prerequisites

### Environment setup
- At least one supported AI coding assistant:
- [Claude Code](https://claude.com/product/claude-code) (CLI or IDE extension)
- [GitHub Copilot](https://github.com/features/copilot) (CLI or VS Code)
- [Cursor](https://www.cursor.com/)
- [Gemini CLI](https://github.com/google-gemini/gemini-cli)
- [OpenCode](https://opencode.ai/)
- [Lola](https://github.com/LobsterTrap/lola) CLI installed
- [Podman](https://podman.io/) (or Docker) — the MCP servers run as containers

Configure Red Hat Lightspeed credentials (names must match **`mcps.json`**):
### Step 1: Install the skill pack

```bash
export LIGHTSPEED_CLIENT_ID="your-service-account-client-id"
export LIGHTSPEED_CLIENT_SECRET="your-service-account-client-secret"
# Add the Red Hat Agentic marketplace (one-time setup)
lola market add rh-agentic-plugins https://raw.githubusercontent.com/RHEcosystemAppEng/agentic-catalog/main/marketplace/rh-agentic-collection.yml

# Install the rh-sre pack (replace claude-code with your AI assistant)
# Valid targets: claude-code, copilot-cli, copilot-vscode, cursor, gemini-cli, opencode
lola install rh-sre -a claude-code
```

For Ansible Automation Platform MCP (optional, for playbook execution flows):
This installs the skills, the instructions file, and the MCP server definitions into your project.

Verify the installation:

```bash
export AAP_MCP_SERVER="your-aap-controller-hostname"
export AAP_API_TOKEN="your-api-token"
lola list
```

### Installation (Lola)
### Step 2: Configure environment variables

The pack uses MCP servers that require credentials passed as environment variables. **Never hardcode tokens — always use environment variables.**

**For CVE discovery and remediation** (`lightspeed-mcp`):

From a checkout of this repository, install the pack with [Lola](https://github.com/LobsterTrap/lola) using the registry file at the repo root:
1. Create a Red Hat Lightspeed service account at [console.redhat.com](https://console.redhat.com/)
2. Export the credentials:

```bash
lola install -f rh-sre
export LIGHTSPEED_CLIENT_ID="<your-client-id>"
export LIGHTSPEED_CLIENT_SECRET="<your-client-secret>"
```

The module is declared in **`marketplace/rh-agentic-collection.yml`** ([agentic-catalog](https://github.com/RHEcosystemAppEng/agentic-catalog)) (`path: rh-sre`). See the root [README.md](../../README.md) for marketplace setup.

### Installation (Claude Code)
**For Ansible Automation Platform playbook execution** (optional — `aap-mcp-job-management`, `aap-mcp-inventory-management`):

```bash
lola install -f rh-sre -a claude-code
export AAP_MCP_SERVER="<your-aap-controller-hostname>"
export AAP_API_TOKEN="<your-api-token>"
```

### Installation (Cursor)
### Step 3: Use the skills

The pack provides 13 skills. See the [rh-sre README](../README.md) for the full list with descriptions and usage examples.

### Uninstall

Remove the skill pack from your project:

```bash
lola install -f rh-sre -a cursor
lola uninstall rh-sre
```

### MCP configuration
To also remove the marketplace registry:

Server definitions live in **`mcps.json`** at the pack root. Use **`${VAR}`** placeholders only; never commit secrets.
```bash
lola market rm rh-agentic-plugins
```
64 changes: 40 additions & 24 deletions rh-virt/.catalog/deploy_and_use.md
Original file line number Diff line number Diff line change
Expand Up @@ -3,55 +3,71 @@
Golden sources: skills/*/SKILL.md, README.md, AGENTS.md
-->

## Deploy and use
**Note:** This skill pack is released as Developer Preview. Developer Preview features provide early access to functionality in advance of possible inclusion in a Red Hat product offering. For more information about the support scope of Red Hat Developer Preview features, see [Developer Preview Support Scope](https://access.redhat.com/support/offerings/devpreview).

### Prerequisites

- Claude Code CLI or IDE extension (if using Claude Code)
- Podman (or Docker) for the container-based MCP server defined in **`mcps.json`**
- At least one supported AI coding assistant:
- [Claude Code](https://claude.com/product/claude-code) (CLI or IDE extension)
- [GitHub Copilot](https://github.com/features/copilot) (CLI or VS Code)
- [Cursor](https://www.cursor.com/)
- [Gemini CLI](https://github.com/google-gemini/gemini-cli)
- [OpenCode](https://opencode.ai/)
- [Lola](https://github.com/LobsterTrap/lola) CLI installed
- [Podman](https://podman.io/) (or Docker) — the MCP server runs as a container
- OpenShift cluster (**>= 4.19**) with the **OpenShift Virtualization** operator installed
- A kubeconfig with RBAC sufficient for VirtualMachine and related KubeVirt resources in target namespaces

### Environment setup

Point **`KUBECONFIG`** at a kubeconfig file the MCP container can read (names must match **`mcps.json`**):
### Step 1: Install the skill pack

```bash
export KUBECONFIG="/path/to/your/kubeconfig"
# Add the Red Hat Agentic marketplace (one-time setup)
lola market add rh-agentic-plugins https://raw.githubusercontent.com/RHEcosystemAppEng/agentic-catalog/main/marketplace/rh-agentic-collection.yml

# Install the rh-virt pack (replace claude-code with your AI assistant)
# Valid targets: claude-code, copilot-cli, copilot-vscode, cursor, gemini-cli, opencode
lola install rh-virt -a claude-code
```

Verify the API sees KubeVirt / VM objects (optional smoke check):
This installs the skills, the instructions file, and the MCP server definitions into your project.

Verify the installation:

```bash
oc get virtualmachines -A
# or
kubectl get vms -A
lola list
```

The pack **`mcps.json`** mounts `${KUBECONFIG}` read-only into the MCP container and passes **`${KUBECONFIG}`** in `env` — use placeholders only in git; never commit kubeconfig contents or secrets.
### Step 2: Configure environment variables

If you build the OpenShift MCP image locally instead of pulling a published image, follow **Building the MCP Server Container Image** in the pack **[README.md](../../README.md)**.
The pack uses an MCP server that requires a kubeconfig passed as an environment variable. **Never hardcode kubeconfig contents — always use environment variables.**

### Installation (Lola)

From a checkout of this repository, install the pack with [Lola](https://github.com/LobsterTrap/lola):
**For cluster operations** (`openshift-virtualization`):

```bash
lola install -f rh-virt
export KUBECONFIG="/path/to/your/kubeconfig"
```

The module is declared in **`marketplace/rh-agentic-collection.yml`** ([agentic-catalog](https://github.com/RHEcosystemAppEng/agentic-catalog)) (`path: rh-virt`). See the root [README.md](../../README.md) for marketplace setup.

### Installation (Claude Code)
Verify the API sees KubeVirt / VM objects (optional smoke check):

```bash
lola install -f rh-virt -a claude-code
oc get virtualmachines -A
```

### Installation (Cursor)
### Step 3: Use the skills

The pack provides 10 skills. See the [rh-virt README](../README.md) for the full list with descriptions and usage examples.

### Uninstall

Remove the skill pack from your project:

```bash
lola install -f rh-virt -a cursor
lola uninstall rh-virt
```

### MCP configuration
To also remove the marketplace registry:

Server definitions live in **`mcps.json`** at the pack root (`openshift-virtualization` server, **`--toolsets`** includes **`kubevirt`**). Use **`${VAR}`** placeholders only; never commit secrets.
```bash
lola market rm rh-agentic-plugins
```
Loading