diff --git a/.agents/skills/nemoclaw-manage-policy/SKILL.md b/.agents/skills/nemoclaw-manage-policy/SKILL.md
index 4f23dd219..a4dc03e29 100644
--- a/.agents/skills/nemoclaw-manage-policy/SKILL.md
+++ b/.agents/skills/nemoclaw-manage-policy/SKILL.md
@@ -114,13 +114,14 @@ Dynamic changes apply a policy update to a running sandbox without restarting it
 
 Create a YAML file with the endpoints to add.
 Follow the same format as the baseline policy in `nemoclaw-blueprint/policies/openclaw-sandbox.yaml`.
+The file must include the mandatory `version` field (e.g., `version: 1`) to be accepted by the OpenShell parser.
 
 ### Apply the Policy
 
 Use the OpenShell CLI to apply the policy update:
 
 ```console
-$ openshell policy set <policy-file>
+$ openshell policy set --policy <policy-file> <name>
 ```
 
 The change takes effect immediately.
@@ -150,14 +151,22 @@ Available presets:
 | `slack` | Slack API and webhooks |
 | `telegram` | Telegram Bot API |
 
-To apply a preset to a running sandbox, pass it as a policy file:
+To apply a preset to a running sandbox:
 
 ```console
-$ openshell policy set nemoclaw-blueprint/policies/presets/pypi.yaml
+$ nemoclaw <name> policy-add
+
+To list which presets are applied to a sandbox:
+
+```console
+$ nemoclaw <name> policy-list
 ```
 
 To include a preset in the baseline, merge its entries into `openclaw-sandbox.yaml` and re-run `nemoclaw onboard`.
 
+> **Note:** The `openshell policy set --policy <file> <name>` command operates on raw policy files and does not accept the `preset:` metadata block used in preset YAML files.
+> Use `nemoclaw <name> policy-add` for presets.
+
 ## Related Skills
 
 - `nemoclaw-reference` — Network Policies for the full baseline policy reference
diff --git a/docs/network-policy/customize-network-policy.md b/docs/network-policy/customize-network-policy.md
index 1749f0606..a585176d8 100644
--- a/docs/network-policy/customize-network-policy.md
+++ b/docs/network-policy/customize-network-policy.md
@@ -75,13 +75,14 @@ Dynamic changes apply a policy update to a running sandbox without restarting it
 
 Create a YAML file with the endpoints to add.
 Follow the same format as the baseline policy in `nemoclaw-blueprint/policies/openclaw-sandbox.yaml`.
+The file must include the mandatory `version` field (e.g., `version: 1`) to be accepted by the OpenShell parser.
 
 ### Apply the Policy
 
 Use the OpenShell CLI to apply the policy update:
 
 ```console
-$ openshell policy set <policy-file>
+$ openshell policy set --policy <policy-file> <name>
 ```
 
 The change takes effect immediately.
@@ -111,14 +112,31 @@ Available presets:
 | `slack` | Slack API and webhooks |
 | `telegram` | Telegram Bot API |
 
-To apply a preset to a running sandbox, pass it as a policy file:
+To apply a preset to a running sandbox:
 
 ```console
-$ openshell policy set nemoclaw-blueprint/policies/presets/pypi.yaml
+$ nemoclaw <name> policy-add
+```
+
+For example, to add PyPI access to a running sandbox, run the command and select 'pypi' at the prompt:
+
+```console
+$ nemoclaw my-assistant policy-add pypi
+```
+
+To list which presets are applied to a sandbox:
+
+```console
+$ nemoclaw <name> policy-list
 ```
 
 To include a preset in the baseline, merge its entries into `openclaw-sandbox.yaml` and re-run `nemoclaw onboard`.
 
+:::{note}
+The `openshell policy set --policy <file> <name>` command operates on raw policy files and does not accept the `preset:` metadata block used in preset YAML files.
+Use `nemoclaw <name> policy-add` for presets.
+:::
+
 ## Related Topics
 
 - [Approve or Deny Agent Network Requests](approve-network-requests.md) for real-time operator approval.