docs(skills): use markdown documentation links

Signed-off-by: Johnny Greco <jogreco@nvidia.com>

Author: johnnygreco

skills/debug-inference/SKILL.md

@@ -34,7 +34,7 @@ For local or self-hosted engines such as Ollama, vLLM, SGLang, TRT-LLM, and many
 - The active gateway is running
 - You know the failing setup, or can infer it from commands and config
 
-Use `openshell --help` and nested `--help` output as the authority for the installed CLI version. Use the published [inference routing guide](https://docs.nvidia.com/openshell/latest/sandboxes/inference-routing) for route behavior and [provider management guide](https://docs.nvidia.com/openshell/latest/sandboxes/manage-providers) for credential and profile concepts.
+Use `openshell --help` and nested `--help` output as the authority for the installed CLI version. Use the published [inference routing guide](https://docs.nvidia.com/openshell/latest/sandboxes/inference-routing.md) for route behavior and [provider management guide](https://docs.nvidia.com/openshell/latest/sandboxes/manage-providers.md) for credential and profile concepts.
 
 ## Tools Available
 

skills/debug-openshell-cluster/SKILL.md

@@ -36,7 +36,7 @@ For local evaluation only, TLS may be disabled and the gateway can be reached th
 - For Kubernetes: `kubectl` must target the cluster that hosts OpenShell and Helm version 3 or later must be available.
 - For Docker or Podman: the runtime socket must be reachable from the gateway host.
 
-Use `openshell --help` and nested `--help` output as the authority for the installed CLI version. Use the published [installation guide](https://docs.nvidia.com/openshell/latest/about/installation), [compute-driver reference](https://docs.nvidia.com/openshell/latest/reference/sandbox-compute-drivers), [gateway configuration reference](https://docs.nvidia.com/openshell/latest/reference/gateway-config), and [Kubernetes setup guide](https://docs.nvidia.com/openshell/latest/kubernetes/setup) as the authority for deployment and configuration behavior.
+Use `openshell --help` and nested `--help` output as the authority for the installed CLI version. Use the published [installation guide](https://docs.nvidia.com/openshell/latest/about/installation.md), [compute-driver reference](https://docs.nvidia.com/openshell/latest/reference/sandbox-compute-drivers.md), [gateway configuration reference](https://docs.nvidia.com/openshell/latest/reference/gateway-config.md), and [Kubernetes setup guide](https://docs.nvidia.com/openshell/latest/kubernetes/setup.md) as the authority for deployment and configuration behavior.
 
 ## Workflow
 

skills/generate-sandbox-policy/SKILL.md

@@ -157,7 +157,7 @@ You may need to go back and forth a few times. Keep the loop tight:
 
 ## Step 3: Read the Policy Schema
 
-Read the published [policy schema reference](https://docs.nvidia.com/openshell/latest/reference/policy-schema) before generating or changing a policy. Published documentation is the authority for the current schema; do not infer fields from examples in this skill.
+Read the published [policy schema reference](https://docs.nvidia.com/openshell/latest/reference/policy-schema.md) before generating or changing a policy. Published documentation is the authority for the current schema; do not infer fields from examples in this skill.
 
 Key sections to reference:
 - **Policy Schema Reference** — top-level structure
@@ -169,9 +169,9 @@ Key sections to reference:
 - **Network Middleware** - top-level middleware configs, ordering, host selection, and failure behavior
 - **Validation Rules** — what combinations are valid/invalid
 
-When middleware is requested, also read the published [supervisor middleware guide](https://docs.nvidia.com/openshell/latest/extensibility/supervisor-middleware).
+When middleware is requested, also read the published [supervisor middleware guide](https://docs.nvidia.com/openshell/latest/extensibility/supervisor-middleware.md).
 
-For enforcement concepts and the shipped baseline, read [sandbox policies](https://docs.nvidia.com/openshell/latest/sandboxes/policies) and the [default policy reference](https://docs.nvidia.com/openshell/latest/reference/default-policy). The default policy is baked into the community base image (`ghcr.io/nvidia/openshell-community/sandboxes/base:latest`).
+For enforcement concepts and the shipped baseline, read [sandbox policies](https://docs.nvidia.com/openshell/latest/sandboxes/policies.md) and the [default policy reference](https://docs.nvidia.com/openshell/latest/reference/default-policy.md). The default policy is baked into the community base image (`ghcr.io/nvidia/openshell-community/sandboxes/base:latest`).
 
 ## Step 4: Choose Policy Shape
 
@@ -632,9 +632,9 @@ private_services:
 
 ## Additional Resources
 
-- [Policy schema](https://docs.nvidia.com/openshell/latest/reference/policy-schema)
-- [Sandbox policies](https://docs.nvidia.com/openshell/latest/sandboxes/policies)
-- [Default policy](https://docs.nvidia.com/openshell/latest/reference/default-policy)
-- [Supervisor middleware](https://docs.nvidia.com/openshell/latest/extensibility/supervisor-middleware)
+- [Policy schema](https://docs.nvidia.com/openshell/latest/reference/policy-schema.md)
+- [Sandbox policies](https://docs.nvidia.com/openshell/latest/sandboxes/policies.md)
+- [Default policy](https://docs.nvidia.com/openshell/latest/reference/default-policy.md)
+- [Supervisor middleware](https://docs.nvidia.com/openshell/latest/extensibility/supervisor-middleware.md)
 - Default policy: baked into the community base image (`ghcr.io/nvidia/openshell-community/sandboxes/base:latest`)
 - For translation examples from real API docs, see [examples.md](examples.md)

skills/openshell-cli/SKILL.md

@@ -25,7 +25,7 @@ This is your primary fallback. Use it freely -- the CLI's help output is authori
 
 ## Prerequisites
 
-- `openshell` is on the PATH. Follow the published [installation guide](https://docs.nvidia.com/openshell/latest/about/installation) when it is not installed.
+- `openshell` is on the PATH. Follow the published [installation guide](https://docs.nvidia.com/openshell/latest/about/installation.md) when it is not installed.
 - A reachable OpenShell gateway backed by Docker, Podman, Kubernetes, or the experimental VM driver
 - Docker is running only when using BYOC local builds or a Docker-backed gateway
 - For Kubernetes deployments: `kubectl` and Helm access to the target cluster
@@ -34,11 +34,11 @@ This is your primary fallback. Use it freely -- the CLI's help output is authori
 
 Use `openshell --help` and nested `--help` output as the authority for the installed CLI version. Use the published documentation for product concepts and supported workflows:
 
-- [Manage gateways](https://docs.nvidia.com/openshell/latest/sandboxes/manage-gateways)
-- [Manage sandboxes](https://docs.nvidia.com/openshell/latest/sandboxes/manage-sandboxes)
-- [Manage providers](https://docs.nvidia.com/openshell/latest/sandboxes/manage-providers)
-- [Sandbox policies](https://docs.nvidia.com/openshell/latest/sandboxes/policies)
-- [Inference routing](https://docs.nvidia.com/openshell/latest/sandboxes/inference-routing)
+- [Manage gateways](https://docs.nvidia.com/openshell/latest/sandboxes/manage-gateways.md)
+- [Manage sandboxes](https://docs.nvidia.com/openshell/latest/sandboxes/manage-sandboxes.md)
+- [Manage providers](https://docs.nvidia.com/openshell/latest/sandboxes/manage-providers.md)
+- [Sandbox policies](https://docs.nvidia.com/openshell/latest/sandboxes/policies.md)
+- [Inference routing](https://docs.nvidia.com/openshell/latest/sandboxes/inference-routing.md)
 
 ---