docs: add permissionRequest hook and built-in CLI skills to Learning Hub

- automating-with-hooks.md: Add new permissionRequest hook event to the
  events table, with an explanatory note and a practical example showing
  how to programmatically approve or deny tool permission requests in CI
  and automated environments (introduced in CLI 1.0.16)
- creating-effective-skills.md: Add a 'Built-in CLI Skills' section
  documenting that CLI 1.0.17 ships with built-in skills pre-installed,
  how to list them, and how they complement community and personal skills

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

website/src/content/docs/learning-hub/automating-with-hooks.md

@@ -3,7 +3,7 @@ title: 'Automating with Hooks'
 description: 'Learn how to use hooks to automate lifecycle events like formatting, linting, and governance checks during Copilot agent sessions.'
 authors:
   - GitHub Copilot Learning Hub Team
-lastUpdated: 2026-04-01
+lastUpdated: 2026-04-03
 estimatedReadingTime: '8 minutes'
 tags:
   - hooks
@@ -90,6 +90,7 @@ Hooks can trigger on several lifecycle events:
 | `sessionStart` | Agent session begins or resumes | Initialize environments, log session starts, validate project state |
 | `sessionEnd` | Agent session completes or is terminated | Clean up temp files, generate reports, send notifications |
 | `userPromptSubmitted` | User submits a prompt | Log requests for auditing and compliance |
+| `permissionRequest` | Agent requests permission to take an action | **Programmatically approve or deny** permission requests, auto-approve trusted action categories in CI/automation |
 | `preToolUse` | Before the agent uses any tool (e.g., `bash`, `edit`) | **Approve or deny** tool executions, block dangerous commands, enforce security policies |
 | `postToolUse` | After a tool **successfully** completes execution | Log results, track usage, format code after edits |
 | `postToolUseFailure` | When a tool call **fails with an error** | Log errors for debugging, send failure alerts, track error patterns |
@@ -101,6 +102,8 @@ Hooks can trigger on several lifecycle events:
 
 > **Key insight**: The `preToolUse` hook is the most powerful — it can **approve or deny** individual tool executions. This enables fine-grained security policies like blocking specific shell commands or requiring approval for sensitive file operations.
 
+> **New in 1.0.16**: The `permissionRequest` hook is a companion to `preToolUse` that fires when the agent requests permission for an action at the permission-prompt level, before the tool is invoked. Use it to programmatically approve trusted action categories in CI and automation pipelines without human interaction.
+
 ### sessionStart additionalContext
 
 The `sessionStart` hook supports an `additionalContext` field in its output. When your hook script writes JSON to stdout containing an `additionalContext` key, that text is **injected directly into the conversation** at the start of the session. This lets hooks dynamically provide environment-specific context—such as the current git branch, deployment environment, or team onboarding notes—without requiring the user to paste it manually.
@@ -207,6 +210,51 @@ automatically before the agent commits changes.
 
 ## Practical Examples
 
+### Programmatic Permission Approval with permissionRequest
+
+The `permissionRequest` hook fires when the agent requests permission to take an action — before the agent's permission prompt is shown to the user. Use it to auto-approve certain categories of actions in CI and automation environments, or to implement policy-based controls over what the agent is allowed to do:
+
+```json
+{
+  "version": 1,
+  "hooks": {
+    "permissionRequest": [
+      {
+        "type": "command",
+        "bash": "./scripts/approve-or-deny-permission.sh",
+        "cwd": ".",
+        "timeoutSec": 5
+      }
+    ]
+  }
+}
+```
+
+The hook receives JSON input describing the requested action. Your script can exit `0` to approve the request, or non-zero to deny it. This is particularly useful in:
+
+- **CI pipelines**: Auto-approve read-only actions (file reads, searches) while denying write operations.
+- **Governance environments**: Enforce a policy that logs and approves only pre-defined action categories.
+- **Automated workflows**: Allow the agent to run without interactive prompts for well-understood tasks.
+
+```bash
+#!/usr/bin/env bash
+# approve-or-deny-permission.sh
+# Auto-approve read-only actions; deny everything else
+
+INPUT=$(cat)
+TOOL=$(echo "$INPUT" | jq -r '.tool // empty')
+
+case "$TOOL" in
+  read|search|glob|grep|list_dir)
+    exit 0  # Approve read-only tools
+    ;;
+  *)
+    echo "Permission denied for tool: $TOOL" >&2
+    exit 1  # Deny anything that modifies state
+    ;;
+esac
+```
+
 ### Handling Tool Failures with postToolUseFailure
 
 The `postToolUseFailure` hook fires when a tool call fails with an error — distinct from `postToolUse`, which only fires on success. Use it to log errors, send failure alerts, or implement retry logic:

website/src/content/docs/learning-hub/creating-effective-skills.md

@@ -3,7 +3,7 @@ title: 'Creating Effective Skills'
 description: 'Master the art of writing reusable, shareable skill folders that deliver consistent results across your team.'
 authors:
   - GitHub Copilot Learning Hub Team
-lastUpdated: 2026-02-26
+lastUpdated: 2026-04-03
 estimatedReadingTime: '9 minutes'
 tags:
   - skills
@@ -35,6 +35,16 @@ Skills are folders containing a `SKILL.md` file and optional bundled assets. The
 - Skills are **more normalised across coding agent systems** via the open [Agent Skills specification](https://agentskills.io/home)
 - Skills still support **slash-command invocation** just like prompts did
 
+### Built-in CLI Skills
+
+Starting with GitHub Copilot CLI **1.0.17**, the CLI ships with a set of **built-in skills** that are available immediately after installation — no setup required. These skills cover common tasks like customizing the Copilot coding agent's environment. To discover what built-in skills are available, list them from within a session:
+
+```
+/skills list
+```
+
+Built-in skills work exactly like your own project or personal skills — agents can discover and invoke them automatically, or you can invoke them manually with their `/command` name. They complement the community skills in this repository and the skills you create yourself.
+
 ### How Skills Differ from Other Customizations
 
 **Skills vs Instructions**: