workshop docs: add gh-aw doc links (batch 2) (#2025)

Author: github-actions[bot]

workshop/08b-interpret-your-run.md

@@ -51,7 +51,7 @@ Then verify the real output in your repository. For **Daily Report Status**, tha
 
 If your run does not look right, start with these quick checks before changing the workflow:
 
-- **The workflow never appears in Actions** — confirm the workflow file is committed on `main`, then refresh. If you use the terminal path, run `gh aw compile` to catch compile errors.
+- **The workflow never appears in Actions** — confirm the workflow file is committed on `main`, then refresh. If you use the terminal path, run `gh aw compile` to catch [compile](https://github.github.com/gh-aw/reference/compilation-process/) errors.
 - **The log shows lots of thinking but no useful action** — your instructions may be too vague. Keep the run open, then refine the workflow body in a later step.
 - **The run finishes but nothing changed in GitHub** — make sure your repository has an open issue and that the workflow had permission to write.
 

workshop/14-next-steps.md

@@ -18,7 +18,7 @@ Take stock of everything you've learned, then choose a direction for what to bui
 
 You've gone from zero to a fully automated, AI-powered workflow that:
 
-- Runs on a schedule in GitHub Actions
+- Runs on a [schedule](https://github.github.com/gh-aw/reference/triggers/#scheduled-triggers-schedule) in GitHub Actions
 - Uses gh-aw to call an AI model from a simple YAML file
 - Posts a daily summary without any manual intervention
 

workshop/14b-pr-reviewer-workflow.md

@@ -65,7 +65,7 @@ A few things to notice in this frontmatter:
 - `safe-outputs: create-issue-comment: limit: 1` caps the workflow at one comment per run, preventing spam if the workflow is triggered repeatedly.
 - The agent brief uses only information available in the trigger context (changed file paths, PR title, PR description) — it does not need to read raw file contents to produce a useful first-pass review.
 
-## Compile and Push
+## [Compile](https://github.github.com/gh-aw/reference/compilation-process/) and Push
 
 From your repository root, compile the workflow:
 

workshop/16-connect-data-source.md

@@ -124,7 +124,7 @@ GitHub resolves the step-output expressions before the AI sees the prompt, so th
 
 ✏️ Try it: Change `"two short paragraphs"` to `"one bullet list per topic"` and re-run. Notice how the output format shifts.
 
-### Compile, push, and test
+### [Compile](https://github.github.com/gh-aw/reference/compilation-process/), push, and test
 
 The `/agentic-workflows` skill recompiles the lock file automatically. If you edited the workflow manually, run `gh aw compile` first, then push:
 

workshop/17-add-mcp-tools.md

@@ -83,7 +83,7 @@ Open your daily-status workflow file (`.github/workflows/daily-status.md`) and f
 >
 > `mode: gh-proxy` routes all GitHub tool calls through the `GITHUB_TOKEN` that Actions provides automatically — no extra credentials or setup needed on github.com or GHEC.
 >
-> On GHES, the GitHub MCP server is supported from GHES 3.16+. If your instance is older, the `tools:` block will compile without errors but the agent's tool calls will fail at runtime. Verify your GHES version and confirm with your admin that the Copilot MCP proxy feature is enabled for your organization.
+> On GHES, the GitHub MCP server is supported from GHES 3.16+. If your instance is older, the `tools:` block will [compile](https://github.github.com/gh-aw/reference/compilation-process/) without errors but the agent's tool calls will fail at runtime. Verify your GHES version and confirm with your admin that the Copilot MCP proxy feature is enabled for your organization.
 >
 > If MCP is unavailable in your environment, the [Connect a Live Data Source](16-connect-data-source.md) step covers an alternative approach using deterministic shell steps that only require `GITHUB_TOKEN` and the `gh` CLI — no MCP server needed.
 >

workshop/18-share-and-reuse.md

@@ -65,7 +65,7 @@ For example, if your username is `jsmith`, your repo is `my-workshop`, and your
 gh aw add jsmith/my-workshop/daily-status
 ```
 
-Your teammate runs this inside their repository. `gh aw add` copies the Markdown file into their `.github/workflows/` folder and they can then edit and compile it for their own context.
+Your teammate runs this inside their repository. `gh aw add` copies the Markdown file into their `.github/workflows/` folder and they can then edit and [compile](https://github.github.com/gh-aw/reference/compilation-process/) it for their own context.
 
 > [!TIP]
 > You can also pin to a specific version using a tag or commit SHA: `gh aw add jsmith/my-workshop/daily-status@v1.0`. This is useful when you want to guarantee stability for a team-wide rollout.

workshop/19-research-driven-training-node.md

@@ -66,7 +66,7 @@ Keep the comment concise and traceable to real sources you used.
 
 ### Validate before opening a pull request
 
-Run markdown lint and compile checks so your proposal is production-ready:
+Run markdown lint and [compile](https://github.github.com/gh-aw/reference/compilation-process/) checks so your proposal is production-ready:
 
 ```bash
 npx --yes markdownlint-cli2 "workshop/**/*.md"

workshop/20-persistent-memory.md

@@ -114,7 +114,7 @@ have already reported on. On each run:
 > [!TIP]
 > Be explicit in the brief about _reading_ and _writing_ the memory. The agent will not automatically persist anything unless you ask it to in the task brief.
 
-### Compile, validate, and push
+### [Compile](https://github.github.com/gh-aw/reference/compilation-process/), validate, and push
 
 The `/agentic-workflows` skill recompiles the lock file automatically. If you edited manually, run `gh aw compile` first to confirm the memory block is valid.