Conversation
Add documentation page for Erode, an AI-powered architecture drift detection tool that uses LikeC4 models. Includes experimental callout, links to erode.dev and GitHub, and quick start for GitHub Actions, CLI, and Claude Code skill integrations.
|
📝 WalkthroughWalkthroughA new documentation page for the Erode tool has been added to the docs site. The page describes AI-powered architecture drift detection capabilities, includes integration methods (GitHub Actions, CLI, Claude Code Skill), quick-start guidance, and navigation links to related resources. Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~5 minutes Poem
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@apps/docs/src/content/docs/tooling/erode.mdx`:
- Around line 46-48: Under the "Claude Code Skill" subsection (heading "Claude
Code Skill"), add a minimal concrete first step so it reads like a quick start:
briefly state one install or enable action (e.g., install the Erode Claude Code
skill or enable it in Claude), show the minimal required config values or
command to run, and include a one-line example of invoking the skill (e.g., what
a sample prompt or call looks like) and a pointer to the external docs link for
details; keep this as a short 2–3 sentence snippet immediately after the heading
and before the existing link.
- Around line 36-38: The snippet currently shows a standalone "uses:
erode-app/erode@0" step fragment; wrap it in a minimal runnable GitHub Actions
workflow by adding a top-level jobs block with a job id (e.g., "erode"), a
runs-on value (e.g., ubuntu-latest), and a steps list that contains the existing
"uses: erode-app/erode@0" entry so the example is valid under
jobs.<job_id>.steps; update the docs file content around the "uses:
erode-app/erode@0" fragment accordingly.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 62fceceb-1206-4d71-8f6e-b6b32c2b7398
📒 Files selected for processing (1)
apps/docs/src/content/docs/tooling/erode.mdx
| ```yaml | ||
| - uses: erode-app/erode@0 | ||
| ``` |
There was a problem hiding this comment.
🧩 Analysis chain
🌐 Web query:
Does GitHub Actions allow - uses: owner/repo@refas a standalone workflow snippet, or mustusesappear underjobs.<job_id>.steps? Please cite the official GitHub Actions workflow syntax docs.
💡 Result:
No. In a workflow file, - uses: owner/repo@ref is valid only as a step under jobs.<job_id>.steps[*].uses (i.e., jobs.<job_id>.steps: - uses: ...). GitHub’s workflow syntax defines uses for actions at the step level, not as a top-level/standalone workflow snippet. [1]
The only place uses is valid at the job level is jobs.<job_id>.uses, and that is specifically for calling a reusable workflow (with syntax like {owner}/{repo}/.github/workflows/{filename}@{ref}), not owner/repo@ref for an action. [2]
Sources (official docs):
- GitHub Docs — Workflow syntax for GitHub Actions (
jobs.<job_id>.steps[*].usesand examples showinguses:understeps). (docs.github.com) - GitHub Docs — Workflow syntax for GitHub Actions (
jobs.<job_id>.usesfor reusable workflows and its required syntax). (docs.github.com)
Citations:
- 1: https://docs.github.com/en/actions/reference/workflows-and-actions/workflow-syntax
- 2: https://docs.github.com/en/actions/reference/workflows-and-actions/workflow-syntax
Use a runnable workflow example here.
The snippet at line 37 is only a step fragment. GitHub Actions requires uses to appear under jobs.<job_id>.steps, not as a standalone workflow snippet. Wrap it in the minimal jobs → steps context.
Proposed doc fix
### GitHub Actions
```yaml
-- uses: erode-app/erode@0
+jobs:
+ erode:
+ runs-on: ubuntu-latest
+ steps:
+ - uses: erode-app/erode@0</details>
<!-- suggestion_start -->
<details>
<summary>📝 Committable suggestion</summary>
> ‼️ **IMPORTANT**
> Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
```suggestion
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@apps/docs/src/content/docs/tooling/erode.mdx` around lines 36 - 38, The
snippet currently shows a standalone "uses: erode-app/erode@0" step fragment;
wrap it in a minimal runnable GitHub Actions workflow by adding a top-level jobs
block with a job id (e.g., "erode"), a runs-on value (e.g., ubuntu-latest), and
a steps list that contains the existing "uses: erode-app/erode@0" entry so the
example is valid under jobs.<job_id>.steps; update the docs file content around
the "uses: erode-app/erode@0" fragment accordingly.
| ### Claude Code Skill | ||
|
|
||
| Erode is also available as a Claude Code skill — see the [docs](https://erode.dev/docs/getting-started/) for details. |
There was a problem hiding this comment.
Add one concrete first step for the Claude Code skill.
This subsection currently just redirects readers to external docs, so it doesn't really function as a quick start like the GitHub Actions and CLI sections do. A minimal install/config snippet here would make the "three ways" framing consistent.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@apps/docs/src/content/docs/tooling/erode.mdx` around lines 46 - 48, Under the
"Claude Code Skill" subsection (heading "Claude Code Skill"), add a minimal
concrete first step so it reads like a quick start: briefly state one install or
enable action (e.g., install the Erode Claude Code skill or enable it in
Claude), show the minimal required config values or command to run, and include
a one-line example of invoking the skill (e.g., what a sample prompt or call
looks like) and a pointer to the external docs link for details; keep this as a
short 2–3 sentence snippet immediately after the heading and before the existing
link.
Summary
Summary by CodeRabbit