Skip to content

forcedotcom/sf-skills / plugins/builder/experience-cms/skills/experience-cms-content-generate

experience-cms-content-generate

Verified

Creates, edits, and publishes Salesforce CMS content of any kind — any domain, any topic. Single and bulk: create many in parallel, edit one or many, publish all or a subset. Use this skill ANY TIME a user asks to create, generate, write, draft, author, or add content, OR to update, edit, or revise a content record, OR to publish it, OR to delete/remove a content record. Triggers like "create a <thing> about X", "create 5 <things>", "update content <id>", "publish content <id>", "publish the record <id>", "make <id> live", "delete content <id>" — where <thing> is any user-named content type. Activates FIRST whenever content authoring, editing, publishing, or deletion is mentioned, regardless of subject. Handles the full workflow: finding the content type, resolving the workspace, creating content, editing or publishing it — including a record identified by its variantId. Does not apply to defining a content type / schema (use experience-cms-content-type-generate), cloning, versioning, workspaces, or media.

assets/display-formats.md

View on GitHub
# Content display formats

Consistent tables used after every successful `create_cms_content`, `update_cms_content_variant`, `get_content` / `get_content_variant` fetch, and `publish_content` response. Never switch between formats mid-session.

**RENDER AS A REAL MARKDOWN TABLE — do NOT wrap it in a code fence.** The templates below are shown inside ```` ```text ```` fences ONLY so you can see the literal layout. When you emit the table to the user, write the raw markdown (`| Field | Value |` with the `|---|---|` separator row) directly in your chat response with **no surrounding ```` ``` ```` fence and no `text`/`markdown` language tag** — a fenced block renders as preformatted plain text and the pipes do NOT become a table. The pipe rows must be at the start of a line, one row per line, so the chat client renders an actual table. This applies to the fetched content body too (Step 0-U / Step 6): show it as a rendered table, never as pasted plain text.

## Single content — summary table

```text
| Field | Value |
|---|---|
| **Title** | <title> |
| **Content Key** | <contentKey> |
| **Managed Content ID** | <managedContentId> |
| **Content Type** | <contentFqn> |
| **Workspace / Folder** | <contentSpace.label>[/<folder.label>] |
| **URL slug** | <urlName> |
```

Omit fields the response did not include.

## Single content — content body table

```text
| Field | Value |
|---|---|
| **<fieldName>** | <fieldValue> |
| ... | ... |
```

Iterate over all keys in `contentBody` from the response. For nested objects (e.g. `bannerImage` with `source` and `altText`), flatten into readable sub-fields:

```text
| **Banner Image** | <bannerImage.source.ref> |
| **Banner Alt Text** | <bannerImage.altText> |
```

## Bulk content — summary table

```text
Created <N> content items:

| # | Title | Managed Content ID | Variant ID |
|---|---|---|---|
| 1 | <title1> | <id1> | <variantId1> |
| 2 | <title2> | <id2> | <variantId2> |
| ... | ... | ... | ... |
```

Then display each item's content body using the single-item format above, prefixed with its number:

```text
### Item 1: <title1>
| Field | Value |
|---|---|
| ... | ... |

### Item 2: <title2>
| Field | Value |
|---|---|
| ... | ... |
```

## Single publish confirmation

```text
Content published successfully.

  Title:              <title>
  Managed Content ID: <managedContentId>
  Variant ID:         <managedContentVariantId>
```

## Bulk publish confirmation

```text
Published <N> content items successfully.

| # | Title | Managed Content ID | Variant ID |
|---|---|---|---|
| 1 | <title1> | <id1> | <variantId1> |
| 2 | <title2> | <id2> | <variantId2> |
| ... | ... | ... | ... |
```
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall