Merge branch 'main' into t/tse/21829588/update-clt-skills

This commit is contained in:
suhanigupta-collab 2026-04-23 12:21:17 +05:30 committed by GitHub
commit d0c9eb2331
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 21 additions and 123 deletions

View File

@ -1,3 +1,12 @@
## [1.7.2](https://github.com/forcedotcom/afv-library/compare/1.7.1...1.7.2) (2026-04-22)
### Bug Fixes
* @W-22134404@ delete fragment skill ([#212](https://github.com/forcedotcom/afv-library/issues/212)) ([c818135](https://github.com/forcedotcom/afv-library/commit/c8181350b47fe0b2f512a9d2d01bd11dceed3793))
## [1.7.1](https://github.com/forcedotcom/afv-library/compare/1.7.0...1.7.1) (2026-04-21)

View File

@ -1,6 +1,6 @@
{
"name": "@salesforce/afv-skills",
"version": "1.7.1",
"version": "1.7.2",
"description": "Salesforce skills for Agentforce Vibes",
"license": "CC-BY-NC-4.0",
"files": [

View File

@ -1,117 +0,0 @@
---
name: generating-fragment
description: "Use this skill when users need to create or edit Salesforce Fragments (reusable UI pieces). Trigger when users mention fragments, UEM blocks, reusable UI templates, structured rendering across Slack/Mobile/LEX, or block-based layouts. Also use when users want to create unified experience components. Always use this skill for any fragment work."
---
## When to Use This Skill
Use this skill when you need to:
- Create reusable UI fragments for Salesforce experiences
- Generate Fragment metadata following UEM structure
- Build fragments for Slack, Mobile, LEX, and other Salesforce experiences
- Troubleshoot deployment errors related to Fragments
## Specification
# Fragment Generation Guide
## 📋 Overview
Fragments are reusable pieces of UI similar to templates, with placeholders for actual data values. The purpose of this file is to assist developers in creating and editing fragments.
## 🎯 Purpose
Fragments render data in a structured and unified way across various Salesforce experiences like Slack, Mobile, LEX etc
## ⚙️ Composition
A fragment is a UEM (Unified Experience Model) tree of blocks and regions. The fragment you return must follow the Typescript interfaces below:
```ts
interface BlockType {
type: 'block'
definition: string // {namespace}/{blockName}
attributes?: Record<string, any>
children?: (BlockType | RegionType)[]
}
interface RegionType {
type: 'region'
name: string
children: BlockType[]
}
```
---
## 🔧 Available Metadata Actions
### When to Use Each Action
#### discoverUiComponents
**When:** You want to see what block components are available for fragments.
**Purpose:** Discover the palette of available blocks that can be used in fragment composition.
**Input Parameters:**
- `pageType` (required): "FRAGMENT"
- `pageContext` (optional): JSON object - not required for FRAGMENT type
- `searchQuery` (optional): String to filter components by name or description
**Returns:** List of components with:
- `definition`: Fully qualified name (e.g., "namespace/definiton")
- `description`: Component description
- `label`: Human-readable label
- `attributes`: Optional attribute metadata
**Use for:** Finding available blocks before building your fragment structure.
#### getUiComponentSchemas
**When:** You know which components you want but need to understand their properties and attributes.
**Purpose:** Get detailed JSON schemas for component configuration, including property types, required vs optional fields, and validation rules.
**Input Parameters:**
- `pageType` (required): "FRAGMENT"
- `pageContext` (optional): JSON object - not required for FRAGMENT type
- `componentDefinitions` (required): List of fully qualified names (e.g., ["namespace/definition"])
- `includeKnowledge` (optional): Boolean, defaults to true - includes additional component-specific guidance
**Returns:**
- `componentSchemas`: List of results (supports partial failures)
- **Success entries**: Contains JSON schema with property definitions, types, constraints
- **Failure entries**: Contains error message explaining why schema couldn't be retrieved
- `$defs`: Schema definitions and references (if schema transformation applied)
**Use for:** Understanding how to configure component attributes before adding blocks to your fragment.
**Key Feature:** Supports partial failures - if some components can't be found, you still get schemas for the successful ones.
---
## 💡 Typical Workflow
1. **Discover Available Blocks**
- Use `discoverUiComponents` to explore what blocks are available
- Optional: Use `searchQuery` to filter by keywords (e.g., "text", "button", "image")
2. **Select Components**
- Choose blocks that fit your fragment requirements
- Note their fully qualified definitions (e.g., "namespace/definition")
3. **Get Component Schemas**
- Use `getUiComponentSchemas` with the selected component definitions
- Review the JSON schemas to understand required and optional attributes
4. **Build Fragment**
- Construct your fragment using the UEM tree structure
- Configure block attributes according to the schemas
- Use the TypeScript interfaces defined above
---
## ⚠️ Important Notes
- Block definitions always follow the `{namespace}/{blockName}` convention
- Use the same definition format returned by `discoverUiComponents` when calling `getUiComponentSchemas`
- The FRAGMENT page type doesn't require additional `pageContext` parameters
- Schemas include both required and optional attributes - review carefully to ensure valid configuration

View File

@ -33,11 +33,12 @@ Universal routing skill for searching and retrieving existing images and media.
When a user requests to find an image:
**Your first response MUST be plain text only — zero tool calls.** You MUST follow this sequence:
**Your first action MUST use the ask_followup_question tool to present search sources.**
1. **Use ask_followup_question** to present available search sources as options
2. **Receive the user's selection** from the tool response
3. **Then** call the appropriate search tool based on their choice
1. **First response MUST be text only:** A numbered list of search sources for the user. No tool calls of any kind.
2. **Wait for user to reply** with their selected option number
3. **Only then** call the appropriate search tool (this is the FIRST tool call in the entire interaction)
**Example of what NOT to do:**
- ❌ Calling ANY tool before the user picks a source (MCP tools, file reads, descriptor checks, etc.)
@ -279,7 +280,11 @@ Ask the user to provide:
## Presenting Search Results
Parse the tool response and present **ALL** results as numbered options. Show the image title only — do not display the URL. When the user selects an option, use the URL internally to apply the image.
**Your action MUST use the `ask_followup_question` tool to present search results as options.**
1. **Parse the tool response** — Extract all image results (title and source)
2. **Use `ask_followup_question`** to present ALL results as selectable options. Show the image title only — do not display the URL.
3. **Receive the user's selection** from the tool response
4. **Then** apply the selected image
```
I found 4 images. Which one would you like to use?
@ -301,6 +306,7 @@ I found 4 images. Which one would you like to use?
## Applying the Selected Image
After the user chooses:
1. Confirm the selection with image name and URL