@salesforce/afv-skills 1.7.0 β 1.7.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +28 -23
- package/package.json +1 -1
- package/skills/generating-flow/SKILL.md +3 -1
package/README.md
CHANGED
|
@@ -1,10 +1,8 @@
|
|
|
1
1
|
# Agentforce Vibes Library
|
|
2
2
|
|
|
3
|
-
|
|
3
|
+
This repository provides a curated collection of Salesforce agent skills for building applications. It includes skills for Agentforce agents, Lightning apps, Flow, Apex, SOQL, Lightning Web Components (LWC), UI bundles, objects and fields, permission sets, and related areas.
|
|
4
4
|
|
|
5
|
-
|
|
6
|
-
|
|
7
|
-
This repository curates Salesforce-focused skills from the wider developer community to accelerate Agentforce Vibes agentic workflows.
|
|
5
|
+
The skills are contributed by Salesforce and the broader community. Itβs optimized for Agentforce Vibes and can be used with any AI tool that supports skills.
|
|
8
6
|
|
|
9
7
|
## ποΈ Structure
|
|
10
8
|
|
|
@@ -23,44 +21,51 @@ afv-library/
|
|
|
23
21
|
βββ README.md
|
|
24
22
|
```
|
|
25
23
|
|
|
26
|
-
##
|
|
24
|
+
## π Usage
|
|
25
|
+
|
|
26
|
+
| **Tool** | **Usage** |
|
|
27
|
+
|----------|-------------|
|
|
28
|
+
| **Agentforce Vibes** | Skills are auto-installed and auto-updated |
|
|
29
|
+
| **OpenCode, Claude Code, Codex, Cursor, [more](https://agentskills.io/)** | `npx skills add forcedotcom/afv-library` |
|
|
27
30
|
|
|
28
|
-
|
|
31
|
+
## π¦ Samples
|
|
29
32
|
|
|
30
|
-
|
|
33
|
+
The `samples/` folder contains synced sample apps. For example, `samples/ui-bundle-template-app-react-sample-b2e/` tracks the npm package `@salesforce/ui-bundle-template-app-react-sample-b2e` (nightly and on manual trigger via GitHub Actions).
|
|
31
34
|
|
|
32
|
-
|
|
35
|
+
To run the same sync locally from the repository root:
|
|
33
36
|
|
|
34
37
|
```bash
|
|
35
38
|
npm install
|
|
36
39
|
npm run sync-react-b2e-sample
|
|
37
40
|
```
|
|
38
41
|
|
|
39
|
-
The GitHub Action runs
|
|
40
|
-
|
|
42
|
+
The GitHub Action runs the same commands and opens a pull request when the npm package version changes. For more information, see [samples/README.md](samples/README.md).
|
|
41
43
|
|
|
42
44
|
## π οΈ Agent Skills
|
|
43
45
|
|
|
44
|
-
Agent Skills
|
|
46
|
+
Agent Skills package executable workflows, scripts, and reference material into self-contained directories. This repository follows the open [Agent Skills specification](https://agentskills.io/) and can be used with OpenCode, Claude Code, Codex, Cursor, and other tools that support skills.
|
|
45
47
|
|
|
46
48
|
### Directory Structure
|
|
47
49
|
|
|
48
|
-
Each skill is a folder
|
|
49
|
-
- `SKILL.md` (required)
|
|
50
|
-
- `scripts/` (optional)
|
|
51
|
-
- `references/` (optional)
|
|
52
|
-
- `assets/` (optional)
|
|
53
|
-
|
|
50
|
+
Each skill is a folder that can include:
|
|
51
|
+
- `SKILL.md` (required): Instructions and YAML front matter.
|
|
52
|
+
- `scripts/` (optional): Executable scripts (For example, Python, Bash, or JavaScript).
|
|
53
|
+
- `references/` (optional): Extra reference documentation.
|
|
54
|
+
- `assets/` (optional): Templates, schemas, and lookup data
|
|
54
55
|
|
|
55
56
|
## π€ Contributing
|
|
56
57
|
|
|
57
|
-
See [Contributing](./CONTRIBUTING.md)
|
|
58
|
+
See [Contributing](./CONTRIBUTING.md).
|
|
58
59
|
|
|
60
|
+
## π¬ Feedback
|
|
59
61
|
|
|
60
|
-
|
|
62
|
+
- Open an issue in this repository
|
|
63
|
+
- Open a pull request with suggested changes
|
|
64
|
+
- Use GitHub Discussions or the pull request thread for broader conversation
|
|
61
65
|
|
|
62
|
-
|
|
63
|
-
- Open an issue in GitHub
|
|
64
|
-
- Suggest improvements via pull request
|
|
65
|
-
- Start a discussion in GitHub Discussions or the pull request thread
|
|
66
|
+
## Project Governance & Support
|
|
66
67
|
|
|
68
|
+
- [License](./LICENSE.txt)
|
|
69
|
+
- [Code of Conduct](./CODE_OF_CONDUCT.md)
|
|
70
|
+
- [Contributing](./CONTRIBUTING.md)
|
|
71
|
+
- [Security](./SECURITY.md)
|
package/package.json
CHANGED
|
@@ -87,7 +87,7 @@ Generates flow metadata element by element. This step is **mandatory** and must
|
|
|
87
87
|
- When `isComplete` is `true`, extract the flow metadata from the `result` field.
|
|
88
88
|
- If errors are returned, stop the loop and surface the error to the user.
|
|
89
89
|
|
|
90
|
-
**STRICT CONSTRAINTS (CRITICAL):**
|
|
90
|
+
**STRICT CONSTRAINTS (CRITICAL) β These rules apply to the XML returned by the generation pipeline:**
|
|
91
91
|
- DO NOT modify the content, values, or child nodes inside any block.
|
|
92
92
|
- DO NOT add new nodes, tags, attributes, or text (do not add missing labels, X/Y coordinates, etc.).
|
|
93
93
|
- DO NOT remove any existing nodes.
|
|
@@ -334,6 +334,7 @@ Call repeatedly with the same `operationId` until `isComplete` is `true` or erro
|
|
|
334
334
|
## Mandatory Best Practices
|
|
335
335
|
- **ALWAYS** follow the 3-step pipeline: fetchGroundedObjectMetadata β flowElementSelection β flowElementGeneration. This is the ONLY way to generate flow metadata. There are no alternatives.
|
|
336
336
|
- Do NOT manually create flow metadata XML, JSON, or any other format outside of this pipeline.
|
|
337
|
+
- **When the user explicitly requests fixes to validation or deployment errors** in an already-generated flow XML, you ARE permitted to make targeted manual edits to the XML to resolve those errors. This is the only exception to the "no manual metadata" rule.
|
|
337
338
|
- Do NOT attempt to "optimize" by skipping steps or combining steps. Each step is atomic and required.
|
|
338
339
|
- **NEVER** skip any step in the pipeline. All 3 steps are required.
|
|
339
340
|
- **NEVER** try to generate flow metadata without calling all 3 steps.
|
|
@@ -366,3 +367,4 @@ Call repeatedly with the same `operationId` until `isComplete` is `true` or erro
|
|
|
366
367
|
- [ ] **Multi-flow**: Each flow's full pipeline is completed before starting the next flow's pipeline (no interleaving)
|
|
367
368
|
- [ ] **result** field is used to extract the XML flow metadata only when `isComplete` is `true`
|
|
368
369
|
- [ ] **No additions to XML**: NO elements, attributes, or properties were added that were not present in the original pipeline output. Nothing was inserted (no `<label>`, `<description>`, or any other node). The final XML must be identical to what the pipeline returned.
|
|
370
|
+
- [ ] **Error fix exception**: If the user explicitly requested fixes to validation/deployment errors, targeted manual edits to the XML are permitted and the "No additions to XML" / "No manual metadata" constraints do not apply to those edits.
|