> For the complete documentation index, see [llms.txt](https://docs.stackai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.stackai.com/stackai-tools/skill-management/validate-skill.md).

# Validate Skill

Check proposed skill content before creating or updating a skill. Validation identifies structural problems and warnings without publishing a version.

## Check a proposed skill

1. Supply **Name**, **Description**, **Instructions**, and the same actions and supporting files you intend to publish.
2. Run the tool and check **Valid**, **Error Count**, and **Warning Count**.
3. Correct **Errors** and review **Warnings**. Inspect **Normalization** for changes that would be made during import.
4. Create or update the skill only after you have reviewed the result.

**Result:** **Valid** is true when the proposed content has no blocking validation errors.

## Behavior and troubleshooting

Validation does not run the skill against a real task or prove that an external service connection works. After publication, check the skill in the agent and workflow where it will be used.

## Inputs

| Field                   | Parameter      | Description                                                      |
| ----------------------- | -------------- | ---------------------------------------------------------------- |
| Name (required)         | `name`         | The proposed skill's name.                                       |
| Description (required)  | `description`  | What the proposed skill does and when to use it.                 |
| Instructions (required) | `instructions` | The proposed skill's instructions, in markdown.                  |
| File Source             | `file_source`  | Choose how all optional supporting files are provided.           |
| Supporting Files        | `text_files`   | Optional text files, each with a bundle name and inline content. |
| Supporting Files        | `url_files`    | Optional files fetched from URLs, each with its bundle name.     |
| Actions                 | `actions`      | Action refs to check alongside the bundle.                       |

## Outputs

| Field         | Parameter       | Description                                      |
| ------------- | --------------- | ------------------------------------------------ |
| Summary       | `summary`       | One-line verdict on the bundle.                  |
| Valid         | `valid`         | True when the bundle has no errors.              |
| Error Count   | `error_count`   | Number of blocking problems found.               |
| Warning Count | `warning_count` | Number of non-blocking problems found.           |
| Errors        | `errors`        | Blocking problems, one message each.             |
| Warnings      | `warnings`      | Non-blocking problems, one message each.         |
| Normalization | `normalization` | Preview of what the import process would change. |

## Related guidance

[Skill Instructions, Files, and Action References](https://docs.stackai.com/technical-reference/models-agents-and-skills/skill-instructions-files-and-action-references.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.stackai.com/stackai-tools/skill-management/validate-skill.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
