> 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-mcp/tool-reference/skills-and-versions/skills-validate.md).

# skills\_validate

Validate a proposed file bundle without saving and preview normalization.

**Effect:** This call reads data and does not run or change a project.

## Inputs

| Name      | Type                  | Requirement | Description                                                                                                                                            |
| --------- | --------------------- | ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ |
| `files`   | array of file objects | Required    | Array of `{path, content_base64}`. Include a root `SKILL.md` with `name` and `description` frontmatter. Paths must be relative, with no `..` segments. |
| `actions` | array of strings      | Optional    | Complete array of `provider_id.action_id` references. On skill update, omission or null clears the existing references.                                |

Each file contains `path` (relative path) and `content_base64` (standard base64). File mode requires `SKILL.md` at the root. Its YAML frontmatter must include `name` and `description`.

## Example

These are MCP tool arguments, not an HTTP request body. Replace bracketed IDs with values returned from your account.

```json
{
  "files": [
    {
      "path": "SKILL.md",
      "content_base64": "LS0tCm5hbWU6IEV2aWRlbmNlLWJhc2VkIGFuc3dlcnMKZGVzY3JpcHRpb246IEFuc3dlciB1c2luZyBzdXBwbGllZCBldmlkZW5jZS4KLS0tCkNpdGUgc291cmNlcyBhbmQgaWRlbnRpZnkgbWlzc2luZyBpbmZvcm1hdGlvbi4K"
    }
  ]
}
```

## Result

Abbreviated result example; unshown fields are omitted for clarity.

```json
{
  "valid": true,
  "error_count": 0,
  "warning_count": 0,
  "findings": []
}
```

## Behavior

Returns valid, error/warning counts, findings and normalization.

Checks action-reference format, not live catalog existence; create/update also checks the live catalog.

A root SKILL.md is required.

MCP inline limits are 50 files, 100 KiB per decoded file and 150 KiB total; larger bundles belong in the web UI.

Supporting files imply computer.terminal; inspect mapped, unmapped and implied actions.

## Troubleshooting

Correct error-severity findings first. This checks action-reference format; creation or update also checks that the referenced actions exist.

## Related resources

[Skills and versions](https://docs.stackai.com/stackai-mcp/tool-reference/skills-and-versions.md)

[Connection, permissions, pagination, and recovery](https://docs.stackai.com/stackai-mcp/best-practices-and-troubleshooting.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-mcp/tool-reference/skills-and-versions/skills-validate.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.
