Agent Platform API . projects . locations . skills

Instance Methods

operations()

Returns the operations Resource.

revisions()

Returns the revisions Resource.

close()

Close httplib2 connections.

create(parent, body=None, skillId=None, x__xgafv=None)

Create a Skill.

delete(name, x__xgafv=None)

Delete a Skill.

get(name, x__xgafv=None)

Get a Skill.

list(parent, pageSize=None, pageToken=None, x__xgafv=None)

List Skills.

list_next()

Retrieves the next page of results.

patch(name, body=None, updateMask=None, x__xgafv=None)

Update a Skill.

retrieve(parent, query=None, topK=None, x__xgafv=None)

Retrieves skills.

Method Details

close()
Close httplib2 connections.
create(parent, body=None, skillId=None, x__xgafv=None)
Create a Skill.

Args:
  parent: string, Required. The location to create the Skill in. Format: `projects/{project}/locations/{location}` (required)
  body: object, The request body.
    The object takes the form of:

{ # A skill.
  "compatibility": "A String", # Optional. Specifies the compatibility of the Skill. Indicates environment requirements (intended product, system packages, network access, etc.). This should align with `compatibility` in the `SKILL.md` file.
  "createTime": "A String", # Output only. Timestamp when this Skill was created.
  "description": "A String", # Required. Describes the Skill. Should describe both what the skill does and when to use it. Should include specific keywords that help agents identify relevant tasks. This should align with `description` in the `SKILL.md` file.
  "displayName": "A String", # Required. Provides the display name of the Skill. This should align with `name` in the `SKILL.md` file.
  "labels": { # The labels with user-defined metadata to organize Skills.
    "a_key": "A String",
  },
  "license": "A String", # Optional. Specifies the license of the Skill. This should be an SPDX license identifier (e.g., "MIT", "Apache-2.0"). See https://spdx.org/licenses/. This should align with `license` in the `SKILL.md` file.
  "name": "A String", # Identifier. The resource name of the Skill. Format: `projects/{project}/locations/{location}/skills/{skill}`
  "sha256": "A String", # Output only. The SHA256 checksum of the zipped filesystem.
  "skillSource": "A String", # Output only. The source of the Skill.
  "state": "A String", # Output only. The state of the Skill.
  "updateTime": "A String", # Output only. Timestamp when this Skill was most recently updated.
  "zippedFilesystem": "A String", # Required. Provides the zipped filesystem of the Skill. This should contain the `SKILL.md` file at the root of the zip and optional directories for scripts, references, and assets. Directory should align with the directory structure specified at https://agentskills.io/specification#directory-structure.
}

  skillId: string, Optional. The ID to use for the Skill, which will become the final component of the Skill's resource name. If not provided, a system-generated ID will be used. This value must be 1-63 characters. Valid characters are lowercase letters, numbers, and hyphens. The first character must be a lowercase letter, and the last character must be a lowercase letter or a number. Specifically, the ID must match the regular expression: `^[a-z]([a-z0-9-]{0,61}[a-z0-9])?$` See [AIP-122](https://aip.dev/122#resource-id-segments) for more details.
  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # This resource represents a long-running operation that is the result of a network API call.
  "done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
  "error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
    "code": 42, # The status code, which should be an enum value of google.rpc.Code.
    "details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
      {
        "a_key": "", # Properties of the object. Contains field @type with type URL.
      },
    ],
    "message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
  },
  "metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
    "a_key": "", # Properties of the object. Contains field @type with type URL.
  },
  "name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
  "response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
    "a_key": "", # Properties of the object. Contains field @type with type URL.
  },
}
delete(name, x__xgafv=None)
Delete a Skill.

Args:
  name: string, Required. The resource name of the Skill to delete. Format: `projects/{project}/locations/{location}/skills/{skill}` (required)
  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # This resource represents a long-running operation that is the result of a network API call.
  "done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
  "error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
    "code": 42, # The status code, which should be an enum value of google.rpc.Code.
    "details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
      {
        "a_key": "", # Properties of the object. Contains field @type with type URL.
      },
    ],
    "message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
  },
  "metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
    "a_key": "", # Properties of the object. Contains field @type with type URL.
  },
  "name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
  "response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
    "a_key": "", # Properties of the object. Contains field @type with type URL.
  },
}
get(name, x__xgafv=None)
Get a Skill.

Args:
  name: string, Required. The resource name of the Skill to retrieve. Format: `projects/{project}/locations/{location}/skills/{skill}` (required)
  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # A skill.
  "compatibility": "A String", # Optional. Specifies the compatibility of the Skill. Indicates environment requirements (intended product, system packages, network access, etc.). This should align with `compatibility` in the `SKILL.md` file.
  "createTime": "A String", # Output only. Timestamp when this Skill was created.
  "description": "A String", # Required. Describes the Skill. Should describe both what the skill does and when to use it. Should include specific keywords that help agents identify relevant tasks. This should align with `description` in the `SKILL.md` file.
  "displayName": "A String", # Required. Provides the display name of the Skill. This should align with `name` in the `SKILL.md` file.
  "labels": { # The labels with user-defined metadata to organize Skills.
    "a_key": "A String",
  },
  "license": "A String", # Optional. Specifies the license of the Skill. This should be an SPDX license identifier (e.g., "MIT", "Apache-2.0"). See https://spdx.org/licenses/. This should align with `license` in the `SKILL.md` file.
  "name": "A String", # Identifier. The resource name of the Skill. Format: `projects/{project}/locations/{location}/skills/{skill}`
  "sha256": "A String", # Output only. The SHA256 checksum of the zipped filesystem.
  "skillSource": "A String", # Output only. The source of the Skill.
  "state": "A String", # Output only. The state of the Skill.
  "updateTime": "A String", # Output only. Timestamp when this Skill was most recently updated.
  "zippedFilesystem": "A String", # Required. Provides the zipped filesystem of the Skill. This should contain the `SKILL.md` file at the root of the zip and optional directories for scripts, references, and assets. Directory should align with the directory structure specified at https://agentskills.io/specification#directory-structure.
}
list(parent, pageSize=None, pageToken=None, x__xgafv=None)
List Skills.

Args:
  parent: string, Required. The location to list the Skills in. Format: `projects/{project}/locations/{location}` (required)
  pageSize: integer, Optional. The standard list page size.
  pageToken: string, Optional. The standard list page token.
  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # Response message for SkillRegistryService.ListSkills.
  "nextPageToken": "A String", # A token, which can be sent as ListSkillsRequest.page_token to retrieve the next page. If this field is omitted, there are no subsequent pages.
  "skills": [ # The Skills.
    { # A skill.
      "compatibility": "A String", # Optional. Specifies the compatibility of the Skill. Indicates environment requirements (intended product, system packages, network access, etc.). This should align with `compatibility` in the `SKILL.md` file.
      "createTime": "A String", # Output only. Timestamp when this Skill was created.
      "description": "A String", # Required. Describes the Skill. Should describe both what the skill does and when to use it. Should include specific keywords that help agents identify relevant tasks. This should align with `description` in the `SKILL.md` file.
      "displayName": "A String", # Required. Provides the display name of the Skill. This should align with `name` in the `SKILL.md` file.
      "labels": { # The labels with user-defined metadata to organize Skills.
        "a_key": "A String",
      },
      "license": "A String", # Optional. Specifies the license of the Skill. This should be an SPDX license identifier (e.g., "MIT", "Apache-2.0"). See https://spdx.org/licenses/. This should align with `license` in the `SKILL.md` file.
      "name": "A String", # Identifier. The resource name of the Skill. Format: `projects/{project}/locations/{location}/skills/{skill}`
      "sha256": "A String", # Output only. The SHA256 checksum of the zipped filesystem.
      "skillSource": "A String", # Output only. The source of the Skill.
      "state": "A String", # Output only. The state of the Skill.
      "updateTime": "A String", # Output only. Timestamp when this Skill was most recently updated.
      "zippedFilesystem": "A String", # Required. Provides the zipped filesystem of the Skill. This should contain the `SKILL.md` file at the root of the zip and optional directories for scripts, references, and assets. Directory should align with the directory structure specified at https://agentskills.io/specification#directory-structure.
    },
  ],
}
list_next()
Retrieves the next page of results.

        Args:
          previous_request: The request for the previous page. (required)
          previous_response: The response from the request for the previous page. (required)

        Returns:
          A request object that you can call 'execute()' on to request the next
          page. Returns None if there are no more items in the collection.
        
patch(name, body=None, updateMask=None, x__xgafv=None)
Update a Skill.

Args:
  name: string, Identifier. The resource name of the Skill. Format: `projects/{project}/locations/{location}/skills/{skill}` (required)
  body: object, The request body.
    The object takes the form of:

{ # A skill.
  "compatibility": "A String", # Optional. Specifies the compatibility of the Skill. Indicates environment requirements (intended product, system packages, network access, etc.). This should align with `compatibility` in the `SKILL.md` file.
  "createTime": "A String", # Output only. Timestamp when this Skill was created.
  "description": "A String", # Required. Describes the Skill. Should describe both what the skill does and when to use it. Should include specific keywords that help agents identify relevant tasks. This should align with `description` in the `SKILL.md` file.
  "displayName": "A String", # Required. Provides the display name of the Skill. This should align with `name` in the `SKILL.md` file.
  "labels": { # The labels with user-defined metadata to organize Skills.
    "a_key": "A String",
  },
  "license": "A String", # Optional. Specifies the license of the Skill. This should be an SPDX license identifier (e.g., "MIT", "Apache-2.0"). See https://spdx.org/licenses/. This should align with `license` in the `SKILL.md` file.
  "name": "A String", # Identifier. The resource name of the Skill. Format: `projects/{project}/locations/{location}/skills/{skill}`
  "sha256": "A String", # Output only. The SHA256 checksum of the zipped filesystem.
  "skillSource": "A String", # Output only. The source of the Skill.
  "state": "A String", # Output only. The state of the Skill.
  "updateTime": "A String", # Output only. Timestamp when this Skill was most recently updated.
  "zippedFilesystem": "A String", # Required. Provides the zipped filesystem of the Skill. This should contain the `SKILL.md` file at the root of the zip and optional directories for scripts, references, and assets. Directory should align with the directory structure specified at https://agentskills.io/specification#directory-structure.
}

  updateMask: string, Optional. Mask specifying which fields to update.
  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # This resource represents a long-running operation that is the result of a network API call.
  "done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
  "error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
    "code": 42, # The status code, which should be an enum value of google.rpc.Code.
    "details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
      {
        "a_key": "", # Properties of the object. Contains field @type with type URL.
      },
    ],
    "message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
  },
  "metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
    "a_key": "", # Properties of the object. Contains field @type with type URL.
  },
  "name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
  "response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
    "a_key": "", # Properties of the object. Contains field @type with type URL.
  },
}
retrieve(parent, query=None, topK=None, x__xgafv=None)
Retrieves skills.

Args:
  parent: string, Required. The location to retrieve the Skills in. Format: `projects/{project}/locations/{location}` (required)
  query: string, Optional. The query to find matching skills.
  topK: integer, Optional. The maximum number of skills to return. The service may return fewer than this value. If unspecified, at most 10 skills will be returned. The maximum value is 100.
  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # Response message for SkillRegistryService.RetrieveSkills.
  "retrievedSkills": [ # Skills ranked by similarity if applicable; otherwise, the order is undefined.
    { # A retrieved skill.
      "description": "A String", # The skill description.
      "skillName": "A String", # The skill resource name. Format: projects/{project}/locations/{location}/skills/{skill}
    },
  ],
}