Returns the revisions Resource.
Close httplib2 connections.
create(parent, body=None, requestId=None, skillId=None, x__xgafv=None)
========================================================================= # Skills Collection APIs Creates a Skill resource container, optionally publishing the initial SkillRevision inline in a single, atomic CRUD roundtrip.
delete(name, force=None, requestId=None, x__xgafv=None)
Deletes a Skill container along with all its revisions.
Fetches the active configuration and metadata of a Skill.
list(parent, filter=None, orderBy=None, pageSize=None, pageToken=None, x__xgafv=None)
Lists logical Skills available in a project.
Retrieves the next page of results.
patch(name, body=None, requestId=None, updateMask=None, x__xgafv=None)
Updates Skill metadata or overrides active pointers/state using REST standard PATCH.
Custom deep-search method to filter by frontmatter or query SKILL.md text blobs.
Retrieves the next page of results.
close()
Close httplib2 connections.
create(parent, body=None, requestId=None, skillId=None, x__xgafv=None)
========================================================================= # Skills Collection APIs Creates a Skill resource container, optionally publishing the initial SkillRevision inline in a single, atomic CRUD roundtrip.
Args:
parent: string, Required. The project and location location to bootstrap. (required)
body: object, The request body.
The object takes the form of:
{ # Represents an Executable Agent Skill or a Composite Tool Suite (Bundle). Sibling resource with Agent and McpServer under agentregistry.googleapis.com.
"createTime": "A String", # Output only. Create time.
"defaultRevision": "A String", # Optional. The full resource name of the revision currently served by default (floating track). Format: `projects/{project}/locations/{location}/skills/{skill}/revisions/{revision}`
"description": "A String", # Optional. Brief summary describing the capabilities of the skill. Maximum length is 2048 characters.
"displayName": "A String", # Required. Human-readable display name of the skill. Maximum length is 128 characters.
"frontmatter": { # Structured metadata attributes extracted from the package's local SKILL.md frontmatter. # Output only. Lightweight frontmatter metadata attributes copied from the default revision.
"compatibility": "A String", # Optional. Environmental dependencies or local sidecars.
"description": "A String", # Required. Functional description.
"license": "A String", # Optional. License.
"metadata": { # Optional. Extensible flattened map mapping custom tags, authors, and version parameters.
"a_key": "A String",
},
"name": "A String", # Required. The name of the skill.
},
"initialRevision": { # Represents an immutable, versioned snapshot of a Skill package. # Optional. Input only. Optional nested initial revision payload to support standard one-shot creation. The server processes this field on input during creation but must never return it in responses.
"archiveUploadSource": { # Direct write-only raw archive payload upload. # Optional. Immutable. Direct write-only raw archive upload source.
"archiveContent": "A String", # Required. Input only. Write-only raw ZIP/TAR archive payload bytes containing the skill package.
},
"createTime": "A String", # Output only. Revision creation timestamp.
"frontmatter": { # Structured metadata attributes extracted from the package's local SKILL.md frontmatter. # Output only. Extracted YAML frontmatter configuration snapshot.
"compatibility": "A String", # Optional. Environmental dependencies or local sidecars.
"description": "A String", # Required. Functional description.
"license": "A String", # Optional. License.
"metadata": { # Optional. Extensible flattened map mapping custom tags, authors, and version parameters.
"a_key": "A String",
},
"name": "A String", # Required. The name of the skill.
},
"gcsSource": { # Specifications for Cloud Storage objects. # Optional. Immutable. Cloud Storage object generation URI.
"generation": "A String", # Optional. Cloud Storage object generation ID. If not specified, the latest generation is used.
"uri": "A String", # Required. Cloud Storage object URI. Format: `gs://{bucket_name}/{object_name}`
},
"name": "A String", # Identifier. Resource name of the SkillRevision. Format: `projects/{project}/locations/{location}/skills/{skill}/revisions/{revision}`
"sha256Hash": "A String", # Output only. Cryptographic SHA-256 integrity and deduplication digest of the payload zip.
"sizeBytes": "A String", # Output only. Size of the compiled zip payload in bytes (assists client download progress).
"state": "A String", # Output only. The system-managed lifecycle state of this revision.
"uid": "A String", # Output only. Universally unique identifier (UUID4) for the skill revision.
},
"name": "A String", # Identifier. Resource name of the Skill. Format: `projects/{project}/locations/{location}/skills/{skill}` The `{skill}` segment acts as the resource ID. If the skill is associated with a Publisher, this segment typically uses a hyphenated namespace prefix corresponding to the publisher (e.g., `google-workspace-create-docs`).
"publisher": "A String", # Optional. The publisher resource associated with this skill. Format: `projects/{project}/locations/{location}/publishers/{publisher}` The publisher dictates the allowed namespace prefixes for the skill's name and logical `skill_id` (e.g., Publisher `google` authorizes the `google-*` prefix).
"skillId": "A String", # Output only. A stable, globally unique logical identifier for the skill. It is securely constructed by the backend by combining the associated `publisher`'s verified namespace and the skill's resource ID to enforce strict ownership. For example, the prefix `google-` is reserved exclusively for first-party Google publishers to prevent namespace squatting. Example: `urn:skill:google-workspace:create-docs`
"state": "A String", # Output only. The system-managed state of the skill.
"targetState": "A String", # Required. User-managed target state of the skill.
"type": "A String", # Required. Structural deployment type (SIMPLE leaf vs COMPOSITE bundle).
"uid": "A String", # Output only. Universally unique identifier (UUID4) for the logical container.
"updateTime": "A String", # Output only. Update time.
}
requestId: string, Optional. Signed UUID request idempotency token.
skillId: string, Required. Custom, user-defined unique container identifier. Must be unique within the parent project and location. This value should be 4-63 characters, and valid characters are `/a-z-/`.
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, force=None, requestId=None, x__xgafv=None)
Deletes a Skill container along with all its revisions.
Args:
name: string, Required. Target Skill container name to remove. (required)
force: boolean, Optional. If set to true, any child SkillRevisions under this Skill will also be deleted. Otherwise, the request will only succeed if the Skill has no child SkillRevisions.
requestId: string, Optional. Signed UUID request idempotency token.
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)
Fetches the active configuration and metadata of a Skill.
Args:
name: string, Required. Target resource container name. (required)
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # Represents an Executable Agent Skill or a Composite Tool Suite (Bundle). Sibling resource with Agent and McpServer under agentregistry.googleapis.com.
"createTime": "A String", # Output only. Create time.
"defaultRevision": "A String", # Optional. The full resource name of the revision currently served by default (floating track). Format: `projects/{project}/locations/{location}/skills/{skill}/revisions/{revision}`
"description": "A String", # Optional. Brief summary describing the capabilities of the skill. Maximum length is 2048 characters.
"displayName": "A String", # Required. Human-readable display name of the skill. Maximum length is 128 characters.
"frontmatter": { # Structured metadata attributes extracted from the package's local SKILL.md frontmatter. # Output only. Lightweight frontmatter metadata attributes copied from the default revision.
"compatibility": "A String", # Optional. Environmental dependencies or local sidecars.
"description": "A String", # Required. Functional description.
"license": "A String", # Optional. License.
"metadata": { # Optional. Extensible flattened map mapping custom tags, authors, and version parameters.
"a_key": "A String",
},
"name": "A String", # Required. The name of the skill.
},
"initialRevision": { # Represents an immutable, versioned snapshot of a Skill package. # Optional. Input only. Optional nested initial revision payload to support standard one-shot creation. The server processes this field on input during creation but must never return it in responses.
"archiveUploadSource": { # Direct write-only raw archive payload upload. # Optional. Immutable. Direct write-only raw archive upload source.
"archiveContent": "A String", # Required. Input only. Write-only raw ZIP/TAR archive payload bytes containing the skill package.
},
"createTime": "A String", # Output only. Revision creation timestamp.
"frontmatter": { # Structured metadata attributes extracted from the package's local SKILL.md frontmatter. # Output only. Extracted YAML frontmatter configuration snapshot.
"compatibility": "A String", # Optional. Environmental dependencies or local sidecars.
"description": "A String", # Required. Functional description.
"license": "A String", # Optional. License.
"metadata": { # Optional. Extensible flattened map mapping custom tags, authors, and version parameters.
"a_key": "A String",
},
"name": "A String", # Required. The name of the skill.
},
"gcsSource": { # Specifications for Cloud Storage objects. # Optional. Immutable. Cloud Storage object generation URI.
"generation": "A String", # Optional. Cloud Storage object generation ID. If not specified, the latest generation is used.
"uri": "A String", # Required. Cloud Storage object URI. Format: `gs://{bucket_name}/{object_name}`
},
"name": "A String", # Identifier. Resource name of the SkillRevision. Format: `projects/{project}/locations/{location}/skills/{skill}/revisions/{revision}`
"sha256Hash": "A String", # Output only. Cryptographic SHA-256 integrity and deduplication digest of the payload zip.
"sizeBytes": "A String", # Output only. Size of the compiled zip payload in bytes (assists client download progress).
"state": "A String", # Output only. The system-managed lifecycle state of this revision.
"uid": "A String", # Output only. Universally unique identifier (UUID4) for the skill revision.
},
"name": "A String", # Identifier. Resource name of the Skill. Format: `projects/{project}/locations/{location}/skills/{skill}` The `{skill}` segment acts as the resource ID. If the skill is associated with a Publisher, this segment typically uses a hyphenated namespace prefix corresponding to the publisher (e.g., `google-workspace-create-docs`).
"publisher": "A String", # Optional. The publisher resource associated with this skill. Format: `projects/{project}/locations/{location}/publishers/{publisher}` The publisher dictates the allowed namespace prefixes for the skill's name and logical `skill_id` (e.g., Publisher `google` authorizes the `google-*` prefix).
"skillId": "A String", # Output only. A stable, globally unique logical identifier for the skill. It is securely constructed by the backend by combining the associated `publisher`'s verified namespace and the skill's resource ID to enforce strict ownership. For example, the prefix `google-` is reserved exclusively for first-party Google publishers to prevent namespace squatting. Example: `urn:skill:google-workspace:create-docs`
"state": "A String", # Output only. The system-managed state of the skill.
"targetState": "A String", # Required. User-managed target state of the skill.
"type": "A String", # Required. Structural deployment type (SIMPLE leaf vs COMPOSITE bundle).
"uid": "A String", # Output only. Universally unique identifier (UUID4) for the logical container.
"updateTime": "A String", # Output only. Update time.
}
list(parent, filter=None, orderBy=None, pageSize=None, pageToken=None, x__xgafv=None)
Lists logical Skills available in a project.
Args:
parent: string, Required. Parent value for ListSkillsRequest (required)
filter: string, Optional. Use this field to specify filter criteria on list results. Filter expressions can be used to restrict results based upon filterable fields, where equality operators can be used. See [instructions](https://docs.cloud.google.com/agent-registry/search-agents-and-tools) for more details. Allowed operators: `=`, `<`, `>`, `NOT`, `AND`, `OR`, and `()`. | Field | `=` | `<`, `>` | |--------------|-----|----------| | state | Yes | No | | targetState | Yes | No | | createTime | Yes | Yes | | updateTime | Yes | Yes | Examples: * `state=ACTIVE` to restrict results to skills in the `ACTIVE` state.
orderBy: string, Optional. Hint for how to order the results
pageSize: integer, Optional. Requested page size. Server may return fewer items than requested. If unspecified, server will pick an appropriate default.
pageToken: string, Optional. A token identifying a page of results the server should return.
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # Response structure listing logical Skills.
"nextPageToken": "A String", # Page continuation continuation token.
"skills": [ # Returned container list.
{ # Represents an Executable Agent Skill or a Composite Tool Suite (Bundle). Sibling resource with Agent and McpServer under agentregistry.googleapis.com.
"createTime": "A String", # Output only. Create time.
"defaultRevision": "A String", # Optional. The full resource name of the revision currently served by default (floating track). Format: `projects/{project}/locations/{location}/skills/{skill}/revisions/{revision}`
"description": "A String", # Optional. Brief summary describing the capabilities of the skill. Maximum length is 2048 characters.
"displayName": "A String", # Required. Human-readable display name of the skill. Maximum length is 128 characters.
"frontmatter": { # Structured metadata attributes extracted from the package's local SKILL.md frontmatter. # Output only. Lightweight frontmatter metadata attributes copied from the default revision.
"compatibility": "A String", # Optional. Environmental dependencies or local sidecars.
"description": "A String", # Required. Functional description.
"license": "A String", # Optional. License.
"metadata": { # Optional. Extensible flattened map mapping custom tags, authors, and version parameters.
"a_key": "A String",
},
"name": "A String", # Required. The name of the skill.
},
"initialRevision": { # Represents an immutable, versioned snapshot of a Skill package. # Optional. Input only. Optional nested initial revision payload to support standard one-shot creation. The server processes this field on input during creation but must never return it in responses.
"archiveUploadSource": { # Direct write-only raw archive payload upload. # Optional. Immutable. Direct write-only raw archive upload source.
"archiveContent": "A String", # Required. Input only. Write-only raw ZIP/TAR archive payload bytes containing the skill package.
},
"createTime": "A String", # Output only. Revision creation timestamp.
"frontmatter": { # Structured metadata attributes extracted from the package's local SKILL.md frontmatter. # Output only. Extracted YAML frontmatter configuration snapshot.
"compatibility": "A String", # Optional. Environmental dependencies or local sidecars.
"description": "A String", # Required. Functional description.
"license": "A String", # Optional. License.
"metadata": { # Optional. Extensible flattened map mapping custom tags, authors, and version parameters.
"a_key": "A String",
},
"name": "A String", # Required. The name of the skill.
},
"gcsSource": { # Specifications for Cloud Storage objects. # Optional. Immutable. Cloud Storage object generation URI.
"generation": "A String", # Optional. Cloud Storage object generation ID. If not specified, the latest generation is used.
"uri": "A String", # Required. Cloud Storage object URI. Format: `gs://{bucket_name}/{object_name}`
},
"name": "A String", # Identifier. Resource name of the SkillRevision. Format: `projects/{project}/locations/{location}/skills/{skill}/revisions/{revision}`
"sha256Hash": "A String", # Output only. Cryptographic SHA-256 integrity and deduplication digest of the payload zip.
"sizeBytes": "A String", # Output only. Size of the compiled zip payload in bytes (assists client download progress).
"state": "A String", # Output only. The system-managed lifecycle state of this revision.
"uid": "A String", # Output only. Universally unique identifier (UUID4) for the skill revision.
},
"name": "A String", # Identifier. Resource name of the Skill. Format: `projects/{project}/locations/{location}/skills/{skill}` The `{skill}` segment acts as the resource ID. If the skill is associated with a Publisher, this segment typically uses a hyphenated namespace prefix corresponding to the publisher (e.g., `google-workspace-create-docs`).
"publisher": "A String", # Optional. The publisher resource associated with this skill. Format: `projects/{project}/locations/{location}/publishers/{publisher}` The publisher dictates the allowed namespace prefixes for the skill's name and logical `skill_id` (e.g., Publisher `google` authorizes the `google-*` prefix).
"skillId": "A String", # Output only. A stable, globally unique logical identifier for the skill. It is securely constructed by the backend by combining the associated `publisher`'s verified namespace and the skill's resource ID to enforce strict ownership. For example, the prefix `google-` is reserved exclusively for first-party Google publishers to prevent namespace squatting. Example: `urn:skill:google-workspace:create-docs`
"state": "A String", # Output only. The system-managed state of the skill.
"targetState": "A String", # Required. User-managed target state of the skill.
"type": "A String", # Required. Structural deployment type (SIMPLE leaf vs COMPOSITE bundle).
"uid": "A String", # Output only. Universally unique identifier (UUID4) for the logical container.
"updateTime": "A String", # Output only. Update time.
},
],
"unreachable": [ # Unreachable locations or failures.
"A String",
],
}
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, requestId=None, updateMask=None, x__xgafv=None)
Updates Skill metadata or overrides active pointers/state using REST standard PATCH.
Args:
name: string, Identifier. Resource name of the Skill. Format: `projects/{project}/locations/{location}/skills/{skill}` The `{skill}` segment acts as the resource ID. If the skill is associated with a Publisher, this segment typically uses a hyphenated namespace prefix corresponding to the publisher (e.g., `google-workspace-create-docs`). (required)
body: object, The request body.
The object takes the form of:
{ # Represents an Executable Agent Skill or a Composite Tool Suite (Bundle). Sibling resource with Agent and McpServer under agentregistry.googleapis.com.
"createTime": "A String", # Output only. Create time.
"defaultRevision": "A String", # Optional. The full resource name of the revision currently served by default (floating track). Format: `projects/{project}/locations/{location}/skills/{skill}/revisions/{revision}`
"description": "A String", # Optional. Brief summary describing the capabilities of the skill. Maximum length is 2048 characters.
"displayName": "A String", # Required. Human-readable display name of the skill. Maximum length is 128 characters.
"frontmatter": { # Structured metadata attributes extracted from the package's local SKILL.md frontmatter. # Output only. Lightweight frontmatter metadata attributes copied from the default revision.
"compatibility": "A String", # Optional. Environmental dependencies or local sidecars.
"description": "A String", # Required. Functional description.
"license": "A String", # Optional. License.
"metadata": { # Optional. Extensible flattened map mapping custom tags, authors, and version parameters.
"a_key": "A String",
},
"name": "A String", # Required. The name of the skill.
},
"initialRevision": { # Represents an immutable, versioned snapshot of a Skill package. # Optional. Input only. Optional nested initial revision payload to support standard one-shot creation. The server processes this field on input during creation but must never return it in responses.
"archiveUploadSource": { # Direct write-only raw archive payload upload. # Optional. Immutable. Direct write-only raw archive upload source.
"archiveContent": "A String", # Required. Input only. Write-only raw ZIP/TAR archive payload bytes containing the skill package.
},
"createTime": "A String", # Output only. Revision creation timestamp.
"frontmatter": { # Structured metadata attributes extracted from the package's local SKILL.md frontmatter. # Output only. Extracted YAML frontmatter configuration snapshot.
"compatibility": "A String", # Optional. Environmental dependencies or local sidecars.
"description": "A String", # Required. Functional description.
"license": "A String", # Optional. License.
"metadata": { # Optional. Extensible flattened map mapping custom tags, authors, and version parameters.
"a_key": "A String",
},
"name": "A String", # Required. The name of the skill.
},
"gcsSource": { # Specifications for Cloud Storage objects. # Optional. Immutable. Cloud Storage object generation URI.
"generation": "A String", # Optional. Cloud Storage object generation ID. If not specified, the latest generation is used.
"uri": "A String", # Required. Cloud Storage object URI. Format: `gs://{bucket_name}/{object_name}`
},
"name": "A String", # Identifier. Resource name of the SkillRevision. Format: `projects/{project}/locations/{location}/skills/{skill}/revisions/{revision}`
"sha256Hash": "A String", # Output only. Cryptographic SHA-256 integrity and deduplication digest of the payload zip.
"sizeBytes": "A String", # Output only. Size of the compiled zip payload in bytes (assists client download progress).
"state": "A String", # Output only. The system-managed lifecycle state of this revision.
"uid": "A String", # Output only. Universally unique identifier (UUID4) for the skill revision.
},
"name": "A String", # Identifier. Resource name of the Skill. Format: `projects/{project}/locations/{location}/skills/{skill}` The `{skill}` segment acts as the resource ID. If the skill is associated with a Publisher, this segment typically uses a hyphenated namespace prefix corresponding to the publisher (e.g., `google-workspace-create-docs`).
"publisher": "A String", # Optional. The publisher resource associated with this skill. Format: `projects/{project}/locations/{location}/publishers/{publisher}` The publisher dictates the allowed namespace prefixes for the skill's name and logical `skill_id` (e.g., Publisher `google` authorizes the `google-*` prefix).
"skillId": "A String", # Output only. A stable, globally unique logical identifier for the skill. It is securely constructed by the backend by combining the associated `publisher`'s verified namespace and the skill's resource ID to enforce strict ownership. For example, the prefix `google-` is reserved exclusively for first-party Google publishers to prevent namespace squatting. Example: `urn:skill:google-workspace:create-docs`
"state": "A String", # Output only. The system-managed state of the skill.
"targetState": "A String", # Required. User-managed target state of the skill.
"type": "A String", # Required. Structural deployment type (SIMPLE leaf vs COMPOSITE bundle).
"uid": "A String", # Output only. Universally unique identifier (UUID4) for the logical container.
"updateTime": "A String", # Output only. Update time.
}
requestId: string, Optional. Signed UUID request idempotency token.
updateMask: string, Optional. Standard update target mask mapping relative fields.
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.
},
}
search(parent, filter=None, pageSize=None, pageToken=None, searchString=None, searchType=None, x__xgafv=None)
Custom deep-search method to filter by frontmatter or query SKILL.md text blobs.
Args:
parent: string, Required. Parent value for SearchSkillsRequest. Format: `projects/{project}/locations/{location}`. (required)
filter: string, Optional. Use this field to specify additional filter criteria on search results. Filter expressions can be used to restrict results based upon filterable fields, where equality operators can be used. See [instructions](https://docs.cloud.google.com/agent-registry/search-agents-and-tools) for more details. Allowed operators: `=`, `<`, `>`, `NOT`, `AND`, `OR`, and `()`. | Field | `=` | `<`, `>` | |--------------|-----|----------| | state | Yes | No | | targetState | Yes | No | | createTime | Yes | Yes | | updateTime | Yes | Yes | Examples: * `state=ACTIVE` to restrict results to skills in the `ACTIVE` state.
pageSize: integer, Optional. The maximum number of search results to return per page. The page size is capped at `100`, even if a larger value is specified. A negative value will result in an `INVALID_ARGUMENT` error. If unspecified or set to `0`, a default value of `20` will be used. The server may return fewer results than requested.
pageToken: string, Optional. If present, retrieve the next batch of results from the preceding call to this method. `page_token` must be the value of `next_page_token` from the previous response. The values of all other method parameters, must be identical to those in the previous call.
searchString: string, Optional. Search criteria used to select the Skills to return. If no search criteria is specified then all accessible Skills will be returned. Search expressions can be used to restrict results based upon searchable fields, where the operators can be used along with the suffix wildcard symbol `*`. See [instructions](https://docs.cloud.google.com/agent-registry/search-agents-and-tools) for more details. Allowed operators: `=`, `:`, `NOT`, `AND`, `OR`, and `()`. Searchable fields: | Field | `=` | `:` | `*` | Keyword Search | |---------------------------|-----|-----|-----|----------------| | skillId | Yes | Yes | Yes | Included | | name | No | Yes | Yes | Included | | displayName | No | Yes | Yes | Included | | description | No | Yes | No | Included | | frontmatter.name | No | Yes | No | Included | | frontmatter.description | No | Yes | No | Included | | frontmatter.compatibility | No | Yes | No | Included | | frontmatter.license | No | Yes | No | Included | Examples: * `skillId="urn:skill:projects-1234:locations:global:private-important-skill"` to find the skill with the specified skill ID. * `name:important` to find skills whose name contains `important` as a word. * `displayName:works*` to find skills whose display name contains words that start with `works`.
searchType: string, Optional. The type of search.
Allowed values
SEARCH_TYPE_UNSPECIFIED - Invalid search type.
KEYWORD - Search for a keyword across all searchable fields.
SEMANTIC - Search based on the meaning and intent of a natural language query.
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # Response listing searched Skills.
"nextPageToken": "A String", # Query page offset continuation token.
"skills": [ # Matched Skills list.
{ # Represents an Executable Agent Skill or a Composite Tool Suite (Bundle). Sibling resource with Agent and McpServer under agentregistry.googleapis.com.
"createTime": "A String", # Output only. Create time.
"defaultRevision": "A String", # Optional. The full resource name of the revision currently served by default (floating track). Format: `projects/{project}/locations/{location}/skills/{skill}/revisions/{revision}`
"description": "A String", # Optional. Brief summary describing the capabilities of the skill. Maximum length is 2048 characters.
"displayName": "A String", # Required. Human-readable display name of the skill. Maximum length is 128 characters.
"frontmatter": { # Structured metadata attributes extracted from the package's local SKILL.md frontmatter. # Output only. Lightweight frontmatter metadata attributes copied from the default revision.
"compatibility": "A String", # Optional. Environmental dependencies or local sidecars.
"description": "A String", # Required. Functional description.
"license": "A String", # Optional. License.
"metadata": { # Optional. Extensible flattened map mapping custom tags, authors, and version parameters.
"a_key": "A String",
},
"name": "A String", # Required. The name of the skill.
},
"initialRevision": { # Represents an immutable, versioned snapshot of a Skill package. # Optional. Input only. Optional nested initial revision payload to support standard one-shot creation. The server processes this field on input during creation but must never return it in responses.
"archiveUploadSource": { # Direct write-only raw archive payload upload. # Optional. Immutable. Direct write-only raw archive upload source.
"archiveContent": "A String", # Required. Input only. Write-only raw ZIP/TAR archive payload bytes containing the skill package.
},
"createTime": "A String", # Output only. Revision creation timestamp.
"frontmatter": { # Structured metadata attributes extracted from the package's local SKILL.md frontmatter. # Output only. Extracted YAML frontmatter configuration snapshot.
"compatibility": "A String", # Optional. Environmental dependencies or local sidecars.
"description": "A String", # Required. Functional description.
"license": "A String", # Optional. License.
"metadata": { # Optional. Extensible flattened map mapping custom tags, authors, and version parameters.
"a_key": "A String",
},
"name": "A String", # Required. The name of the skill.
},
"gcsSource": { # Specifications for Cloud Storage objects. # Optional. Immutable. Cloud Storage object generation URI.
"generation": "A String", # Optional. Cloud Storage object generation ID. If not specified, the latest generation is used.
"uri": "A String", # Required. Cloud Storage object URI. Format: `gs://{bucket_name}/{object_name}`
},
"name": "A String", # Identifier. Resource name of the SkillRevision. Format: `projects/{project}/locations/{location}/skills/{skill}/revisions/{revision}`
"sha256Hash": "A String", # Output only. Cryptographic SHA-256 integrity and deduplication digest of the payload zip.
"sizeBytes": "A String", # Output only. Size of the compiled zip payload in bytes (assists client download progress).
"state": "A String", # Output only. The system-managed lifecycle state of this revision.
"uid": "A String", # Output only. Universally unique identifier (UUID4) for the skill revision.
},
"name": "A String", # Identifier. Resource name of the Skill. Format: `projects/{project}/locations/{location}/skills/{skill}` The `{skill}` segment acts as the resource ID. If the skill is associated with a Publisher, this segment typically uses a hyphenated namespace prefix corresponding to the publisher (e.g., `google-workspace-create-docs`).
"publisher": "A String", # Optional. The publisher resource associated with this skill. Format: `projects/{project}/locations/{location}/publishers/{publisher}` The publisher dictates the allowed namespace prefixes for the skill's name and logical `skill_id` (e.g., Publisher `google` authorizes the `google-*` prefix).
"skillId": "A String", # Output only. A stable, globally unique logical identifier for the skill. It is securely constructed by the backend by combining the associated `publisher`'s verified namespace and the skill's resource ID to enforce strict ownership. For example, the prefix `google-` is reserved exclusively for first-party Google publishers to prevent namespace squatting. Example: `urn:skill:google-workspace:create-docs`
"state": "A String", # Output only. The system-managed state of the skill.
"targetState": "A String", # Required. User-managed target state of the skill.
"type": "A String", # Required. Structural deployment type (SIMPLE leaf vs COMPOSITE bundle).
"uid": "A String", # Output only. Universally unique identifier (UUID4) for the logical container.
"updateTime": "A String", # Output only. Update time.
},
],
}
search_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.